mirror of
https://github.com/vladmandic/automatic
synced 2026-09-19 17:24:32 +02:00
pre merge cleanup
This commit is contained in:
Vladimir Mandic
+2
-2
@@ -71,7 +71,7 @@ echo "- nVIDIA: $SMI"
|
||||
|
||||
git-version () {
|
||||
pushd $1 >/dev/null
|
||||
BRANCH=$(git branch | tail -1 | awk '{print $NF}')
|
||||
BRANCH=$(git branch | grep -E 'main|master' | tail -1 | awk '{print $NF}')
|
||||
VER=$(git log -1 --pretty=format:"%h %ad")
|
||||
URL=$(git remote get-url origin)
|
||||
popd >/dev/null
|
||||
@@ -80,7 +80,7 @@ git-version () {
|
||||
|
||||
git-update () {
|
||||
pushd $1 >/dev/null
|
||||
BRANCH=$(git branch | tail -1 | awk '{print $NF}')
|
||||
BRANCH=$(git branch | grep -E 'main|master' | tail -1 | awk '{print $NF}')
|
||||
git checkout --quiet $BRANCH
|
||||
git pull --quiet --rebase --autostash
|
||||
popd >/dev/null
|
||||
|
||||
@@ -0,0 +1,161 @@
|
||||
# Stable Diffusion web UI
|
||||
A browser interface based on Gradio library for Stable Diffusion.
|
||||
|
||||
|
||||
|
||||
## Features
|
||||
[Detailed feature showcase with images](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Features):
|
||||
- Original txt2img and img2img modes
|
||||
- One click install and run script (but you still must install python and git)
|
||||
- Outpainting
|
||||
- Inpainting
|
||||
- Color Sketch
|
||||
- Prompt Matrix
|
||||
- Stable Diffusion Upscale
|
||||
- Attention, specify parts of text that the model should pay more attention to
|
||||
- a man in a ((tuxedo)) - will pay more attention to tuxedo
|
||||
- a man in a (tuxedo:1.21) - alternative syntax
|
||||
- select text and press ctrl+up or ctrl+down to automatically adjust attention to selected text (code contributed by anonymous user)
|
||||
- Loopback, run img2img processing multiple times
|
||||
- X/Y/Z plot, a way to draw a 3 dimensional plot of images with different parameters
|
||||
- Textual Inversion
|
||||
- have as many embeddings as you want and use any names you like for them
|
||||
- use multiple embeddings with different numbers of vectors per token
|
||||
- works with half precision floating point numbers
|
||||
- train embeddings on 8GB (also reports of 6GB working)
|
||||
- Extras tab with:
|
||||
- GFPGAN, neural network that fixes faces
|
||||
- CodeFormer, face restoration tool as an alternative to GFPGAN
|
||||
- RealESRGAN, neural network upscaler
|
||||
- ESRGAN, neural network upscaler with a lot of third party models
|
||||
- SwinIR and Swin2SR([see here](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/2092)), neural network upscalers
|
||||
- LDSR, Latent diffusion super resolution upscaling
|
||||
- Resizing aspect ratio options
|
||||
- Sampling method selection
|
||||
- Adjust sampler eta values (noise multiplier)
|
||||
- More advanced noise setting options
|
||||
- Interrupt processing at any time
|
||||
- 4GB video card support (also reports of 2GB working)
|
||||
- Correct seeds for batches
|
||||
- Live prompt token length validation
|
||||
- Generation parameters
|
||||
- parameters you used to generate images are saved with that image
|
||||
- in PNG chunks for PNG, in EXIF for JPEG
|
||||
- can drag the image to PNG info tab to restore generation parameters and automatically copy them into UI
|
||||
- can be disabled in settings
|
||||
- drag and drop an image/text-parameters to promptbox
|
||||
- Read Generation Parameters Button, loads parameters in promptbox to UI
|
||||
- Settings page
|
||||
- Running arbitrary python code from UI (must run with --allow-code to enable)
|
||||
- Mouseover hints for most UI elements
|
||||
- Possible to change defaults/mix/max/step values for UI elements via text config
|
||||
- Tiling support, a checkbox to create images that can be tiled like textures
|
||||
- Progress bar and live image generation preview
|
||||
- Can use a separate neural network to produce previews with almost none VRAM or compute requirement
|
||||
- Negative prompt, an extra text field that allows you to list what you don't want to see in generated image
|
||||
- Styles, a way to save part of prompt and easily apply them via dropdown later
|
||||
- Variations, a way to generate same image but with tiny differences
|
||||
- Seed resizing, a way to generate same image but at slightly different resolution
|
||||
- CLIP interrogator, a button that tries to guess prompt from an image
|
||||
- Prompt Editing, a way to change prompt mid-generation, say to start making a watermelon and switch to anime girl midway
|
||||
- Batch Processing, process a group of files using img2img
|
||||
- Img2img Alternative, reverse Euler method of cross attention control
|
||||
- Highres Fix, a convenience option to produce high resolution pictures in one click without usual distortions
|
||||
- Reloading checkpoints on the fly
|
||||
- Checkpoint Merger, a tab that allows you to merge up to 3 checkpoints into one
|
||||
- [Custom scripts](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Custom-Scripts) with many extensions from community
|
||||
- [Composable-Diffusion](https://energy-based-model.github.io/Compositional-Visual-Generation-with-Composable-Diffusion-Models/), a way to use multiple prompts at once
|
||||
- separate prompts using uppercase `AND`
|
||||
- also supports weights for prompts: `a cat :1.2 AND a dog AND a penguin :2.2`
|
||||
- No token limit for prompts (original stable diffusion lets you use up to 75 tokens)
|
||||
- DeepDanbooru integration, creates danbooru style tags for anime prompts
|
||||
- [xformers](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Xformers), major speed increase for select cards: (add --xformers to commandline args)
|
||||
- via extension: [History tab](https://github.com/yfszzx/stable-diffusion-webui-images-browser): view, direct and delete images conveniently within the UI
|
||||
- Generate forever option
|
||||
- Training tab
|
||||
- hypernetworks and embeddings options
|
||||
- Preprocessing images: cropping, mirroring, autotagging using BLIP or deepdanbooru (for anime)
|
||||
- Clip skip
|
||||
- Hypernetworks
|
||||
- Loras (same as Hypernetworks but more pretty)
|
||||
- A sparate UI where you can choose, with preview, which embeddings, hypernetworks or Loras to add to your prompt.
|
||||
- Can select to load a different VAE from settings screen
|
||||
- Estimated completion time in progress bar
|
||||
- API
|
||||
- Support for dedicated [inpainting model](https://github.com/runwayml/stable-diffusion#inpainting-with-stable-diffusion) by RunwayML.
|
||||
- via extension: [Aesthetic Gradients](https://github.com/AUTOMATIC1111/stable-diffusion-webui-aesthetic-gradients), a way to generate images with a specific aesthetic by using clip images embeds (implementation of [https://github.com/vicgalle/stable-diffusion-aesthetic-gradients](https://github.com/vicgalle/stable-diffusion-aesthetic-gradients))
|
||||
- [Stable Diffusion 2.0](https://github.com/Stability-AI/stablediffusion) support - see [wiki](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Features#stable-diffusion-20) for instructions
|
||||
- [Alt-Diffusion](https://arxiv.org/abs/2211.06679) support - see [wiki](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Features#alt-diffusion) for instructions
|
||||
- Now without any bad letters!
|
||||
- Load checkpoints in safetensors format
|
||||
- Eased resolution restriction: generated image's domension must be a multiple of 8 rather than 64
|
||||
- Now with a license!
|
||||
- Reorder elements in the UI from settings screen
|
||||
-
|
||||
|
||||
## Installation and Running
|
||||
Make sure the required [dependencies](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Dependencies) are met and follow the instructions available for both [NVidia](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Install-and-Run-on-NVidia-GPUs) (recommended) and [AMD](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Install-and-Run-on-AMD-GPUs) GPUs.
|
||||
|
||||
Alternatively, use online services (like Google Colab):
|
||||
|
||||
- [List of Online Services](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Online-Services)
|
||||
|
||||
### Automatic Installation on Windows
|
||||
1. Install [Python 3.10.6](https://www.python.org/downloads/windows/), checking "Add Python to PATH"
|
||||
2. Install [git](https://git-scm.com/download/win).
|
||||
3. Download the stable-diffusion-webui repository, for example by running `git clone https://github.com/AUTOMATIC1111/stable-diffusion-webui.git`.
|
||||
4. Run `webui-user.bat` from Windows Explorer as normal, non-administrator, user.
|
||||
|
||||
### Automatic Installation on Linux
|
||||
1. Install the dependencies:
|
||||
```bash
|
||||
# Debian-based:
|
||||
sudo apt install wget git python3 python3-venv
|
||||
# Red Hat-based:
|
||||
sudo dnf install wget git python3
|
||||
# Arch-based:
|
||||
sudo pacman -S wget git python3
|
||||
```
|
||||
2. To install in `/home/$(whoami)/stable-diffusion-webui/`, run:
|
||||
```bash
|
||||
bash <(wget -qO- https://raw.githubusercontent.com/AUTOMATIC1111/stable-diffusion-webui/master/webui.sh)
|
||||
```
|
||||
3. Run `webui.sh`.
|
||||
### Installation on Apple Silicon
|
||||
|
||||
Find the instructions [here](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Installation-on-Apple-Silicon).
|
||||
|
||||
## Contributing
|
||||
Here's how to add code to this repo: [Contributing](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Contributing)
|
||||
|
||||
## Documentation
|
||||
The documentation was moved from this README over to the project's [wiki](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki).
|
||||
|
||||
## Credits
|
||||
Licenses for borrowed code can be found in `Settings -> Licenses` screen, and also in `html/licenses.html` file.
|
||||
|
||||
- Stable Diffusion - https://github.com/CompVis/stable-diffusion, https://github.com/CompVis/taming-transformers
|
||||
- k-diffusion - https://github.com/crowsonkb/k-diffusion.git
|
||||
- GFPGAN - https://github.com/TencentARC/GFPGAN.git
|
||||
- CodeFormer - https://github.com/sczhou/CodeFormer
|
||||
- ESRGAN - https://github.com/xinntao/ESRGAN
|
||||
- SwinIR - https://github.com/JingyunLiang/SwinIR
|
||||
- Swin2SR - https://github.com/mv-lab/swin2sr
|
||||
- LDSR - https://github.com/Hafiidz/latent-diffusion
|
||||
- MiDaS - https://github.com/isl-org/MiDaS
|
||||
- Ideas for optimizations - https://github.com/basujindal/stable-diffusion
|
||||
- Cross Attention layer optimization - Doggettx - https://github.com/Doggettx/stable-diffusion, original idea for prompt editing.
|
||||
- Cross Attention layer optimization - InvokeAI, lstein - https://github.com/invoke-ai/InvokeAI (originally http://github.com/lstein/stable-diffusion)
|
||||
- Sub-quadratic Cross Attention layer optimization - Alex Birch (https://github.com/Birch-san/diffusers/pull/1), Amin Rezaei (https://github.com/AminRezaei0x443/memory-efficient-attention)
|
||||
- Textual Inversion - Rinon Gal - https://github.com/rinongal/textual_inversion (we're not using his code, but we are using his ideas).
|
||||
- Idea for SD upscale - https://github.com/jquesnelle/txt2imghd
|
||||
- Noise generation for outpainting mk2 - https://github.com/parlance-zz/g-diffuser-bot
|
||||
- CLIP interrogator idea and borrowing some code - https://github.com/pharmapsychotic/clip-interrogator
|
||||
- Idea for Composable Diffusion - https://github.com/energy-based-model/Compositional-Visual-Generation-with-Composable-Diffusion-Models-PyTorch
|
||||
- xformers - https://github.com/facebookresearch/xformers
|
||||
- DeepDanbooru - interrogator for anime diffusers https://github.com/KichangKim/DeepDanbooru
|
||||
- Sampling in float32 precision from a float16 UNet - marunine for the idea, Birch-san for the example Diffusers implementation (https://github.com/Birch-san/diffusers-play/tree/92feee6)
|
||||
- Instruct pix2pix - Tim Brooks (star), Aleksander Holynski (star), Alexei A. Efros (no star) - https://github.com/timothybrooks/instruct-pix2pix
|
||||
- Security advice - RyotaK
|
||||
- Initial Gradio script - posted on 4chan by an Anonymous user. Thank you Anonymous user.
|
||||
- (You)
|
||||
@@ -0,0 +1,37 @@
|
||||
import json
|
||||
import os
|
||||
import lora
|
||||
|
||||
from modules import shared, ui_extra_networks
|
||||
|
||||
|
||||
class ExtraNetworksPageLora(ui_extra_networks.ExtraNetworksPage):
|
||||
def __init__(self):
|
||||
super().__init__('Lora')
|
||||
|
||||
def refresh(self):
|
||||
lora.list_available_loras()
|
||||
|
||||
def list_items(self):
|
||||
for name, lora_on_disk in lora.available_loras.items():
|
||||
path, ext = os.path.splitext(lora_on_disk.filename)
|
||||
previews = [path + ".png", path + ".preview.png"]
|
||||
|
||||
preview = None
|
||||
for file in previews:
|
||||
if os.path.isfile(file):
|
||||
preview = self.link_preview(file)
|
||||
break
|
||||
|
||||
yield {
|
||||
"name": name,
|
||||
"filename": path,
|
||||
"preview": preview,
|
||||
"search_term": self.search_terms_from_path(lora_on_disk.filename),
|
||||
"prompt": json.dumps(f"<lora:{name}:") + " + opts.extra_networks_default_multiplier + " + json.dumps(">"),
|
||||
"local_preview": path + ".png",
|
||||
}
|
||||
|
||||
def allowed_directories_for_previews(self):
|
||||
return [shared.cmd_opts.lora_dir]
|
||||
|
||||
@@ -0,0 +1,243 @@
|
||||
// code related to showing and updating progressbar shown as the image is being made
|
||||
|
||||
|
||||
galleries = {}
|
||||
storedGallerySelections = {}
|
||||
galleryObservers = {}
|
||||
|
||||
function rememberGallerySelection(id_gallery){
|
||||
storedGallerySelections[id_gallery] = getGallerySelectedIndex(id_gallery)
|
||||
}
|
||||
|
||||
function getGallerySelectedIndex(id_gallery){
|
||||
let galleryButtons = gradioApp().querySelectorAll('#'+id_gallery+' .gallery-item')
|
||||
let galleryBtnSelected = gradioApp().querySelector('#'+id_gallery+' .gallery-item.\\!ring-2')
|
||||
|
||||
let currentlySelectedIndex = -1
|
||||
galleryButtons.forEach(function(v, i){ if(v==galleryBtnSelected) { currentlySelectedIndex = i } })
|
||||
|
||||
return currentlySelectedIndex
|
||||
}
|
||||
|
||||
// this is a workaround for https://github.com/gradio-app/gradio/issues/2984
|
||||
function check_gallery(id_gallery){
|
||||
let gallery = gradioApp().getElementById(id_gallery)
|
||||
// if gallery has no change, no need to setting up observer again.
|
||||
if (gallery && galleries[id_gallery] !== gallery){
|
||||
galleries[id_gallery] = gallery;
|
||||
if(galleryObservers[id_gallery]){
|
||||
galleryObservers[id_gallery].disconnect();
|
||||
}
|
||||
|
||||
storedGallerySelections[id_gallery] = -1
|
||||
|
||||
galleryObservers[id_gallery] = new MutationObserver(function (){
|
||||
let galleryButtons = gradioApp().querySelectorAll('#'+id_gallery+' .gallery-item')
|
||||
let galleryBtnSelected = gradioApp().querySelector('#'+id_gallery+' .gallery-item.\\!ring-2')
|
||||
let currentlySelectedIndex = getGallerySelectedIndex(id_gallery)
|
||||
prevSelectedIndex = storedGallerySelections[id_gallery]
|
||||
storedGallerySelections[id_gallery] = -1
|
||||
|
||||
if (prevSelectedIndex !== -1 && galleryButtons.length>prevSelectedIndex && !galleryBtnSelected) {
|
||||
// automatically re-open previously selected index (if exists)
|
||||
activeElement = gradioApp().activeElement;
|
||||
let scrollX = window.scrollX;
|
||||
let scrollY = window.scrollY;
|
||||
|
||||
galleryButtons[prevSelectedIndex].click();
|
||||
showGalleryImage();
|
||||
|
||||
// When the gallery button is clicked, it gains focus and scrolls itself into view
|
||||
// We need to scroll back to the previous position
|
||||
setTimeout(function (){
|
||||
window.scrollTo(scrollX, scrollY);
|
||||
}, 50);
|
||||
|
||||
if(activeElement){
|
||||
// i fought this for about an hour; i don't know why the focus is lost or why this helps recover it
|
||||
// if someone has a better solution please by all means
|
||||
setTimeout(function (){
|
||||
activeElement.focus({
|
||||
preventScroll: true // Refocus the element that was focused before the gallery was opened without scrolling to it
|
||||
})
|
||||
}, 1);
|
||||
}
|
||||
}
|
||||
})
|
||||
galleryObservers[id_gallery].observe( gallery, { childList:true, subtree:false })
|
||||
}
|
||||
}
|
||||
|
||||
onUiUpdate(function(){
|
||||
check_gallery('txt2img_gallery')
|
||||
check_gallery('img2img_gallery')
|
||||
})
|
||||
|
||||
function request(url, data, handler, errorHandler){
|
||||
var xhr = new XMLHttpRequest();
|
||||
var url = url;
|
||||
xhr.open("POST", url, true);
|
||||
xhr.setRequestHeader("Content-Type", "application/json");
|
||||
xhr.onreadystatechange = function () {
|
||||
if (xhr.readyState === 4) {
|
||||
if (xhr.status === 200) {
|
||||
try {
|
||||
var js = JSON.parse(xhr.responseText);
|
||||
handler(js)
|
||||
} catch (error) {
|
||||
console.error(error);
|
||||
errorHandler()
|
||||
}
|
||||
} else{
|
||||
errorHandler()
|
||||
}
|
||||
}
|
||||
};
|
||||
var js = JSON.stringify(data);
|
||||
xhr.send(js);
|
||||
}
|
||||
|
||||
function pad2(x){
|
||||
return x<10 ? '0'+x : x
|
||||
}
|
||||
|
||||
function formatTime(secs){
|
||||
if(secs > 3600){
|
||||
return pad2(Math.floor(secs/60/60)) + ":" + pad2(Math.floor(secs/60)%60) + ":" + pad2(Math.floor(secs)%60)
|
||||
} else if(secs > 60){
|
||||
return pad2(Math.floor(secs/60)) + ":" + pad2(Math.floor(secs)%60)
|
||||
} else{
|
||||
return Math.floor(secs) + "s"
|
||||
}
|
||||
}
|
||||
|
||||
function setTitle(progress){
|
||||
var title = 'Stable Diffusion'
|
||||
|
||||
if(opts.show_progress_in_title && progress){
|
||||
title = '[' + progress.trim() + '] ' + title;
|
||||
}
|
||||
|
||||
if(document.title != title){
|
||||
document.title = title;
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
function randomId(){
|
||||
return "task(" + Math.random().toString(36).slice(2, 7) + Math.random().toString(36).slice(2, 7) + Math.random().toString(36).slice(2, 7)+")"
|
||||
}
|
||||
|
||||
// starts sending progress requests to "/internal/progress" uri, creating progressbar above progressbarContainer element and
|
||||
// preview inside gallery element. Cleans up all created stuff when the task is over and calls atEnd.
|
||||
// calls onProgress every time there is a progress update
|
||||
function requestProgress(id_task, progressbarContainer, gallery, atEnd, onProgress){
|
||||
var dateStart = new Date()
|
||||
var wasEverActive = false
|
||||
var parentProgressbar = progressbarContainer.parentNode
|
||||
var parentGallery = gallery ? gallery.parentNode : null
|
||||
|
||||
var divProgress = document.createElement('div')
|
||||
divProgress.className='progressDiv'
|
||||
divProgress.style.display = opts.show_progressbar ? "" : "none"
|
||||
var divInner = document.createElement('div')
|
||||
divInner.className='progress'
|
||||
|
||||
divProgress.appendChild(divInner)
|
||||
parentProgressbar.insertBefore(divProgress, progressbarContainer)
|
||||
|
||||
if(parentGallery){
|
||||
var livePreview = document.createElement('div')
|
||||
livePreview.className='livePreview'
|
||||
parentGallery.insertBefore(livePreview, gallery)
|
||||
}
|
||||
|
||||
var removeProgressBar = function(){
|
||||
setTitle("")
|
||||
parentProgressbar.removeChild(divProgress)
|
||||
if(parentGallery) parentGallery.removeChild(livePreview)
|
||||
atEnd()
|
||||
}
|
||||
|
||||
var fun = function(id_task, id_live_preview){
|
||||
request("./internal/progress", {"id_task": id_task, "id_live_preview": id_live_preview}, function(res){
|
||||
if(res.completed){
|
||||
removeProgressBar()
|
||||
return
|
||||
}
|
||||
|
||||
var rect = progressbarContainer.getBoundingClientRect()
|
||||
|
||||
if(rect.width){
|
||||
divProgress.style.width = rect.width + "px";
|
||||
}
|
||||
|
||||
progressText = ""
|
||||
|
||||
divInner.style.width = ((res.progress || 0) * 100.0) + '%'
|
||||
divInner.style.background = res.progress ? "" : "transparent"
|
||||
|
||||
if(res.progress > 0){
|
||||
progressText = ((res.progress || 0) * 100.0).toFixed(0) + '%'
|
||||
}
|
||||
|
||||
if(res.eta){
|
||||
progressText += " ETA: " + formatTime(res.eta)
|
||||
}
|
||||
|
||||
|
||||
setTitle(progressText)
|
||||
|
||||
if(res.textinfo && res.textinfo.indexOf("\n") == -1){
|
||||
progressText = res.textinfo + " " + progressText
|
||||
}
|
||||
|
||||
divInner.textContent = progressText
|
||||
|
||||
var elapsedFromStart = (new Date() - dateStart) / 1000
|
||||
|
||||
if(res.active) wasEverActive = true;
|
||||
|
||||
if(! res.active && wasEverActive){
|
||||
removeProgressBar()
|
||||
return
|
||||
}
|
||||
|
||||
if(elapsedFromStart > 5 && !res.queued && !res.active){
|
||||
removeProgressBar()
|
||||
return
|
||||
}
|
||||
|
||||
|
||||
if(res.live_preview && gallery){
|
||||
var rect = gallery.getBoundingClientRect()
|
||||
if(rect.width){
|
||||
livePreview.style.width = rect.width + "px"
|
||||
livePreview.style.height = rect.height + "px"
|
||||
}
|
||||
|
||||
var img = new Image();
|
||||
img.onload = function() {
|
||||
livePreview.appendChild(img)
|
||||
if(livePreview.childElementCount > 2){
|
||||
livePreview.removeChild(livePreview.firstElementChild)
|
||||
}
|
||||
}
|
||||
img.src = res.live_preview;
|
||||
}
|
||||
|
||||
|
||||
if(onProgress){
|
||||
onProgress(res)
|
||||
}
|
||||
|
||||
setTimeout(() => {
|
||||
fun(id_task, res.id_live_preview);
|
||||
}, opts.live_preview_refresh_period || 500)
|
||||
}, function(){
|
||||
removeProgressBar()
|
||||
})
|
||||
}
|
||||
|
||||
fun(id_task, 0)
|
||||
}
|
||||
@@ -0,0 +1,551 @@
|
||||
import base64
|
||||
import io
|
||||
import time
|
||||
import datetime
|
||||
import uvicorn
|
||||
from threading import Lock
|
||||
from io import BytesIO
|
||||
from gradio.processing_utils import decode_base64_to_file
|
||||
from fastapi import APIRouter, Depends, FastAPI, HTTPException, Request, Response
|
||||
from fastapi.security import HTTPBasic, HTTPBasicCredentials
|
||||
from secrets import compare_digest
|
||||
|
||||
import modules.shared as shared
|
||||
from modules import sd_samplers, deepbooru, sd_hijack, images, scripts, ui, postprocessing
|
||||
from modules.api.models import *
|
||||
from modules.processing import StableDiffusionProcessingTxt2Img, StableDiffusionProcessingImg2Img, process_images
|
||||
from modules.textual_inversion.textual_inversion import create_embedding, train_embedding
|
||||
from modules.textual_inversion.preprocess import preprocess
|
||||
from modules.hypernetworks.hypernetwork import create_hypernetwork, train_hypernetwork
|
||||
from PIL import PngImagePlugin,Image
|
||||
from modules.sd_models import checkpoints_list
|
||||
from modules.sd_models_config import find_checkpoint_config_near_filename
|
||||
from modules.realesrgan_model import get_realesrgan_models
|
||||
from modules import devices
|
||||
from typing import List
|
||||
import piexif
|
||||
import piexif.helper
|
||||
|
||||
def upscaler_to_index(name: str):
|
||||
try:
|
||||
return [x.name.lower() for x in shared.sd_upscalers].index(name.lower())
|
||||
except:
|
||||
raise HTTPException(status_code=400, detail=f"Invalid upscaler, needs to be one of these: {' , '.join([x.name for x in sd_upscalers])}")
|
||||
|
||||
def script_name_to_index(name, scripts):
|
||||
try:
|
||||
return [script.title().lower() for script in scripts].index(name.lower())
|
||||
except:
|
||||
raise HTTPException(status_code=422, detail=f"Script '{name}' not found")
|
||||
|
||||
def validate_sampler_name(name):
|
||||
config = sd_samplers.all_samplers_map.get(name, None)
|
||||
if config is None:
|
||||
raise HTTPException(status_code=404, detail="Sampler not found")
|
||||
|
||||
return name
|
||||
|
||||
def setUpscalers(req: dict):
|
||||
reqDict = vars(req)
|
||||
reqDict['extras_upscaler_1'] = reqDict.pop('upscaler_1', None)
|
||||
reqDict['extras_upscaler_2'] = reqDict.pop('upscaler_2', None)
|
||||
return reqDict
|
||||
|
||||
def decode_base64_to_image(encoding):
|
||||
if encoding.startswith("data:image/"):
|
||||
encoding = encoding.split(";")[1].split(",")[1]
|
||||
try:
|
||||
image = Image.open(BytesIO(base64.b64decode(encoding)))
|
||||
return image
|
||||
except Exception as err:
|
||||
raise HTTPException(status_code=500, detail="Invalid encoded image")
|
||||
|
||||
def encode_pil_to_base64(image):
|
||||
with io.BytesIO() as output_bytes:
|
||||
|
||||
if opts.samples_format.lower() == 'png':
|
||||
use_metadata = False
|
||||
metadata = PngImagePlugin.PngInfo()
|
||||
for key, value in image.info.items():
|
||||
if isinstance(key, str) and isinstance(value, str):
|
||||
metadata.add_text(key, value)
|
||||
use_metadata = True
|
||||
image.save(output_bytes, format="PNG", pnginfo=(metadata if use_metadata else None), quality=opts.jpeg_quality)
|
||||
|
||||
elif opts.samples_format.lower() in ("jpg", "jpeg", "webp"):
|
||||
parameters = image.info.get('parameters', None)
|
||||
exif_bytes = piexif.dump({
|
||||
"Exif": { piexif.ExifIFD.UserComment: piexif.helper.UserComment.dump(parameters or "", encoding="unicode") }
|
||||
})
|
||||
if opts.samples_format.lower() in ("jpg", "jpeg"):
|
||||
image.save(output_bytes, format="JPEG", exif = exif_bytes, quality=opts.jpeg_quality)
|
||||
else:
|
||||
image.save(output_bytes, format="WEBP", exif = exif_bytes, quality=opts.jpeg_quality)
|
||||
|
||||
else:
|
||||
raise HTTPException(status_code=500, detail="Invalid image format")
|
||||
|
||||
bytes_data = output_bytes.getvalue()
|
||||
|
||||
return base64.b64encode(bytes_data)
|
||||
|
||||
def api_middleware(app: FastAPI):
|
||||
@app.middleware("http")
|
||||
async def log_and_time(req: Request, call_next):
|
||||
ts = time.time()
|
||||
res: Response = await call_next(req)
|
||||
duration = str(round(time.time() - ts, 4))
|
||||
res.headers["X-Process-Time"] = duration
|
||||
endpoint = req.scope.get('path', 'err')
|
||||
if shared.cmd_opts.api_log and endpoint.startswith('/sdapi'):
|
||||
print('API {t} {code} {prot}/{ver} {method} {endpoint} {cli} {duration}'.format(
|
||||
t = datetime.datetime.now().strftime("%Y-%m-%d %H:%M:%S.%f"),
|
||||
code = res.status_code,
|
||||
ver = req.scope.get('http_version', '0.0'),
|
||||
cli = req.scope.get('client', ('0:0.0.0', 0))[0],
|
||||
prot = req.scope.get('scheme', 'err'),
|
||||
method = req.scope.get('method', 'err'),
|
||||
endpoint = endpoint,
|
||||
duration = duration,
|
||||
))
|
||||
return res
|
||||
|
||||
|
||||
class Api:
|
||||
def __init__(self, app: FastAPI, queue_lock: Lock):
|
||||
if shared.cmd_opts.api_auth:
|
||||
self.credentials = dict()
|
||||
for auth in shared.cmd_opts.api_auth.split(","):
|
||||
user, password = auth.split(":")
|
||||
self.credentials[user] = password
|
||||
|
||||
self.router = APIRouter()
|
||||
self.app = app
|
||||
self.queue_lock = queue_lock
|
||||
api_middleware(self.app)
|
||||
self.add_api_route("/sdapi/v1/txt2img", self.text2imgapi, methods=["POST"], response_model=TextToImageResponse)
|
||||
self.add_api_route("/sdapi/v1/img2img", self.img2imgapi, methods=["POST"], response_model=ImageToImageResponse)
|
||||
self.add_api_route("/sdapi/v1/extra-single-image", self.extras_single_image_api, methods=["POST"], response_model=ExtrasSingleImageResponse)
|
||||
self.add_api_route("/sdapi/v1/extra-batch-images", self.extras_batch_images_api, methods=["POST"], response_model=ExtrasBatchImagesResponse)
|
||||
self.add_api_route("/sdapi/v1/png-info", self.pnginfoapi, methods=["POST"], response_model=PNGInfoResponse)
|
||||
self.add_api_route("/sdapi/v1/progress", self.progressapi, methods=["GET"], response_model=ProgressResponse)
|
||||
self.add_api_route("/sdapi/v1/interrogate", self.interrogateapi, methods=["POST"])
|
||||
self.add_api_route("/sdapi/v1/interrupt", self.interruptapi, methods=["POST"])
|
||||
self.add_api_route("/sdapi/v1/skip", self.skip, methods=["POST"])
|
||||
self.add_api_route("/sdapi/v1/options", self.get_config, methods=["GET"], response_model=OptionsModel)
|
||||
self.add_api_route("/sdapi/v1/options", self.set_config, methods=["POST"])
|
||||
self.add_api_route("/sdapi/v1/cmd-flags", self.get_cmd_flags, methods=["GET"], response_model=FlagsModel)
|
||||
self.add_api_route("/sdapi/v1/samplers", self.get_samplers, methods=["GET"], response_model=List[SamplerItem])
|
||||
self.add_api_route("/sdapi/v1/upscalers", self.get_upscalers, methods=["GET"], response_model=List[UpscalerItem])
|
||||
self.add_api_route("/sdapi/v1/sd-models", self.get_sd_models, methods=["GET"], response_model=List[SDModelItem])
|
||||
self.add_api_route("/sdapi/v1/hypernetworks", self.get_hypernetworks, methods=["GET"], response_model=List[HypernetworkItem])
|
||||
self.add_api_route("/sdapi/v1/face-restorers", self.get_face_restorers, methods=["GET"], response_model=List[FaceRestorerItem])
|
||||
self.add_api_route("/sdapi/v1/realesrgan-models", self.get_realesrgan_models, methods=["GET"], response_model=List[RealesrganItem])
|
||||
self.add_api_route("/sdapi/v1/prompt-styles", self.get_prompt_styles, methods=["GET"], response_model=List[PromptStyleItem])
|
||||
self.add_api_route("/sdapi/v1/embeddings", self.get_embeddings, methods=["GET"], response_model=EmbeddingsResponse)
|
||||
self.add_api_route("/sdapi/v1/refresh-checkpoints", self.refresh_checkpoints, methods=["POST"])
|
||||
self.add_api_route("/sdapi/v1/create/embedding", self.create_embedding, methods=["POST"], response_model=CreateResponse)
|
||||
self.add_api_route("/sdapi/v1/create/hypernetwork", self.create_hypernetwork, methods=["POST"], response_model=CreateResponse)
|
||||
self.add_api_route("/sdapi/v1/preprocess", self.preprocess, methods=["POST"], response_model=PreprocessResponse)
|
||||
self.add_api_route("/sdapi/v1/train/embedding", self.train_embedding, methods=["POST"], response_model=TrainResponse)
|
||||
self.add_api_route("/sdapi/v1/train/hypernetwork", self.train_hypernetwork, methods=["POST"], response_model=TrainResponse)
|
||||
self.add_api_route("/sdapi/v1/memory", self.get_memory, methods=["GET"], response_model=MemoryResponse)
|
||||
|
||||
def add_api_route(self, path: str, endpoint, **kwargs):
|
||||
if shared.cmd_opts.api_auth:
|
||||
return self.app.add_api_route(path, endpoint, dependencies=[Depends(self.auth)], **kwargs)
|
||||
return self.app.add_api_route(path, endpoint, **kwargs)
|
||||
|
||||
def auth(self, credentials: HTTPBasicCredentials = Depends(HTTPBasic())):
|
||||
if credentials.username in self.credentials:
|
||||
if compare_digest(credentials.password, self.credentials[credentials.username]):
|
||||
return True
|
||||
|
||||
raise HTTPException(status_code=401, detail="Incorrect username or password", headers={"WWW-Authenticate": "Basic"})
|
||||
|
||||
def get_script(self, script_name, script_runner):
|
||||
if script_name is None:
|
||||
return None, None
|
||||
|
||||
if not script_runner.scripts:
|
||||
script_runner.initialize_scripts(False)
|
||||
ui.create_ui()
|
||||
|
||||
script_idx = script_name_to_index(script_name, script_runner.selectable_scripts)
|
||||
script = script_runner.selectable_scripts[script_idx]
|
||||
return script, script_idx
|
||||
|
||||
def text2imgapi(self, txt2imgreq: StableDiffusionTxt2ImgProcessingAPI):
|
||||
script, script_idx = self.get_script(txt2imgreq.script_name, scripts.scripts_txt2img)
|
||||
|
||||
populate = txt2imgreq.copy(update={ # Override __init__ params
|
||||
"sampler_name": validate_sampler_name(txt2imgreq.sampler_name or txt2imgreq.sampler_index),
|
||||
"do_not_save_samples": True,
|
||||
"do_not_save_grid": True
|
||||
}
|
||||
)
|
||||
if populate.sampler_name:
|
||||
populate.sampler_index = None # prevent a warning later on
|
||||
|
||||
args = vars(populate)
|
||||
args.pop('script_name', None)
|
||||
|
||||
with self.queue_lock:
|
||||
p = StableDiffusionProcessingTxt2Img(sd_model=shared.sd_model, **args)
|
||||
|
||||
shared.state.begin()
|
||||
if script is not None:
|
||||
p.outpath_grids = opts.outdir_txt2img_grids
|
||||
p.outpath_samples = opts.outdir_txt2img_samples
|
||||
p.script_args = [script_idx + 1] + [None] * (script.args_from - 1) + p.script_args
|
||||
processed = scripts.scripts_txt2img.run(p, *p.script_args)
|
||||
else:
|
||||
processed = process_images(p)
|
||||
shared.state.end()
|
||||
|
||||
b64images = list(map(encode_pil_to_base64, processed.images))
|
||||
|
||||
return TextToImageResponse(images=b64images, parameters=vars(txt2imgreq), info=processed.js())
|
||||
|
||||
def img2imgapi(self, img2imgreq: StableDiffusionImg2ImgProcessingAPI):
|
||||
init_images = img2imgreq.init_images
|
||||
if init_images is None:
|
||||
raise HTTPException(status_code=404, detail="Init image not found")
|
||||
|
||||
script, script_idx = self.get_script(img2imgreq.script_name, scripts.scripts_img2img)
|
||||
|
||||
mask = img2imgreq.mask
|
||||
if mask:
|
||||
mask = decode_base64_to_image(mask)
|
||||
|
||||
populate = img2imgreq.copy(update={ # Override __init__ params
|
||||
"sampler_name": validate_sampler_name(img2imgreq.sampler_name or img2imgreq.sampler_index),
|
||||
"do_not_save_samples": True,
|
||||
"do_not_save_grid": True,
|
||||
"mask": mask
|
||||
}
|
||||
)
|
||||
if populate.sampler_name:
|
||||
populate.sampler_index = None # prevent a warning later on
|
||||
|
||||
args = vars(populate)
|
||||
args.pop('include_init_images', None) # this is meant to be done by "exclude": True in model, but it's for a reason that I cannot determine.
|
||||
args.pop('script_name', None)
|
||||
|
||||
with self.queue_lock:
|
||||
p = StableDiffusionProcessingImg2Img(sd_model=shared.sd_model, **args)
|
||||
p.init_images = [decode_base64_to_image(x) for x in init_images]
|
||||
|
||||
shared.state.begin()
|
||||
if script is not None:
|
||||
p.outpath_grids = opts.outdir_img2img_grids
|
||||
p.outpath_samples = opts.outdir_img2img_samples
|
||||
p.script_args = [script_idx + 1] + [None] * (script.args_from - 1) + p.script_args
|
||||
processed = scripts.scripts_img2img.run(p, *p.script_args)
|
||||
else:
|
||||
processed = process_images(p)
|
||||
shared.state.end()
|
||||
|
||||
b64images = list(map(encode_pil_to_base64, processed.images))
|
||||
|
||||
if not img2imgreq.include_init_images:
|
||||
img2imgreq.init_images = None
|
||||
img2imgreq.mask = None
|
||||
|
||||
return ImageToImageResponse(images=b64images, parameters=vars(img2imgreq), info=processed.js())
|
||||
|
||||
def extras_single_image_api(self, req: ExtrasSingleImageRequest):
|
||||
reqDict = setUpscalers(req)
|
||||
|
||||
reqDict['image'] = decode_base64_to_image(reqDict['image'])
|
||||
|
||||
with self.queue_lock:
|
||||
result = postprocessing.run_extras(extras_mode=0, image_folder="", input_dir="", output_dir="", save_output=False, **reqDict)
|
||||
|
||||
return ExtrasSingleImageResponse(image=encode_pil_to_base64(result[0][0]), html_info=result[1])
|
||||
|
||||
def extras_batch_images_api(self, req: ExtrasBatchImagesRequest):
|
||||
reqDict = setUpscalers(req)
|
||||
|
||||
def prepareFiles(file):
|
||||
file = decode_base64_to_file(file.data, file_path=file.name)
|
||||
file.orig_name = file.name
|
||||
return file
|
||||
|
||||
reqDict['image_folder'] = list(map(prepareFiles, reqDict['imageList']))
|
||||
reqDict.pop('imageList')
|
||||
|
||||
with self.queue_lock:
|
||||
result = postprocessing.run_extras(extras_mode=1, image="", input_dir="", output_dir="", save_output=False, **reqDict)
|
||||
|
||||
return ExtrasBatchImagesResponse(images=list(map(encode_pil_to_base64, result[0])), html_info=result[1])
|
||||
|
||||
def pnginfoapi(self, req: PNGInfoRequest):
|
||||
if(not req.image.strip()):
|
||||
return PNGInfoResponse(info="")
|
||||
|
||||
image = decode_base64_to_image(req.image.strip())
|
||||
if image is None:
|
||||
return PNGInfoResponse(info="")
|
||||
|
||||
geninfo, items = images.read_info_from_image(image)
|
||||
if geninfo is None:
|
||||
geninfo = ""
|
||||
|
||||
items = {**{'parameters': geninfo}, **items}
|
||||
|
||||
return PNGInfoResponse(info=geninfo, items=items)
|
||||
|
||||
def progressapi(self, req: ProgressRequest = Depends()):
|
||||
# copy from check_progress_call of ui.py
|
||||
|
||||
if shared.state.job_count == 0:
|
||||
return ProgressResponse(progress=0, eta_relative=0, state=shared.state.dict(), textinfo=shared.state.textinfo)
|
||||
|
||||
# avoid dividing zero
|
||||
progress = 0.01
|
||||
|
||||
if shared.state.job_count > 0:
|
||||
progress += shared.state.job_no / shared.state.job_count
|
||||
if shared.state.sampling_steps > 0:
|
||||
progress += 1 / shared.state.job_count * shared.state.sampling_step / shared.state.sampling_steps
|
||||
|
||||
time_since_start = time.time() - shared.state.time_start
|
||||
eta = (time_since_start/progress)
|
||||
eta_relative = eta-time_since_start
|
||||
|
||||
progress = min(progress, 1)
|
||||
|
||||
shared.state.set_current_image()
|
||||
|
||||
current_image = None
|
||||
if shared.state.current_image and not req.skip_current_image:
|
||||
current_image = encode_pil_to_base64(shared.state.current_image)
|
||||
|
||||
return ProgressResponse(progress=progress, eta_relative=eta_relative, state=shared.state.dict(), current_image=current_image, textinfo=shared.state.textinfo)
|
||||
|
||||
def interrogateapi(self, interrogatereq: InterrogateRequest):
|
||||
image_b64 = interrogatereq.image
|
||||
if image_b64 is None:
|
||||
raise HTTPException(status_code=404, detail="Image not found")
|
||||
|
||||
img = decode_base64_to_image(image_b64)
|
||||
img = img.convert('RGB')
|
||||
|
||||
# Override object param
|
||||
with self.queue_lock:
|
||||
if interrogatereq.model == "clip":
|
||||
processed = shared.interrogator.interrogate(img)
|
||||
elif interrogatereq.model == "deepdanbooru":
|
||||
processed = deepbooru.model.tag(img)
|
||||
else:
|
||||
raise HTTPException(status_code=404, detail="Model not found")
|
||||
|
||||
return InterrogateResponse(caption=processed)
|
||||
|
||||
def interruptapi(self):
|
||||
shared.state.interrupt()
|
||||
|
||||
return {}
|
||||
|
||||
def skip(self):
|
||||
shared.state.skip()
|
||||
|
||||
def get_config(self):
|
||||
options = {}
|
||||
for key in shared.opts.data.keys():
|
||||
metadata = shared.opts.data_labels.get(key)
|
||||
if(metadata is not None):
|
||||
options.update({key: shared.opts.data.get(key, shared.opts.data_labels.get(key).default)})
|
||||
else:
|
||||
options.update({key: shared.opts.data.get(key, None)})
|
||||
|
||||
return options
|
||||
|
||||
def set_config(self, req: Dict[str, Any]):
|
||||
for k, v in req.items():
|
||||
shared.opts.set(k, v)
|
||||
|
||||
shared.opts.save(shared.config_filename)
|
||||
return
|
||||
|
||||
def get_cmd_flags(self):
|
||||
return vars(shared.cmd_opts)
|
||||
|
||||
def get_samplers(self):
|
||||
return [{"name": sampler[0], "aliases":sampler[2], "options":sampler[3]} for sampler in sd_samplers.all_samplers]
|
||||
|
||||
def get_upscalers(self):
|
||||
return [
|
||||
{
|
||||
"name": upscaler.name,
|
||||
"model_name": upscaler.scaler.model_name,
|
||||
"model_path": upscaler.data_path,
|
||||
"model_url": None,
|
||||
"scale": upscaler.scale,
|
||||
}
|
||||
for upscaler in shared.sd_upscalers
|
||||
]
|
||||
|
||||
def get_sd_models(self):
|
||||
return [{"title": x.title, "model_name": x.model_name, "hash": x.shorthash, "sha256": x.sha256, "filename": x.filename, "config": find_checkpoint_config_near_filename(x)} for x in checkpoints_list.values()]
|
||||
|
||||
def get_hypernetworks(self):
|
||||
return [{"name": name, "path": shared.hypernetworks[name]} for name in shared.hypernetworks]
|
||||
|
||||
def get_face_restorers(self):
|
||||
return [{"name":x.name(), "cmd_dir": getattr(x, "cmd_dir", None)} for x in shared.face_restorers]
|
||||
|
||||
def get_realesrgan_models(self):
|
||||
return [{"name":x.name,"path":x.data_path, "scale":x.scale} for x in get_realesrgan_models(None)]
|
||||
|
||||
def get_prompt_styles(self):
|
||||
styleList = []
|
||||
for k in shared.prompt_styles.styles:
|
||||
style = shared.prompt_styles.styles[k]
|
||||
styleList.append({"name":style[0], "prompt": style[1], "negative_prompt": style[2]})
|
||||
|
||||
return styleList
|
||||
|
||||
def get_embeddings(self):
|
||||
db = sd_hijack.model_hijack.embedding_db
|
||||
|
||||
def convert_embedding(embedding):
|
||||
return {
|
||||
"step": embedding.step,
|
||||
"sd_checkpoint": embedding.sd_checkpoint,
|
||||
"sd_checkpoint_name": embedding.sd_checkpoint_name,
|
||||
"shape": embedding.shape,
|
||||
"vectors": embedding.vectors,
|
||||
}
|
||||
|
||||
def convert_embeddings(embeddings):
|
||||
return {embedding.name: convert_embedding(embedding) for embedding in embeddings.values()}
|
||||
|
||||
return {
|
||||
"loaded": convert_embeddings(db.word_embeddings),
|
||||
"skipped": convert_embeddings(db.skipped_embeddings),
|
||||
}
|
||||
|
||||
def refresh_checkpoints(self):
|
||||
shared.refresh_checkpoints()
|
||||
|
||||
def create_embedding(self, args: dict):
|
||||
try:
|
||||
shared.state.begin()
|
||||
filename = create_embedding(**args) # create empty embedding
|
||||
sd_hijack.model_hijack.embedding_db.load_textual_inversion_embeddings() # reload embeddings so new one can be immediately used
|
||||
shared.state.end()
|
||||
return CreateResponse(info = "create embedding filename: {filename}".format(filename = filename))
|
||||
except AssertionError as e:
|
||||
shared.state.end()
|
||||
return TrainResponse(info = "create embedding error: {error}".format(error = e))
|
||||
|
||||
def create_hypernetwork(self, args: dict):
|
||||
try:
|
||||
shared.state.begin()
|
||||
filename = create_hypernetwork(**args) # create empty embedding
|
||||
shared.state.end()
|
||||
return CreateResponse(info = "create hypernetwork filename: {filename}".format(filename = filename))
|
||||
except AssertionError as e:
|
||||
shared.state.end()
|
||||
return TrainResponse(info = "create hypernetwork error: {error}".format(error = e))
|
||||
|
||||
def preprocess(self, args: dict):
|
||||
try:
|
||||
shared.state.begin()
|
||||
preprocess(**args) # quick operation unless blip/booru interrogation is enabled
|
||||
shared.state.end()
|
||||
return PreprocessResponse(info = 'preprocess complete')
|
||||
except KeyError as e:
|
||||
shared.state.end()
|
||||
return PreprocessResponse(info = "preprocess error: invalid token: {error}".format(error = e))
|
||||
except AssertionError as e:
|
||||
shared.state.end()
|
||||
return PreprocessResponse(info = "preprocess error: {error}".format(error = e))
|
||||
except FileNotFoundError as e:
|
||||
shared.state.end()
|
||||
return PreprocessResponse(info = 'preprocess error: {error}'.format(error = e))
|
||||
|
||||
def train_embedding(self, args: dict):
|
||||
try:
|
||||
shared.state.begin()
|
||||
apply_optimizations = shared.opts.training_xattention_optimizations
|
||||
error = None
|
||||
filename = ''
|
||||
if not apply_optimizations:
|
||||
sd_hijack.undo_optimizations()
|
||||
try:
|
||||
embedding, filename = train_embedding(**args) # can take a long time to complete
|
||||
except Exception as e:
|
||||
error = e
|
||||
finally:
|
||||
if not apply_optimizations:
|
||||
sd_hijack.apply_optimizations()
|
||||
shared.state.end()
|
||||
return TrainResponse(info = "train embedding complete: filename: {filename} error: {error}".format(filename = filename, error = error))
|
||||
except AssertionError as msg:
|
||||
shared.state.end()
|
||||
return TrainResponse(info = "train embedding error: {msg}".format(msg = msg))
|
||||
|
||||
def train_hypernetwork(self, args: dict):
|
||||
try:
|
||||
shared.state.begin()
|
||||
shared.loaded_hypernetworks = []
|
||||
apply_optimizations = shared.opts.training_xattention_optimizations
|
||||
error = None
|
||||
filename = ''
|
||||
if not apply_optimizations:
|
||||
sd_hijack.undo_optimizations()
|
||||
try:
|
||||
hypernetwork, filename = train_hypernetwork(**args)
|
||||
except Exception as e:
|
||||
error = e
|
||||
finally:
|
||||
shared.sd_model.cond_stage_model.to(devices.device)
|
||||
shared.sd_model.first_stage_model.to(devices.device)
|
||||
if not apply_optimizations:
|
||||
sd_hijack.apply_optimizations()
|
||||
shared.state.end()
|
||||
return TrainResponse(info="train embedding complete: filename: {filename} error: {error}".format(filename=filename, error=error))
|
||||
except AssertionError as msg:
|
||||
shared.state.end()
|
||||
return TrainResponse(info="train embedding error: {error}".format(error=error))
|
||||
|
||||
def get_memory(self):
|
||||
try:
|
||||
import os, psutil
|
||||
process = psutil.Process(os.getpid())
|
||||
res = process.memory_info() # only rss is cross-platform guaranteed so we dont rely on other values
|
||||
ram_total = 100 * res.rss / process.memory_percent() # and total memory is calculated as actual value is not cross-platform safe
|
||||
ram = { 'free': ram_total - res.rss, 'used': res.rss, 'total': ram_total }
|
||||
except Exception as err:
|
||||
ram = { 'error': f'{err}' }
|
||||
try:
|
||||
import torch
|
||||
if torch.cuda.is_available():
|
||||
s = torch.cuda.mem_get_info()
|
||||
system = { 'free': s[0], 'used': s[1] - s[0], 'total': s[1] }
|
||||
s = dict(torch.cuda.memory_stats(shared.device))
|
||||
allocated = { 'current': s['allocated_bytes.all.current'], 'peak': s['allocated_bytes.all.peak'] }
|
||||
reserved = { 'current': s['reserved_bytes.all.current'], 'peak': s['reserved_bytes.all.peak'] }
|
||||
active = { 'current': s['active_bytes.all.current'], 'peak': s['active_bytes.all.peak'] }
|
||||
inactive = { 'current': s['inactive_split_bytes.all.current'], 'peak': s['inactive_split_bytes.all.peak'] }
|
||||
warnings = { 'retries': s['num_alloc_retries'], 'oom': s['num_ooms'] }
|
||||
cuda = {
|
||||
'system': system,
|
||||
'active': active,
|
||||
'allocated': allocated,
|
||||
'reserved': reserved,
|
||||
'inactive': inactive,
|
||||
'events': warnings,
|
||||
}
|
||||
else:
|
||||
cuda = { 'error': 'unavailable' }
|
||||
except Exception as err:
|
||||
cuda = { 'error': f'{err}' }
|
||||
return MemoryResponse(ram = ram, cuda = cuda)
|
||||
|
||||
def launch(self, server_name, port):
|
||||
self.app.include_router(self.router)
|
||||
uvicorn.run(self.app, host=server_name, port=port)
|
||||
@@ -0,0 +1,269 @@
|
||||
import inspect
|
||||
from pydantic import BaseModel, Field, create_model
|
||||
from typing import Any, Optional
|
||||
from typing_extensions import Literal
|
||||
from inflection import underscore
|
||||
from modules.processing import StableDiffusionProcessingTxt2Img, StableDiffusionProcessingImg2Img
|
||||
from modules.shared import sd_upscalers, opts, parser
|
||||
from typing import Dict, List
|
||||
|
||||
API_NOT_ALLOWED = [
|
||||
"self",
|
||||
"kwargs",
|
||||
"sd_model",
|
||||
"outpath_samples",
|
||||
"outpath_grids",
|
||||
"sampler_index",
|
||||
"do_not_save_samples",
|
||||
"do_not_save_grid",
|
||||
"extra_generation_params",
|
||||
"overlay_images",
|
||||
"do_not_reload_embeddings",
|
||||
"seed_enable_extras",
|
||||
"prompt_for_display",
|
||||
"sampler_noise_scheduler_override",
|
||||
"ddim_discretize"
|
||||
]
|
||||
|
||||
class ModelDef(BaseModel):
|
||||
"""Assistance Class for Pydantic Dynamic Model Generation"""
|
||||
|
||||
field: str
|
||||
field_alias: str
|
||||
field_type: Any
|
||||
field_value: Any
|
||||
field_exclude: bool = False
|
||||
|
||||
|
||||
class PydanticModelGenerator:
|
||||
"""
|
||||
Takes in created classes and stubs them out in a way FastAPI/Pydantic is happy about:
|
||||
source_data is a snapshot of the default values produced by the class
|
||||
params are the names of the actual keys required by __init__
|
||||
"""
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
model_name: str = None,
|
||||
class_instance = None,
|
||||
additional_fields = None,
|
||||
):
|
||||
def field_type_generator(k, v):
|
||||
# field_type = str if not overrides.get(k) else overrides[k]["type"]
|
||||
# print(k, v.annotation, v.default)
|
||||
field_type = v.annotation
|
||||
|
||||
return Optional[field_type]
|
||||
|
||||
def merge_class_params(class_):
|
||||
all_classes = list(filter(lambda x: x is not object, inspect.getmro(class_)))
|
||||
parameters = {}
|
||||
for classes in all_classes:
|
||||
parameters = {**parameters, **inspect.signature(classes.__init__).parameters}
|
||||
return parameters
|
||||
|
||||
|
||||
self._model_name = model_name
|
||||
self._class_data = merge_class_params(class_instance)
|
||||
|
||||
self._model_def = [
|
||||
ModelDef(
|
||||
field=underscore(k),
|
||||
field_alias=k,
|
||||
field_type=field_type_generator(k, v),
|
||||
field_value=v.default
|
||||
)
|
||||
for (k,v) in self._class_data.items() if k not in API_NOT_ALLOWED
|
||||
]
|
||||
|
||||
for fields in additional_fields:
|
||||
self._model_def.append(ModelDef(
|
||||
field=underscore(fields["key"]),
|
||||
field_alias=fields["key"],
|
||||
field_type=fields["type"],
|
||||
field_value=fields["default"],
|
||||
field_exclude=fields["exclude"] if "exclude" in fields else False))
|
||||
|
||||
def generate_model(self):
|
||||
"""
|
||||
Creates a pydantic BaseModel
|
||||
from the json and overrides provided at initialization
|
||||
"""
|
||||
fields = {
|
||||
d.field: (d.field_type, Field(default=d.field_value, alias=d.field_alias, exclude=d.field_exclude)) for d in self._model_def
|
||||
}
|
||||
DynamicModel = create_model(self._model_name, **fields)
|
||||
DynamicModel.__config__.allow_population_by_field_name = True
|
||||
DynamicModel.__config__.allow_mutation = True
|
||||
return DynamicModel
|
||||
|
||||
StableDiffusionTxt2ImgProcessingAPI = PydanticModelGenerator(
|
||||
"StableDiffusionProcessingTxt2Img",
|
||||
StableDiffusionProcessingTxt2Img,
|
||||
[{"key": "sampler_index", "type": str, "default": "Euler"}, {"key": "script_name", "type": str, "default": None}, {"key": "script_args", "type": list, "default": []}]
|
||||
).generate_model()
|
||||
|
||||
StableDiffusionImg2ImgProcessingAPI = PydanticModelGenerator(
|
||||
"StableDiffusionProcessingImg2Img",
|
||||
StableDiffusionProcessingImg2Img,
|
||||
[{"key": "sampler_index", "type": str, "default": "Euler"}, {"key": "init_images", "type": list, "default": None}, {"key": "denoising_strength", "type": float, "default": 0.75}, {"key": "mask", "type": str, "default": None}, {"key": "include_init_images", "type": bool, "default": False, "exclude" : True}, {"key": "script_name", "type": str, "default": None}, {"key": "script_args", "type": list, "default": []}]
|
||||
).generate_model()
|
||||
|
||||
class TextToImageResponse(BaseModel):
|
||||
images: List[str] = Field(default=None, title="Image", description="The generated image in base64 format.")
|
||||
parameters: dict
|
||||
info: str
|
||||
|
||||
class ImageToImageResponse(BaseModel):
|
||||
images: List[str] = Field(default=None, title="Image", description="The generated image in base64 format.")
|
||||
parameters: dict
|
||||
info: str
|
||||
|
||||
class ExtrasBaseRequest(BaseModel):
|
||||
resize_mode: Literal[0, 1] = Field(default=0, title="Resize Mode", description="Sets the resize mode: 0 to upscale by upscaling_resize amount, 1 to upscale up to upscaling_resize_h x upscaling_resize_w.")
|
||||
show_extras_results: bool = Field(default=True, title="Show results", description="Should the backend return the generated image?")
|
||||
gfpgan_visibility: float = Field(default=0, title="GFPGAN Visibility", ge=0, le=1, allow_inf_nan=False, description="Sets the visibility of GFPGAN, values should be between 0 and 1.")
|
||||
codeformer_visibility: float = Field(default=0, title="CodeFormer Visibility", ge=0, le=1, allow_inf_nan=False, description="Sets the visibility of CodeFormer, values should be between 0 and 1.")
|
||||
codeformer_weight: float = Field(default=0, title="CodeFormer Weight", ge=0, le=1, allow_inf_nan=False, description="Sets the weight of CodeFormer, values should be between 0 and 1.")
|
||||
upscaling_resize: float = Field(default=2, title="Upscaling Factor", ge=1, le=8, description="By how much to upscale the image, only used when resize_mode=0.")
|
||||
upscaling_resize_w: int = Field(default=512, title="Target Width", ge=1, description="Target width for the upscaler to hit. Only used when resize_mode=1.")
|
||||
upscaling_resize_h: int = Field(default=512, title="Target Height", ge=1, description="Target height for the upscaler to hit. Only used when resize_mode=1.")
|
||||
upscaling_crop: bool = Field(default=True, title="Crop to fit", description="Should the upscaler crop the image to fit in the chosen size?")
|
||||
upscaler_1: str = Field(default="None", title="Main upscaler", description=f"The name of the main upscaler to use, it has to be one of this list: {' , '.join([x.name for x in sd_upscalers])}")
|
||||
upscaler_2: str = Field(default="None", title="Secondary upscaler", description=f"The name of the secondary upscaler to use, it has to be one of this list: {' , '.join([x.name for x in sd_upscalers])}")
|
||||
extras_upscaler_2_visibility: float = Field(default=0, title="Secondary upscaler visibility", ge=0, le=1, allow_inf_nan=False, description="Sets the visibility of secondary upscaler, values should be between 0 and 1.")
|
||||
upscale_first: bool = Field(default=False, title="Upscale first", description="Should the upscaler run before restoring faces?")
|
||||
|
||||
class ExtraBaseResponse(BaseModel):
|
||||
html_info: str = Field(title="HTML info", description="A series of HTML tags containing the process info.")
|
||||
|
||||
class ExtrasSingleImageRequest(ExtrasBaseRequest):
|
||||
image: str = Field(default="", title="Image", description="Image to work on, must be a Base64 string containing the image's data.")
|
||||
|
||||
class ExtrasSingleImageResponse(ExtraBaseResponse):
|
||||
image: str = Field(default=None, title="Image", description="The generated image in base64 format.")
|
||||
|
||||
class FileData(BaseModel):
|
||||
data: str = Field(title="File data", description="Base64 representation of the file")
|
||||
name: str = Field(title="File name")
|
||||
|
||||
class ExtrasBatchImagesRequest(ExtrasBaseRequest):
|
||||
imageList: List[FileData] = Field(title="Images", description="List of images to work on. Must be Base64 strings")
|
||||
|
||||
class ExtrasBatchImagesResponse(ExtraBaseResponse):
|
||||
images: List[str] = Field(title="Images", description="The generated images in base64 format.")
|
||||
|
||||
class PNGInfoRequest(BaseModel):
|
||||
image: str = Field(title="Image", description="The base64 encoded PNG image")
|
||||
|
||||
class PNGInfoResponse(BaseModel):
|
||||
info: str = Field(title="Image info", description="A string with the parameters used to generate the image")
|
||||
items: dict = Field(title="Items", description="An object containing all the info the image had")
|
||||
|
||||
class ProgressRequest(BaseModel):
|
||||
skip_current_image: bool = Field(default=False, title="Skip current image", description="Skip current image serialization")
|
||||
|
||||
class ProgressResponse(BaseModel):
|
||||
progress: float = Field(title="Progress", description="The progress with a range of 0 to 1")
|
||||
eta_relative: float = Field(title="ETA in secs")
|
||||
state: dict = Field(title="State", description="The current state snapshot")
|
||||
current_image: str = Field(default=None, title="Current image", description="The current image in base64 format. opts.show_progress_every_n_steps is required for this to work.")
|
||||
textinfo: str = Field(default=None, title="Info text", description="Info text used by WebUI.")
|
||||
|
||||
class InterrogateRequest(BaseModel):
|
||||
image: str = Field(default="", title="Image", description="Image to work on, must be a Base64 string containing the image's data.")
|
||||
model: str = Field(default="clip", title="Model", description="The interrogate model used.")
|
||||
|
||||
class InterrogateResponse(BaseModel):
|
||||
caption: str = Field(default=None, title="Caption", description="The generated caption for the image.")
|
||||
|
||||
class TrainResponse(BaseModel):
|
||||
info: str = Field(title="Train info", description="Response string from train embedding or hypernetwork task.")
|
||||
|
||||
class CreateResponse(BaseModel):
|
||||
info: str = Field(title="Create info", description="Response string from create embedding or hypernetwork task.")
|
||||
|
||||
class PreprocessResponse(BaseModel):
|
||||
info: str = Field(title="Preprocess info", description="Response string from preprocessing task.")
|
||||
|
||||
fields = {}
|
||||
for key, metadata in opts.data_labels.items():
|
||||
value = opts.data.get(key)
|
||||
optType = opts.typemap.get(type(metadata.default), type(value))
|
||||
|
||||
if (metadata is not None):
|
||||
fields.update({key: (Optional[optType], Field(
|
||||
default=metadata.default ,description=metadata.label))})
|
||||
else:
|
||||
fields.update({key: (Optional[optType], Field())})
|
||||
|
||||
OptionsModel = create_model("Options", **fields)
|
||||
|
||||
flags = {}
|
||||
_options = vars(parser)['_option_string_actions']
|
||||
for key in _options:
|
||||
if(_options[key].dest != 'help'):
|
||||
flag = _options[key]
|
||||
_type = str
|
||||
if _options[key].default is not None: _type = type(_options[key].default)
|
||||
flags.update({flag.dest: (_type,Field(default=flag.default, description=flag.help))})
|
||||
|
||||
FlagsModel = create_model("Flags", **flags)
|
||||
|
||||
class SamplerItem(BaseModel):
|
||||
name: str = Field(title="Name")
|
||||
aliases: List[str] = Field(title="Aliases")
|
||||
options: Dict[str, str] = Field(title="Options")
|
||||
|
||||
class UpscalerItem(BaseModel):
|
||||
name: str = Field(title="Name")
|
||||
model_name: Optional[str] = Field(title="Model Name")
|
||||
model_path: Optional[str] = Field(title="Path")
|
||||
model_url: Optional[str] = Field(title="URL")
|
||||
scale: Optional[float] = Field(title="Scale")
|
||||
|
||||
class SDModelItem(BaseModel):
|
||||
title: str = Field(title="Title")
|
||||
model_name: str = Field(title="Model Name")
|
||||
hash: Optional[str] = Field(title="Short hash")
|
||||
sha256: Optional[str] = Field(title="sha256 hash")
|
||||
filename: str = Field(title="Filename")
|
||||
config: Optional[str] = Field(title="Config file")
|
||||
|
||||
class HypernetworkItem(BaseModel):
|
||||
name: str = Field(title="Name")
|
||||
path: Optional[str] = Field(title="Path")
|
||||
|
||||
class FaceRestorerItem(BaseModel):
|
||||
name: str = Field(title="Name")
|
||||
cmd_dir: Optional[str] = Field(title="Path")
|
||||
|
||||
class RealesrganItem(BaseModel):
|
||||
name: str = Field(title="Name")
|
||||
path: Optional[str] = Field(title="Path")
|
||||
scale: Optional[int] = Field(title="Scale")
|
||||
|
||||
class PromptStyleItem(BaseModel):
|
||||
name: str = Field(title="Name")
|
||||
prompt: Optional[str] = Field(title="Prompt")
|
||||
negative_prompt: Optional[str] = Field(title="Negative Prompt")
|
||||
|
||||
class ArtistItem(BaseModel):
|
||||
name: str = Field(title="Name")
|
||||
score: float = Field(title="Score")
|
||||
category: str = Field(title="Category")
|
||||
|
||||
class EmbeddingItem(BaseModel):
|
||||
step: Optional[int] = Field(title="Step", description="The number of steps that were used to train this embedding, if available")
|
||||
sd_checkpoint: Optional[str] = Field(title="SD Checkpoint", description="The hash of the checkpoint this embedding was trained on, if available")
|
||||
sd_checkpoint_name: Optional[str] = Field(title="SD Checkpoint Name", description="The name of the checkpoint this embedding was trained on, if available. Note that this is the name that was used by the trainer; for a stable identifier, use `sd_checkpoint` instead")
|
||||
shape: int = Field(title="Shape", description="The length of each individual vector in the embedding")
|
||||
vectors: int = Field(title="Vectors", description="The number of vectors in the embedding")
|
||||
|
||||
class EmbeddingsResponse(BaseModel):
|
||||
loaded: Dict[str, EmbeddingItem] = Field(title="Loaded", description="Embeddings loaded for the current model")
|
||||
skipped: Dict[str, EmbeddingItem] = Field(title="Skipped", description="Embeddings skipped for the current model (likely due to architecture incompatibility)")
|
||||
|
||||
class MemoryResponse(BaseModel):
|
||||
ram: dict = Field(title="RAM", description="System memory stats")
|
||||
cuda: dict = Field(title="CUDA", description="nVidia CUDA memory stats")
|
||||
@@ -0,0 +1,264 @@
|
||||
import torch
|
||||
from torch.nn.functional import silu
|
||||
from types import MethodType
|
||||
|
||||
import modules.textual_inversion.textual_inversion
|
||||
from modules import devices, sd_hijack_optimizations, shared, sd_hijack_checkpoint
|
||||
from modules.hypernetworks import hypernetwork
|
||||
from modules.shared import cmd_opts
|
||||
from modules import sd_hijack_clip, sd_hijack_open_clip, sd_hijack_unet, sd_hijack_xlmr, xlmr
|
||||
|
||||
import ldm.modules.attention
|
||||
import ldm.modules.diffusionmodules.model
|
||||
import ldm.modules.diffusionmodules.openaimodel
|
||||
import ldm.models.diffusion.ddim
|
||||
import ldm.models.diffusion.plms
|
||||
import ldm.modules.encoders.modules
|
||||
|
||||
attention_CrossAttention_forward = ldm.modules.attention.CrossAttention.forward
|
||||
diffusionmodules_model_nonlinearity = ldm.modules.diffusionmodules.model.nonlinearity
|
||||
diffusionmodules_model_AttnBlock_forward = ldm.modules.diffusionmodules.model.AttnBlock.forward
|
||||
|
||||
# new memory efficient cross attention blocks do not support hypernets and we already
|
||||
# have memory efficient cross attention anyway, so this disables SD2.0's memory efficient cross attention
|
||||
ldm.modules.attention.MemoryEfficientCrossAttention = ldm.modules.attention.CrossAttention
|
||||
ldm.modules.attention.BasicTransformerBlock.ATTENTION_MODES["softmax-xformers"] = ldm.modules.attention.CrossAttention
|
||||
|
||||
# silence new console spam from SD2
|
||||
ldm.modules.attention.print = lambda *args: None
|
||||
ldm.modules.diffusionmodules.model.print = lambda *args: None
|
||||
|
||||
|
||||
def apply_optimizations():
|
||||
undo_optimizations()
|
||||
|
||||
ldm.modules.diffusionmodules.model.nonlinearity = silu
|
||||
ldm.modules.diffusionmodules.openaimodel.th = sd_hijack_unet.th
|
||||
|
||||
optimization_method = None
|
||||
|
||||
if cmd_opts.force_enable_xformers or (cmd_opts.xformers and shared.xformers_available and torch.version.cuda and (6, 0) <= torch.cuda.get_device_capability(shared.device) <= (9, 0)):
|
||||
print("Applying xformers cross attention optimization.")
|
||||
ldm.modules.attention.CrossAttention.forward = sd_hijack_optimizations.xformers_attention_forward
|
||||
ldm.modules.diffusionmodules.model.AttnBlock.forward = sd_hijack_optimizations.xformers_attnblock_forward
|
||||
optimization_method = 'xformers'
|
||||
elif cmd_opts.opt_sub_quad_attention:
|
||||
print("Applying sub-quadratic cross attention optimization.")
|
||||
ldm.modules.attention.CrossAttention.forward = sd_hijack_optimizations.sub_quad_attention_forward
|
||||
ldm.modules.diffusionmodules.model.AttnBlock.forward = sd_hijack_optimizations.sub_quad_attnblock_forward
|
||||
optimization_method = 'sub-quadratic'
|
||||
elif cmd_opts.opt_split_attention_v1:
|
||||
print("Applying v1 cross attention optimization.")
|
||||
ldm.modules.attention.CrossAttention.forward = sd_hijack_optimizations.split_cross_attention_forward_v1
|
||||
optimization_method = 'V1'
|
||||
elif not cmd_opts.disable_opt_split_attention and (cmd_opts.opt_split_attention_invokeai or not cmd_opts.opt_split_attention and not torch.cuda.is_available()):
|
||||
print("Applying cross attention optimization (InvokeAI).")
|
||||
ldm.modules.attention.CrossAttention.forward = sd_hijack_optimizations.split_cross_attention_forward_invokeAI
|
||||
optimization_method = 'InvokeAI'
|
||||
elif not cmd_opts.disable_opt_split_attention and (cmd_opts.opt_split_attention or torch.cuda.is_available()):
|
||||
print("Applying cross attention optimization (Doggettx).")
|
||||
ldm.modules.attention.CrossAttention.forward = sd_hijack_optimizations.split_cross_attention_forward
|
||||
ldm.modules.diffusionmodules.model.AttnBlock.forward = sd_hijack_optimizations.cross_attention_attnblock_forward
|
||||
optimization_method = 'Doggettx'
|
||||
|
||||
return optimization_method
|
||||
|
||||
|
||||
def undo_optimizations():
|
||||
ldm.modules.attention.CrossAttention.forward = hypernetwork.attention_CrossAttention_forward
|
||||
ldm.modules.diffusionmodules.model.nonlinearity = diffusionmodules_model_nonlinearity
|
||||
ldm.modules.diffusionmodules.model.AttnBlock.forward = diffusionmodules_model_AttnBlock_forward
|
||||
|
||||
|
||||
def fix_checkpoint():
|
||||
"""checkpoints are now added and removed in embedding/hypernet code, since torch doesn't want
|
||||
checkpoints to be added when not training (there's a warning)"""
|
||||
|
||||
pass
|
||||
|
||||
|
||||
def weighted_loss(sd_model, pred, target, mean=True):
|
||||
#Calculate the weight normally, but ignore the mean
|
||||
loss = sd_model._old_get_loss(pred, target, mean=False)
|
||||
|
||||
#Check if we have weights available
|
||||
weight = getattr(sd_model, '_custom_loss_weight', None)
|
||||
if weight is not None:
|
||||
loss *= weight
|
||||
|
||||
#Return the loss, as mean if specified
|
||||
return loss.mean() if mean else loss
|
||||
|
||||
def weighted_forward(sd_model, x, c, w, *args, **kwargs):
|
||||
try:
|
||||
#Temporarily append weights to a place accessible during loss calc
|
||||
sd_model._custom_loss_weight = w
|
||||
|
||||
#Replace 'get_loss' with a weight-aware one. Otherwise we need to reimplement 'forward' completely
|
||||
#Keep 'get_loss', but don't overwrite the previous old_get_loss if it's already set
|
||||
if not hasattr(sd_model, '_old_get_loss'):
|
||||
sd_model._old_get_loss = sd_model.get_loss
|
||||
sd_model.get_loss = MethodType(weighted_loss, sd_model)
|
||||
|
||||
#Run the standard forward function, but with the patched 'get_loss'
|
||||
return sd_model.forward(x, c, *args, **kwargs)
|
||||
finally:
|
||||
try:
|
||||
#Delete temporary weights if appended
|
||||
del sd_model._custom_loss_weight
|
||||
except AttributeError as e:
|
||||
pass
|
||||
|
||||
#If we have an old loss function, reset the loss function to the original one
|
||||
if hasattr(sd_model, '_old_get_loss'):
|
||||
sd_model.get_loss = sd_model._old_get_loss
|
||||
del sd_model._old_get_loss
|
||||
|
||||
def apply_weighted_forward(sd_model):
|
||||
#Add new function 'weighted_forward' that can be called to calc weighted loss
|
||||
sd_model.weighted_forward = MethodType(weighted_forward, sd_model)
|
||||
|
||||
def undo_weighted_forward(sd_model):
|
||||
try:
|
||||
del sd_model.weighted_forward
|
||||
except AttributeError as e:
|
||||
pass
|
||||
|
||||
|
||||
class StableDiffusionModelHijack:
|
||||
fixes = None
|
||||
comments = []
|
||||
layers = None
|
||||
circular_enabled = False
|
||||
clip = None
|
||||
optimization_method = None
|
||||
|
||||
embedding_db = modules.textual_inversion.textual_inversion.EmbeddingDatabase()
|
||||
|
||||
def __init__(self):
|
||||
self.embedding_db.add_embedding_dir(cmd_opts.embeddings_dir)
|
||||
|
||||
def hijack(self, m):
|
||||
if type(m.cond_stage_model) == xlmr.BertSeriesModelWithTransformation:
|
||||
model_embeddings = m.cond_stage_model.roberta.embeddings
|
||||
model_embeddings.token_embedding = EmbeddingsWithFixes(model_embeddings.word_embeddings, self)
|
||||
m.cond_stage_model = sd_hijack_xlmr.FrozenXLMREmbedderWithCustomWords(m.cond_stage_model, self)
|
||||
|
||||
elif type(m.cond_stage_model) == ldm.modules.encoders.modules.FrozenCLIPEmbedder:
|
||||
model_embeddings = m.cond_stage_model.transformer.text_model.embeddings
|
||||
model_embeddings.token_embedding = EmbeddingsWithFixes(model_embeddings.token_embedding, self)
|
||||
m.cond_stage_model = sd_hijack_clip.FrozenCLIPEmbedderWithCustomWords(m.cond_stage_model, self)
|
||||
|
||||
elif type(m.cond_stage_model) == ldm.modules.encoders.modules.FrozenOpenCLIPEmbedder:
|
||||
m.cond_stage_model.model.token_embedding = EmbeddingsWithFixes(m.cond_stage_model.model.token_embedding, self)
|
||||
m.cond_stage_model = sd_hijack_open_clip.FrozenOpenCLIPEmbedderWithCustomWords(m.cond_stage_model, self)
|
||||
|
||||
apply_weighted_forward(m)
|
||||
if m.cond_stage_key == "edit":
|
||||
sd_hijack_unet.hijack_ddpm_edit()
|
||||
|
||||
self.optimization_method = apply_optimizations()
|
||||
|
||||
self.clip = m.cond_stage_model
|
||||
|
||||
def flatten(el):
|
||||
flattened = [flatten(children) for children in el.children()]
|
||||
res = [el]
|
||||
for c in flattened:
|
||||
res += c
|
||||
return res
|
||||
|
||||
self.layers = flatten(m)
|
||||
|
||||
def undo_hijack(self, m):
|
||||
if type(m.cond_stage_model) == xlmr.BertSeriesModelWithTransformation:
|
||||
m.cond_stage_model = m.cond_stage_model.wrapped
|
||||
|
||||
elif type(m.cond_stage_model) == sd_hijack_clip.FrozenCLIPEmbedderWithCustomWords:
|
||||
m.cond_stage_model = m.cond_stage_model.wrapped
|
||||
|
||||
model_embeddings = m.cond_stage_model.transformer.text_model.embeddings
|
||||
if type(model_embeddings.token_embedding) == EmbeddingsWithFixes:
|
||||
model_embeddings.token_embedding = model_embeddings.token_embedding.wrapped
|
||||
elif type(m.cond_stage_model) == sd_hijack_open_clip.FrozenOpenCLIPEmbedderWithCustomWords:
|
||||
m.cond_stage_model.wrapped.model.token_embedding = m.cond_stage_model.wrapped.model.token_embedding.wrapped
|
||||
m.cond_stage_model = m.cond_stage_model.wrapped
|
||||
|
||||
undo_optimizations()
|
||||
undo_weighted_forward(m)
|
||||
|
||||
self.apply_circular(False)
|
||||
self.layers = None
|
||||
self.clip = None
|
||||
|
||||
def apply_circular(self, enable):
|
||||
if self.circular_enabled == enable:
|
||||
return
|
||||
|
||||
self.circular_enabled = enable
|
||||
|
||||
for layer in [layer for layer in self.layers if type(layer) == torch.nn.Conv2d]:
|
||||
layer.padding_mode = 'circular' if enable else 'zeros'
|
||||
|
||||
def clear_comments(self):
|
||||
self.comments = []
|
||||
|
||||
def get_prompt_lengths(self, text):
|
||||
_, token_count = self.clip.process_texts([text])
|
||||
|
||||
return token_count, self.clip.get_target_prompt_token_count(token_count)
|
||||
|
||||
|
||||
class EmbeddingsWithFixes(torch.nn.Module):
|
||||
def __init__(self, wrapped, embeddings):
|
||||
super().__init__()
|
||||
self.wrapped = wrapped
|
||||
self.embeddings = embeddings
|
||||
|
||||
def forward(self, input_ids):
|
||||
batch_fixes = self.embeddings.fixes
|
||||
self.embeddings.fixes = None
|
||||
|
||||
inputs_embeds = self.wrapped(input_ids)
|
||||
|
||||
if batch_fixes is None or len(batch_fixes) == 0 or max([len(x) for x in batch_fixes]) == 0:
|
||||
return inputs_embeds
|
||||
|
||||
vecs = []
|
||||
for fixes, tensor in zip(batch_fixes, inputs_embeds):
|
||||
for offset, embedding in fixes:
|
||||
emb = devices.cond_cast_unet(embedding.vec)
|
||||
emb_len = min(tensor.shape[0] - offset - 1, emb.shape[0])
|
||||
tensor = torch.cat([tensor[0:offset + 1], emb[0:emb_len], tensor[offset + 1 + emb_len:]])
|
||||
|
||||
vecs.append(tensor)
|
||||
|
||||
return torch.stack(vecs)
|
||||
|
||||
|
||||
def add_circular_option_to_conv_2d():
|
||||
conv2d_constructor = torch.nn.Conv2d.__init__
|
||||
|
||||
def conv2d_constructor_circular(self, *args, **kwargs):
|
||||
return conv2d_constructor(self, *args, padding_mode='circular', **kwargs)
|
||||
|
||||
torch.nn.Conv2d.__init__ = conv2d_constructor_circular
|
||||
|
||||
|
||||
model_hijack = StableDiffusionModelHijack()
|
||||
|
||||
|
||||
def register_buffer(self, name, attr):
|
||||
"""
|
||||
Fix register buffer bug for Mac OS.
|
||||
"""
|
||||
|
||||
if type(attr) == torch.Tensor:
|
||||
if attr.device != devices.device:
|
||||
attr = attr.to(device=devices.device, dtype=(torch.float32 if devices.device.type == 'mps' else None))
|
||||
|
||||
setattr(self, name, attr)
|
||||
|
||||
|
||||
ldm.models.diffusion.ddim.DDIMSampler.register_buffer = register_buffer
|
||||
ldm.models.diffusion.plms.PLMSSampler.register_buffer = register_buffer
|
||||
@@ -0,0 +1,39 @@
|
||||
import html
|
||||
import json
|
||||
import os
|
||||
import urllib.parse
|
||||
|
||||
from modules import shared, ui_extra_networks, sd_models
|
||||
|
||||
|
||||
class ExtraNetworksPageCheckpoints(ui_extra_networks.ExtraNetworksPage):
|
||||
def __init__(self):
|
||||
super().__init__('Checkpoints')
|
||||
|
||||
def refresh(self):
|
||||
shared.refresh_checkpoints()
|
||||
|
||||
def list_items(self):
|
||||
checkpoint: sd_models.CheckpointInfo
|
||||
for name, checkpoint in sd_models.checkpoints_list.items():
|
||||
path, ext = os.path.splitext(checkpoint.filename)
|
||||
previews = [path + ".png", path + ".preview.png"]
|
||||
|
||||
preview = None
|
||||
for file in previews:
|
||||
if os.path.isfile(file):
|
||||
preview = self.link_preview(file)
|
||||
break
|
||||
|
||||
yield {
|
||||
"name": checkpoint.name_for_extra,
|
||||
"filename": path,
|
||||
"preview": preview,
|
||||
"search_term": self.search_terms_from_path(checkpoint.filename) + " " + (checkpoint.sha256 or ""),
|
||||
"onclick": '"' + html.escape(f"""return selectCheckpoint({json.dumps(name)})""") + '"',
|
||||
"local_preview": path + ".png",
|
||||
}
|
||||
|
||||
def allowed_directories_for_previews(self):
|
||||
return [v for v in [shared.cmd_opts.ckpt_dir, sd_models.model_path] if v is not None]
|
||||
|
||||
@@ -0,0 +1,36 @@
|
||||
import json
|
||||
import os
|
||||
|
||||
from modules import shared, ui_extra_networks
|
||||
|
||||
|
||||
class ExtraNetworksPageHypernetworks(ui_extra_networks.ExtraNetworksPage):
|
||||
def __init__(self):
|
||||
super().__init__('Hypernetworks')
|
||||
|
||||
def refresh(self):
|
||||
shared.reload_hypernetworks()
|
||||
|
||||
def list_items(self):
|
||||
for name, path in shared.hypernetworks.items():
|
||||
path, ext = os.path.splitext(path)
|
||||
previews = [path + ".png", path + ".preview.png"]
|
||||
|
||||
preview = None
|
||||
for file in previews:
|
||||
if os.path.isfile(file):
|
||||
preview = self.link_preview(file)
|
||||
break
|
||||
|
||||
yield {
|
||||
"name": name,
|
||||
"filename": path,
|
||||
"preview": preview,
|
||||
"search_term": self.search_terms_from_path(path),
|
||||
"prompt": json.dumps(f"<hypernet:{name}:") + " + opts.extra_networks_default_multiplier + " + json.dumps(">"),
|
||||
"local_preview": path + ".png",
|
||||
}
|
||||
|
||||
def allowed_directories_for_previews(self):
|
||||
return [shared.cmd_opts.hypernetwork_dir]
|
||||
|
||||
@@ -0,0 +1,34 @@
|
||||
import json
|
||||
import os
|
||||
|
||||
from modules import ui_extra_networks, sd_hijack
|
||||
|
||||
|
||||
class ExtraNetworksPageTextualInversion(ui_extra_networks.ExtraNetworksPage):
|
||||
def __init__(self):
|
||||
super().__init__('Textual Inversion')
|
||||
self.allow_negative_prompt = True
|
||||
|
||||
def refresh(self):
|
||||
sd_hijack.model_hijack.embedding_db.load_textual_inversion_embeddings(force_reload=True)
|
||||
|
||||
def list_items(self):
|
||||
for embedding in sd_hijack.model_hijack.embedding_db.word_embeddings.values():
|
||||
path, ext = os.path.splitext(embedding.filename)
|
||||
preview_file = path + ".preview.png"
|
||||
|
||||
preview = None
|
||||
if os.path.isfile(preview_file):
|
||||
preview = self.link_preview(preview_file)
|
||||
|
||||
yield {
|
||||
"name": embedding.name,
|
||||
"filename": embedding.filename,
|
||||
"preview": preview,
|
||||
"search_term": self.search_terms_from_path(embedding.filename),
|
||||
"prompt": json.dumps(embedding.name),
|
||||
"local_preview": path + ".preview.png",
|
||||
}
|
||||
|
||||
def allowed_directories_for_previews(self):
|
||||
return list(sd_hijack.model_hijack.embedding_db.embedding_dirs)
|
||||
@@ -0,0 +1,80 @@
|
||||
import unittest
|
||||
import requests
|
||||
|
||||
|
||||
class TestTxt2ImgWorking(unittest.TestCase):
|
||||
def setUp(self):
|
||||
self.url_txt2img = "http://localhost:7860/sdapi/v1/txt2img"
|
||||
self.simple_txt2img = {
|
||||
"enable_hr": False,
|
||||
"denoising_strength": 0,
|
||||
"firstphase_width": 0,
|
||||
"firstphase_height": 0,
|
||||
"prompt": "example prompt",
|
||||
"styles": [],
|
||||
"seed": -1,
|
||||
"subseed": -1,
|
||||
"subseed_strength": 0,
|
||||
"seed_resize_from_h": -1,
|
||||
"seed_resize_from_w": -1,
|
||||
"batch_size": 1,
|
||||
"n_iter": 1,
|
||||
"steps": 3,
|
||||
"cfg_scale": 7,
|
||||
"width": 64,
|
||||
"height": 64,
|
||||
"restore_faces": False,
|
||||
"tiling": False,
|
||||
"negative_prompt": "",
|
||||
"eta": 0,
|
||||
"s_churn": 0,
|
||||
"s_tmax": 0,
|
||||
"s_tmin": 0,
|
||||
"s_noise": 1,
|
||||
"sampler_index": "Euler a"
|
||||
}
|
||||
|
||||
def test_txt2img_simple_performed(self):
|
||||
self.assertEqual(requests.post(self.url_txt2img, json=self.simple_txt2img).status_code, 200)
|
||||
|
||||
def test_txt2img_with_negative_prompt_performed(self):
|
||||
self.simple_txt2img["negative_prompt"] = "example negative prompt"
|
||||
self.assertEqual(requests.post(self.url_txt2img, json=self.simple_txt2img).status_code, 200)
|
||||
|
||||
def test_txt2img_with_complex_prompt_performed(self):
|
||||
self.simple_txt2img["prompt"] = "((emphasis)), (emphasis1:1.1), [to:1], [from::2], [from:to:0.3], [alt|alt1]"
|
||||
self.assertEqual(requests.post(self.url_txt2img, json=self.simple_txt2img).status_code, 200)
|
||||
|
||||
def test_txt2img_not_square_image_performed(self):
|
||||
self.simple_txt2img["height"] = 128
|
||||
self.assertEqual(requests.post(self.url_txt2img, json=self.simple_txt2img).status_code, 200)
|
||||
|
||||
def test_txt2img_with_hrfix_performed(self):
|
||||
self.simple_txt2img["enable_hr"] = True
|
||||
self.assertEqual(requests.post(self.url_txt2img, json=self.simple_txt2img).status_code, 200)
|
||||
|
||||
def test_txt2img_with_tiling_performed(self):
|
||||
self.simple_txt2img["tiling"] = True
|
||||
self.assertEqual(requests.post(self.url_txt2img, json=self.simple_txt2img).status_code, 200)
|
||||
|
||||
def test_txt2img_with_restore_faces_performed(self):
|
||||
self.simple_txt2img["restore_faces"] = True
|
||||
self.assertEqual(requests.post(self.url_txt2img, json=self.simple_txt2img).status_code, 200)
|
||||
|
||||
def test_txt2img_with_vanilla_sampler_performed(self):
|
||||
self.simple_txt2img["sampler_index"] = "PLMS"
|
||||
self.assertEqual(requests.post(self.url_txt2img, json=self.simple_txt2img).status_code, 200)
|
||||
self.simple_txt2img["sampler_index"] = "DDIM"
|
||||
self.assertEqual(requests.post(self.url_txt2img, json=self.simple_txt2img).status_code, 200)
|
||||
|
||||
def test_txt2img_multiple_batches_performed(self):
|
||||
self.simple_txt2img["n_iter"] = 2
|
||||
self.assertEqual(requests.post(self.url_txt2img, json=self.simple_txt2img).status_code, 200)
|
||||
|
||||
def test_txt2img_batch_performed(self):
|
||||
self.simple_txt2img["batch_size"] = 2
|
||||
self.assertEqual(requests.post(self.url_txt2img, json=self.simple_txt2img).status_code, 200)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
unittest.main()
|
||||
@@ -0,0 +1,16 @@
|
||||
echo 'README.md
|
||||
extensions-builtin/Lora/ui_extra_networks_lora.py
|
||||
javascript/progressbar.js
|
||||
modules/api/api.py
|
||||
modules/api/models.py
|
||||
modules/models/diffusion/uni_pc/sampler.py
|
||||
modules/sd_hijack.py
|
||||
modules/ui_extra_networks_checkpoints.py
|
||||
modules/ui_extra_networks_hypernets.py
|
||||
modules/ui_extra_networks_textual_inversion.py
|
||||
test/basic_features/txt2img_test.py' | while read F; do
|
||||
echo "Creating backup" $F
|
||||
echo $F | cpio -pvd /tmp/backup
|
||||
echo "Copying original" $F
|
||||
echo ~/branches/automatic/$F | cpio -pvd .
|
||||
done
|
||||
Reference in New Issue
Block a user