Public/automatic
1
0
Fork 0
mirror of https://github.com/vladmandic/automatic synced 2026-09-18 16:54:33 +02:00
Code Issues Packages Projects Releases Wiki Activity

pre-merge cleanup

Browse Source
This commit is contained in:
Vladimir Mandic
2023-02-19 10:11:16 -05:00
parent fcd84f2c34
commit efd7ebb0a2
4 changed files with 233 additions and 217 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+149 -110
View File
@@ -1,123 +1,162 @@
# Stable Diffusion - Automatic
# Stable Diffusion web UI
A browser interface based on Gradio library for Stable Diffusion.
*Heavily opinionated custom fork of* <https://github.com/AUTOMATIC1111/stable-diffusion-webui>
![](screenshot.png)
![](ui-screenshot.jpg)
## 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
-
<br>
## 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.
## Notes
Alternatively, use online services (like Google Colab):
Fork is as close as up-to-date with origin as time allows
All code changes are merged upstream whenever possible
- [List of Online Services](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Online-Services)
Fork adds extra functionality:
- New skin and UI layout
- Ships with additional **extensions**
e.g. `System Info`, `Steps Animation`, etc.
- Ships with set of **CLI** tools that rely on *SD API* for execution:
e.g. `generate`, `train`, `bench`, etc.
[Full list](<cli/>)
### 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. Place stable diffusion checkpoint (`model.ckpt`) in the `models/Stable-diffusion` directory (see [dependencies](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Dependencies) for where to get it).
5. Run `webui-user.bat` from Windows Explorer as normal, non-administrator, user.
Simplified start script: `automatic.sh`
*Existing `webui.sh`/`webui.bat` still exist for backward compatibility, fresh installs to auto-install dependencies, etc.*
### 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)
```
> ./automatic.sh
### Installation on Apple Silicon
- Start in default mode with optimizations enabled
Additionally print environment info during startup
Example:
Find the instructions [here](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Installation-on-Apple-Silicon).
Version: b0b326f3 Wed Feb 15 09:07:04 2023 -0500
Repository: https://github.com/vladmandic/automatic
Last Merge: Sun Feb 5 07:03:27 2023 -0500 Merge pull request #35 from AUTOMATIC1111/master
Platform: Ubuntu 22.04.1 LTS 5.15.83.1-microsoft-standard-WSL2 x86_64
nVIDIA: NVIDIA GeForce RTX 3060, 528.49
Python: 3.10.6 Torch: 2.0.0.dev20230211+cu118 CUDA: 11.8 cuDNN: 8700 GPU: NVIDIA GeForce RTX 3060 Arch: (8, 6)
## Contributing
Here's how to add code to this repo: [Contributing](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Contributing)
> ./automatic.sh public
## Documentation
The documentation was moved from this README over to the project's [wiki](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki).
- Start with listen on public IP with authentication enabled
## Credits
Licenses for borrowed code can be found in `Settings -> Licenses` screen, and also in `html/licenses.html` file.
> ./automatic.sh clean
- Start with all optimizations disabled
Use this for troubleshooting
> ./automatic.sh install
- Installs and refreshes:
dependencies, submodules, extensions
<br>
## Install
1. Install `PyTorch` first
2. Clone and initialize repository
> git clone --depth 1 https://github.com/vladmandic/automatic
> cd automatic
> ./automatic.sh install
SD server: install
Installing general requirements
Installing versioned requirements
Updating submodules
Modules:
- 6c76a48 Mon Feb 13 00:03:00 2023 -0800 https://github.com/mcmonkeyprojects/sd-dynamic-thresholding
- a528cd5 Tue Jan 31 07:57:07 2023 -0500 https://github.com/vladmandic/sd-extension-aesthetic-scorer
- 7cf0e3a Tue Feb 7 07:39:40 2023 -0500 https://github.com/vladmandic/sd-extension-steps-animation
- b5d8e6a Thu Feb 9 15:25:18 2023 -0500 https://github.com/vladmandic/sd-extension-system-info
- 7a998ed Wed Feb 8 07:21:52 2023 -0500 https://github.com/Akegarasu/sd-webui-model-converter
- 0a5c897 Thu Feb 16 11:08:00 2023 +0100 https://github.com/yownas/seed_travel
- c8efd35 Mon Feb 13 21:51:25 2023 +0100 https://github.com/AlUlkesh/stable-diffusion-webui-images-browser
- 14d7b24 Thu Feb 16 22:35:47 2023 +0900 https://github.com/kohya-ss/sd-scripts
- b351828 Tue Feb 14 11:47:19 2023 -0500 https://github.com/vladmandic/automatic.wiki
Updating extensions
Extensions:
- e5b773a Sat Feb 11 19:38:18 2023 +0500 https://github.com/klimaleksus/stable-diffusion-webui-embedding-merge
- 0f3f699 Fri Dec 9 11:50:47 2022 +0800 https://github.com/yfszzx/stable-diffusion-webui-inspiration
<br>
## Differences
Fork does differ in few things:
- Drops compatibility with `python` **3.7** and requires **3.9**
- Updated **Python** libraries to latest known compatible versions
e.g. `accelerate`, `transformers`, `numpy`, etc.
- Includes opinionated **System** and **Options** configuration
e.g. `samplers`, `upscalers`, etc.
- Includes reskinned **UI**
Black and orange dark theme with fixed width options panels and larger previews
- Includes **SD2** configuration files
- Uses simplified folder structure
e.g. `/train`, `/outputs/*`
- Modified training templates
- Built-in `LoRA` training
- Built-in `Custom Diffusion` training
Only Python library which is not auto-updated is `PyTorch` itself as that is very system specific
For some Torch optimizations notes, see Wiki
Fork is compatible with regular **PyTorch 1.13** as well as pre-release of **PyTorch 2.0**
See [Wiki](https://github.com/vladmandic/automatic/wiki) for **Torch** optimization notes
<br>
## Scripts
This repository comes with a large collection of scripts that can be used to process inputs, train, generate, and benchmark models
As well as number of auxiliary scripts that do not rely on **WebUI**, but can be used for end-to-end solutions such as extract frames from videos, etc.
For full details see [Docs](cli/README.md)
<br>
## Docs
- Scripts are in [Scripts](cli/README.md)
- Everything else is in [Wiki](https://github.com/vladmandic/automatic/wiki)
- Except my current [TODO](TODO.md)
- 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)
modules/extensions.py
-6
View File
@@ -2,7 +2,6 @@ import os
import sys
import traceback
import time
import git
from modules import paths, shared
@@ -26,7 +25,6 @@ class Extension:
self.status = ''
self.can_update = False
self.is_builtin = is_builtin
self.version = ''
repo = None
try:
@@ -42,10 +40,6 @@ class Extension:
try:
self.remote = next(repo.remote().urls, None)
self.status = 'unknown'
head = repo.head.commit
ts = time.asctime(time.gmtime(repo.head.commit.committed_date))
self.version = f'{head.hexsha[:7]} ({ts})'
except Exception:
self.remote = None
modules/ui.py
+63 -81
View File
@@ -186,18 +186,18 @@ def create_seed_inputs(target_interface):
reuse_seed = gr.Button(reuse_symbol, elem_id=target_interface + '_reuse_seed')
with gr.Group(elem_id=target_interface + '_subseed_show_box'):
seed_checkbox = gr.Checkbox(label='Extra', elem_id=target_interface + '_subseed_show', value=True)
seed_checkbox = gr.Checkbox(label='Extra', elem_id=target_interface + '_subseed_show', value=False)
# Components to show/hide based on the 'Extra' checkbox
seed_extras = []
with FormRow(visible=True, elem_id=target_interface + '_subseed_row') as seed_extra_row_1:
with FormRow(visible=False, elem_id=target_interface + '_subseed_row') as seed_extra_row_1:
seed_extras.append(seed_extra_row_1)
subseed = gr.Number(label='Variation seed', value=-1, elem_id=target_interface + '_subseed')
subseed.style(container=False)
random_subseed = gr.Button(random_symbol, elem_id=target_interface + '_random_subseed')
reuse_subseed = gr.Button(reuse_symbol, elem_id=target_interface + '_reuse_subseed')
subseed_strength = gr.Slider(label='strength', value=0.0, minimum=0, maximum=1, step=0.01, elem_id=target_interface + '_subseed_strength')
subseed_strength = gr.Slider(label='Variation strength', value=0.0, minimum=0, maximum=1, step=0.01, elem_id=target_interface + '_subseed_strength')
with FormRow(visible=False) as seed_extra_row_2:
seed_extras.append(seed_extra_row_2)
@@ -476,32 +476,28 @@ def create_ui():
elif category == "dimensions":
with FormRow():
with gr.Column(elem_id="txt2img_column_size", scale=4):
with FormRow(elem_id="txt2img_row_dimension"):
width = gr.Slider(minimum=128, maximum=2048, step=8, label="Width", value=512, elem_id="txt2img_width")
height = gr.Slider(minimum=128, maximum=2048, step=8, label="Height", value=512, elem_id="txt2img_height")
width = gr.Slider(minimum=64, maximum=2048, step=8, label="Width", value=512, elem_id="txt2img_width")
height = gr.Slider(minimum=64, maximum=2048, step=8, label="Height", value=512, elem_id="txt2img_height")
res_switch_btn = ToolButton(value=switch_values_symbol, elem_id="txt2img_res_switch_btn")
if opts.dimensions_and_batch_together:
with gr.Column(elem_id="txt2img_column_batch"):
with FormRow(elem_id="txt2img_row_batch"):
batch_count = gr.Slider(minimum=1, step=1, label='Batch count', value=1, elem_id="txt2img_batch_count")
batch_size = gr.Slider(minimum=1, maximum=8, step=1, label='Batch size', value=1, elem_id="txt2img_batch_size")
batch_count = gr.Slider(minimum=1, step=1, label='Batch count', value=1, elem_id="txt2img_batch_count")
batch_size = gr.Slider(minimum=1, maximum=8, step=1, label='Batch size', value=1, elem_id="txt2img_batch_size")
elif category == "cfg":
cfg_scale = gr.Slider(minimum=1.0, maximum=30.0, step=0.5, label='CFG Scale', value=7.0, elem_id="txt2img_cfg_scale")
elif category == "seed":
seed, reuse_seed, subseed, reuse_subseed, subseed_strength, seed_resize_from_h, seed_resize_from_w, seed_checkbox = create_seed_inputs('txt2img')
elif category == "checkboxes":
with FormRow(elem_id="txt2img_checkboxes", variant="compact"):
cfg_scale = gr.Slider(minimum=1.0, maximum=30.0, step=0.5, label='CFG Scale', value=7.0, elem_id="txt2img_cfg_scale")
restore_faces = gr.Checkbox(label='Restore faces', value=False, visible=len(shared.face_restorers) > 1, elem_id="txt2img_restore_faces")
tiling = gr.Checkbox(label='Tiling', value=False, elem_id="txt2img_tiling")
enable_hr = gr.Checkbox(label='Hi-res tiling', value=False, elem_id="txt2img_enable_hr")
enable_hr = gr.Checkbox(label='Hires. fix', value=False, elem_id="txt2img_enable_hr")
hr_final_resolution = FormHTML(value="", elem_id="txtimg_hr_finalres", label="Upscaled resolution", interactive=False)
# elif category == "cfg":
# cfg_scale = gr.Slider(minimum=1.0, maximum=30.0, step=0.5, label='CFG Scale', value=7.0, elem_id="txt2img_cfg_scale")
elif category == "hires_fix":
with FormGroup(visible=False, elem_id="txt2img_hires_fix") as hr_options:
with FormRow(elem_id="txt2img_hires_fix_row1", variant="compact"):
@@ -749,7 +745,7 @@ def create_ui():
)
with FormRow():
resize_mode = gr.Radio(label="Resize mode", elem_id="resize_mode", choices=["Just resize", "Crop and resize", "Resize and fill", "Just resize"], type="index", value="Just resize")
resize_mode = gr.Radio(label="Resize mode", elem_id="resize_mode", choices=["Just resize", "Crop and resize", "Resize and fill", "Just resize (latent upscale)"], type="index", value="Just resize")
for category in ordered_ui_categories():
if category == "sampler":
@@ -758,16 +754,14 @@ def create_ui():
elif category == "dimensions":
with FormRow():
with gr.Column(elem_id="img2img_column_size", scale=4):
with FormRow(elem_id="img2img_row_size"):
width = gr.Slider(minimum=64, maximum=2048, step=8, label="Width", value=512, elem_id="img2img_width")
height = gr.Slider(minimum=64, maximum=2048, step=8, label="Height", value=512, elem_id="img2img_height")
width = gr.Slider(minimum=64, maximum=2048, step=8, label="Width", value=512, elem_id="img2img_width")
height = gr.Slider(minimum=64, maximum=2048, step=8, label="Height", value=512, elem_id="img2img_height")
res_switch_btn = ToolButton(value=switch_values_symbol, elem_id="img2img_res_switch_btn")
if opts.dimensions_and_batch_together:
with gr.Column(elem_id="img2img_column_batch"):
with FormRow(elem_id="img2img_row_batch"):
batch_count = gr.Slider(minimum=1, step=1, label='Batch count', value=1, elem_id="img2img_batch_count")
batch_size = gr.Slider(minimum=1, maximum=8, step=1, label='Batch size', value=1, elem_id="img2img_batch_size")
batch_count = gr.Slider(minimum=1, step=1, label='Batch count', value=1, elem_id="img2img_batch_count")
batch_size = gr.Slider(minimum=1, maximum=8, step=1, label='Batch size', value=1, elem_id="img2img_batch_size")
elif category == "cfg":
with FormGroup():
@@ -1012,6 +1006,48 @@ def create_ui():
}
return interp_descriptions[value]
with gr.Blocks(analytics_enabled=False) as modelmerger_interface:
with gr.Row().style(equal_height=False):
with gr.Column(variant='compact'):
interp_description = gr.HTML(value=update_interp_description("Weighted sum"), elem_id="modelmerger_interp_description")
with FormRow(elem_id="modelmerger_models"):
primary_model_name = gr.Dropdown(modules.sd_models.checkpoint_tiles(), elem_id="modelmerger_primary_model_name", label="Primary model (A)")
create_refresh_button(primary_model_name, modules.sd_models.list_models, lambda: {"choices": modules.sd_models.checkpoint_tiles()}, "refresh_checkpoint_A")
secondary_model_name = gr.Dropdown(modules.sd_models.checkpoint_tiles(), elem_id="modelmerger_secondary_model_name", label="Secondary model (B)")
create_refresh_button(secondary_model_name, modules.sd_models.list_models, lambda: {"choices": modules.sd_models.checkpoint_tiles()}, "refresh_checkpoint_B")
tertiary_model_name = gr.Dropdown(modules.sd_models.checkpoint_tiles(), elem_id="modelmerger_tertiary_model_name", label="Tertiary model (C)")
create_refresh_button(tertiary_model_name, modules.sd_models.list_models, lambda: {"choices": modules.sd_models.checkpoint_tiles()}, "refresh_checkpoint_C")
custom_name = gr.Textbox(label="Custom Name (Optional)", elem_id="modelmerger_custom_name")
interp_amount = gr.Slider(minimum=0.0, maximum=1.0, step=0.05, label='Multiplier (M) - set to 0 to get model A', value=0.3, elem_id="modelmerger_interp_amount")
interp_method = gr.Radio(choices=["No interpolation", "Weighted sum", "Add difference"], value="Weighted sum", label="Interpolation Method", elem_id="modelmerger_interp_method")
interp_method.change(fn=update_interp_description, inputs=[interp_method], outputs=[interp_description])
with FormRow():
checkpoint_format = gr.Radio(choices=["ckpt", "safetensors"], value="ckpt", label="Checkpoint format", elem_id="modelmerger_checkpoint_format")
save_as_half = gr.Checkbox(value=False, label="Save as float16", elem_id="modelmerger_save_as_half")
with FormRow():
with gr.Column():
config_source = gr.Radio(choices=["A, B or C", "B", "C", "Don't"], value="A, B or C", label="Copy config from", type="index", elem_id="modelmerger_config_method")
with gr.Column():
with FormRow():
bake_in_vae = gr.Dropdown(choices=["None"] + list(sd_vae.vae_dict), value="None", label="Bake in VAE", elem_id="modelmerger_bake_in_vae")
create_refresh_button(bake_in_vae, sd_vae.refresh_vae_list, lambda: {"choices": ["None"] + list(sd_vae.vae_dict)}, "modelmerger_refresh_bake_in_vae")
with FormRow():
discard_weights = gr.Textbox(value="", label="Discard weights with matching name", elem_id="modelmerger_discard_weights")
with gr.Row():
modelmerger_merge = gr.Button(elem_id="modelmerger_merge", value="Merge", variant='primary')
with gr.Column(variant='compact', elem_id="modelmerger_results_container"):
with gr.Group(elem_id="modelmerger_results_panel"):
modelmerger_result = gr.HTML(elem_id="modelmerger_result", show_label=False)
with gr.Blocks(analytics_enabled=False) as train_interface:
with gr.Row().style(equal_height=False):
@@ -1020,49 +1056,6 @@ def create_ui():
with gr.Row(variant="compact").style(equal_height=False):
with gr.Tabs(elem_id="train_tabs"):
with gr.Tab(label="Merge models") as modelmerger_interface:
with gr.Row().style(equal_height=False):
with gr.Column(variant='compact'):
interp_description = gr.HTML(value=update_interp_description("Weighted sum"), elem_id="modelmerger_interp_description")
with FormRow(elem_id="modelmerger_models"):
primary_model_name = gr.Dropdown(modules.sd_models.checkpoint_tiles(), elem_id="modelmerger_primary_model_name", label="Primary model (A)")
create_refresh_button(primary_model_name, modules.sd_models.list_models, lambda: {"choices": modules.sd_models.checkpoint_tiles()}, "refresh_checkpoint_A")
secondary_model_name = gr.Dropdown(modules.sd_models.checkpoint_tiles(), elem_id="modelmerger_secondary_model_name", label="Secondary model (B)")
create_refresh_button(secondary_model_name, modules.sd_models.list_models, lambda: {"choices": modules.sd_models.checkpoint_tiles()}, "refresh_checkpoint_B")
tertiary_model_name = gr.Dropdown(modules.sd_models.checkpoint_tiles(), elem_id="modelmerger_tertiary_model_name", label="Tertiary model (C)")
create_refresh_button(tertiary_model_name, modules.sd_models.list_models, lambda: {"choices": modules.sd_models.checkpoint_tiles()}, "refresh_checkpoint_C")
custom_name = gr.Textbox(label="Custom Name (Optional)", elem_id="modelmerger_custom_name")
interp_amount = gr.Slider(minimum=0.0, maximum=1.0, step=0.05, label='Multiplier (M) - set to 0 to get model A', value=0.3, elem_id="modelmerger_interp_amount")
interp_method = gr.Radio(choices=["No interpolation", "Weighted sum", "Add difference"], value="Weighted sum", label="Interpolation Method", elem_id="modelmerger_interp_method")
interp_method.change(fn=update_interp_description, inputs=[interp_method], outputs=[interp_description])
with FormRow():
checkpoint_format = gr.Radio(choices=["ckpt", "safetensors"], value="ckpt", label="Checkpoint format", elem_id="modelmerger_checkpoint_format")
save_as_half = gr.Checkbox(value=False, label="Save as float16", elem_id="modelmerger_save_as_half")
with FormRow():
with gr.Column():
config_source = gr.Radio(choices=["A, B or C", "B", "C", "Don't"], value="A, B or C", label="Copy config from", type="index", elem_id="modelmerger_config_method")
with gr.Column():
with FormRow():
bake_in_vae = gr.Dropdown(choices=["None"] + list(sd_vae.vae_dict), value="None", label="Bake in VAE", elem_id="modelmerger_bake_in_vae")
create_refresh_button(bake_in_vae, sd_vae.refresh_vae_list, lambda: {"choices": ["None"] + list(sd_vae.vae_dict)}, "modelmerger_refresh_bake_in_vae")
with FormRow():
discard_weights = gr.Textbox(value="", label="Discard weights with matching name", elem_id="modelmerger_discard_weights")
with gr.Row():
modelmerger_merge = gr.Button(elem_id="modelmerger_merge", value="Merge", variant='primary')
with gr.Column(variant='compact', elem_id="modelmerger_results_container"):
with gr.Group(elem_id="modelmerger_results_panel"):
modelmerger_result = gr.HTML(elem_id="modelmerger_result", show_label=False)
with gr.Tab(label="Create embedding"):
new_embedding_name = gr.Textbox(label="Name", elem_id="train_new_embedding_name")
initialization_text = gr.Textbox(label="Initialization text", value="*", elem_id="train_initialization_text")
@@ -1536,11 +1529,11 @@ def create_ui():
)
interfaces = [
(txt2img_interface, "From Text", "txt2img"),
(img2img_interface, "From Image", "img2img"),
(extras_interface, "Process", "extras"),
(pnginfo_interface, "Image Info", "pnginfo"),
# (modelmerger_interface, "Checkpoint Merger", "modelmerger"),
(txt2img_interface, "txt2img", "txt2img"),
(img2img_interface, "img2img", "img2img"),
(extras_interface, "Extras", "extras"),
(pnginfo_interface, "PNG Info", "pnginfo"),
(modelmerger_interface, "Checkpoint Merger", "modelmerger"),
(train_interface, "Train", "ti"),
]
@@ -1566,10 +1559,6 @@ def create_ui():
extensions_interface = ui_extensions.create_ui()
interfaces += [(extensions_interface, "Extensions", "extensions")]
shared.tab_names = []
for _interface, label, _ifid in interfaces:
shared.tab_names.append(label)
with gr.Blocks(css=css, analytics_enabled=False, title="Stable Diffusion") as demo:
with gr.Row(elem_id="quicksettings", variant="compact"):
for i, k, item in sorted(quicksettings_list, key=lambda x: quicksettings_names.get(x[1], x[0])):
@@ -1580,8 +1569,6 @@ def create_ui():
with gr.Tabs(elem_id="tabs") as tabs:
for interface, label, ifid in interfaces:
if label in shared.opts.hidden_tabs:
continue
with gr.TabItem(label, id=ifid, elem_id='tab_' + ifid):
interface.render()
@@ -1792,15 +1779,10 @@ def versions_html():
else:
xformers_version = "N/A"
try:
torch_version = torch.__long_version__
except:
torch_version = torch.__version__
return f"""
python: <span title="{sys.version}">{python_version}</span>
 • 
torch: {torch_version}
torch: {torch.__version__}
 • 
xformers: {xformers_version}
 • 
requirements_versions.txt
+21 -20
View File
@@ -1,28 +1,29 @@
accelerate==0.16.0
basicsr==1.4.2
blendmodes==2022
clean-fid==0.1.35
diffusers==0.12.1
einops==0.4.1
fastapi==0.90.1
transformers==4.25.1
accelerate==0.12.0
basicsr==1.4.2
gfpgan==1.3.8
GitPython==3.1.27
gradio==3.16.2
inflection==0.5.1
jsonmerge==1.9.0
kornia==0.6.9
lark==1.1.5
numpy==1.23.5
omegaconf==2.3.0
piexif==1.1.3
numpy==1.23.3
Pillow==9.4.0
protobuf==3.20.3
pytorch_lightning==1.7.7
realesrgan==0.3.0
torch
omegaconf==2.2.3
pytorch_lightning==1.7.6
scikit-image==0.19.2
fonts
font-roboto
timm==0.6.7
piexif==1.1.3
einops==0.4.1
jsonmerge==1.8.0
clean-fid==0.1.29
resize-right==0.0.2
safetensors==0.2.8
scikit-image==0.19.3
timm==0.6.12
torchdiffeq==0.2.3
kornia==0.6.7
lark==1.1.2
inflection==0.5.1
GitPython==3.1.27
torchsde==0.2.5
transformers==4.26.1
safetensors==0.2.7
httpcore<=0.15