diff --git a/CHANGELOG.md b/CHANGELOG.md index 85ee74860..2f1e330cc 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -16,7 +16,7 @@ - Support for [Stable Fast](https://github.com/chengzeyi/stable-fast) model compile on *Windows/Linux/WSL2* with *CUDA* See [Wiki:Benchmark](https://github.com/vladmandic/automatic/wiki/Benchmark) for details and comparisment of different backends, precision modes, advanced settings and compile modes - *Hint*: **100+ it/s** is possible on *RTX4090* with no special tweaks + *Hint*: **70+ it/s** is possible on *RTX4090* with no special tweaks - Add additional pipeline types for manual model loads when loading from `safetensors` - Updated logic for calculating **steps** when using base/hires/refiner workflows - Safe model offloading for non-standard models @@ -44,6 +44,7 @@ - Better Lora trigger words support - Auto refresh styles on change - **General** + - Many **mobile UI** optimizations, thanks @iDeNoh - Support for **Torch 2.1.1** with CUDA 12.1 or CUDA 11.8 - Configurable location for HF cache folder Default is standard `~/.cache/huggingface/hub` diff --git a/README.md b/README.md index 72f8032e4..ac2085039 100644 --- a/README.md +++ b/README.md @@ -48,10 +48,10 @@ All individual features are not listed here, instead check [ChangeLog](CHANGELOG - **Original**: Based on [LDM](https://github.com/Stability-AI/stablediffusion) reference implementation and significantly expanded on by [A1111](https://github.com/AUTOMATIC1111/stable-diffusion-webui) This is the default backend and it is fully compatible with all existing functionality and extensions - It supports **SD 1.x** and **SD 2.x** models + Supports **SD 1.x** and **SD 2.x** models All other model types such as *SD-XL, LCM, PixArt, Segmind, Kandinsky, etc.* require backend **Diffusers** - **Diffusers**: Based on new [Huggingface Diffusers](https://huggingface.co/docs/diffusers/index) implementation - It supports *original* SD models as well as *all* models listed below + Supports *original* SD models as well as *all* models listed below See [wiki article](https://github.com/vladmandic/automatic/wiki/Diffusers) for more information ## Model support @@ -164,9 +164,9 @@ SD.Next comes with several extensions pre-installed: ### **Collab** -- To avoid having this repo rely just on me, I'd love to have additional maintainers with full admin rights. If you're interested, ping me! +- We'd love to have additional maintainers with full admin rights. If you're interested, ping us! - In addition to general cross-platform code, desire is to have a lead for each of the main platforms. -This should be fully cross-platform, but I would really love to have additional contributors and/or maintainers to join and help lead the efforts on different platforms. +This should be fully cross-platform, but we'd really love to have additional contributors and/or maintainers to join and help lead the efforts on different platforms. ### **Goals** diff --git a/cli/process.py b/cli/process.py index d03e6cb16..3bcd97ed9 100644 --- a/cli/process.py +++ b/cli/process.py @@ -182,7 +182,7 @@ def interrogate_image(res: Result, tag: str = None): def resize_image(res: Result): resized = res.image - resized.thumbnail((options.process.target_size, options.process.target_size), Image.HAMMING) + resized.thumbnail((options.process.target_size, options.process.target_size), Image.Resampling.HAMMING) res.image = resized res.ops.append('resize') return res diff --git a/cli/requirements.txt b/cli/requirements.txt index 9452617f0..a63adae95 100644 --- a/cli/requirements.txt +++ b/cli/requirements.txt @@ -2,5 +2,3 @@ mediapipe colormap filetype albumentations -accelerate==0.19.0 -diffusers==0.10.2 diff --git a/extensions-builtin/sd-webui-controlnet b/extensions-builtin/sd-webui-controlnet index aa4747ab5..10bd9b25f 160000 --- a/extensions-builtin/sd-webui-controlnet +++ b/extensions-builtin/sd-webui-controlnet @@ -1 +1 @@ -Subproject commit aa4747ab5f949b5d7aa1ccae238571ddca6ef33f +Subproject commit 10bd9b25f62deab9acb256301bbf3363c42645e7