From 6b44c101dbfe742fd912456c200ad1bfa4a88473 Mon Sep 17 00:00:00 2001 From: Manuel Schmid Date: Mon, 18 Mar 2024 12:30:39 +0100 Subject: [PATCH] feat: update changelog and readme --- readme.md | 10 +++++++--- update_log.md | 11 +++++++++++ 2 files changed, 18 insertions(+), 3 deletions(-) diff --git a/readme.md b/readme.md index 4e47ac08..6ec24eed 100644 --- a/readme.md +++ b/readme.md @@ -84,6 +84,10 @@ The first time you launch the software, it will automatically download models: After Fooocus 2.1.60, you will also have `run_anime.bat` and `run_realistic.bat`. They are different model presets (and require different models, but they will be automatically downloaded). [Check here for more details](https://github.com/lllyasviel/Fooocus/discussions/679). +After Fooocus 2.3.0 you can also switch presets directly in the browser. Keep in mind to add these arguments if you want to change the default behavior: +* Use `--disable-preset-selection` to disable preset selection in the browser. +* Use `--always-download-new-model` to download missing models on preset switch. Default is fallback to `previous_default_models` defined in the corresponding preset, also see terminal output. + ![image](https://github.com/lllyasviel/Fooocus/assets/19834515/d386f817-4bd7-490c-ad89-c1e228c23447) If you already have these files, you can copy them to the above locations to speed up installation. @@ -115,7 +119,7 @@ See also the common problems and troubleshoots [here](troubleshoot.md). ### Colab -(Last tested - 2024 Mar 11) +(Last tested - 2024 Mar 18 - @mashb1t) | Colab | Info | --- | --- | @@ -125,9 +129,9 @@ In Colab, you can modify the last line to `!python entry_with_update.py --share Note that this Colab will disable refiner by default because Colab free's resources are relatively limited (and some "big" features like image prompt may cause free-tier Colab to disconnect). We make sure that basic text-to-image is always working on free-tier Colab. -Using `--always-high-vram` shifts resource allocation from RAM to VRAM and achieves the overall best balance between performance, flexibility and stability on the default T4 instance. +Using `--always-high-vram` shifts resource allocation from RAM to VRAM and achieves the overall best balance between performance, flexibility and stability on the default T4 instance. Please find more information [here](https://github.com/lllyasviel/Fooocus/pull/1710#issuecomment-1989185346). -Thanks to [camenduru](https://github.com/camenduru)! +Thanks to [camenduru](https://github.com/camenduru) for the template! ### Linux (Using Anaconda) diff --git a/update_log.md b/update_log.md index 322c19c1..4e22db0a 100644 --- a/update_log.md +++ b/update_log.md @@ -1,3 +1,14 @@ +# [2.3.0](https://github.com/lllyasviel/Fooocus/releases/tag/2.3.0) + +* Add performance "lightning" (based on [SDXL-Lightning 4 step LoRA](https://huggingface.co/ByteDance/SDXL-Lightning/blob/main/sdxl_lightning_4step_lora.safetensors)) +* Add preset selection to UI, disable with argument `--disable-preset-selection`. Use `--always-download-new-model` to download missing models on preset switch. +* Improve face swap consistency by switching later in the process to (synthetic) refiner +* Add temp path cleanup on startup +* Add support for wildcard subdirectories +* Add scrollable 2 column layout for styles for better structure +* Improve Colab resource needs for T4 instances (default), positively tested with all image prompt features +* Improve anime preset, now uses style `Fooocus Semi Realistic` instead of `Fooocus Negative` (less wet look images) + # [2.2.1](https://github.com/lllyasviel/Fooocus/releases/tag/2.2.1) * Fix some small bugs (e.g. image grid, upscale fast 2x, LoRA weight width in Firefox)