From 233c381f4b47795d265d177c1baa32a421cf4638 Mon Sep 17 00:00:00 2001 From: DeepBeepMeep Date: Fri, 6 Jun 2025 00:53:39 +0200 Subject: [PATCH] AccVideo support --- README.md | 10 +++++++--- docs/CHANGELOG.md | 3 +++ docs/LORAS.md | 29 ++++++++++++++++++++++++++++- requirements.txt | 2 +- 4 files changed, 39 insertions(+), 5 deletions(-) diff --git a/README.md b/README.md index bd9a1aa..40d7c60 100644 --- a/README.md +++ b/README.md @@ -18,12 +18,16 @@ WanGP supports the Wan (and derived models), Hunyuan Video and LTV Video models **Discord Server to get Help from Other Users and show your Best Videos:** https://discord.gg/g7efUW9jGV ## 🔥 Latest Updates +### May 28 2025: WanGP v5.41 +👋 Bonus release: Support for **AccVideo** Lora to speed up x2 Video generations in Wan models. Check the Loras documentation to get the usage instructions of AccVideo.\ +You will need to do a *pip install -r requirements.txt* + ### May 28 2025: WanGP v5.4 -👋 World Exclusive : Hunyuan Video Avatar Support ! You won't need 80 GB of VRAM nor 32 GB oF VRAM, just 10 GB of VRAM will be sufficient to generate up to 15s of high quality speech / song driven Video at a high speed with no quality degradation. Support for TeaCache included.\ +👋 World Exclusive : **Hunyuan Video Avatar** Support ! You won't need 80 GB of VRAM nor 32 GB oF VRAM, just 10 GB of VRAM will be sufficient to generate up to 15s of high quality speech / song driven Video at a high speed with no quality degradation. Support for TeaCache included.\ Also many thanks to Reevoy24 for his repackaging / completing the documentation ### May 28 2025: WanGP v5.31 -👋 Added Phantom 14B, a model that you can use to transfer objects / people in the video. My preference goes to Vace that remains the king of controlnets. +👋 Added **Phantom 14B**, a model that you can use to transfer objects / people in the video. My preference goes to Vace that remains the king of controlnets. VACE improvements: Better sliding window transitions, image mask support in Matanyone, new Extend Video feature, and enhanced background removal options. ### May 26, 2025: WanGP v5.3 @@ -33,7 +37,7 @@ VACE improvements: Better sliding window transitions, image mask support in Mata - Export/import settings as JSON files for easy sharing and backup ### May 20, 2025: WanGP v5.2 -👋 **CausVid support** - Generate videos in just 4-12 steps with the new distilled Wan model! Also added experimental MoviiGen for 1080p generation (20GB+ VRAM required). +👋 **CausVid support** - Generate videos in just 4-12 steps with the new distilled Wan model! Also added experimental MoviiGen for 1080p generation (20GB+ VRAM required). Check the Loras documentation to get the usage instructions of CausVid. ### May 18, 2025: WanGP v5.1 👋 **LTX Video 13B Distilled** - Generate high-quality videos in less than one minute! diff --git a/docs/CHANGELOG.md b/docs/CHANGELOG.md index 08a4bae..c2f1488 100644 --- a/docs/CHANGELOG.md +++ b/docs/CHANGELOG.md @@ -1,6 +1,9 @@ # Changelog ## 🔥 Latest News +### May 28 2025: WanGP v5.41 +👋 Bonus release: Support for **AccVideo** Lora to speed up x2 Video generations in Wan models. Check the Loras documentation to get the usage instructions of AccVideo. + ### May 28 2025: WanGP v5.4 👋 World Exclusive : Hunyuan Video Avatar Support ! You won't need 80 GB of VRAM nor 32 GB oF VRAM, just 10 GB of VRAM will be sufficient to generate up to 15s of high quality speech / song driven Video at a high speed with no quality degradation. Support for TeaCache included. diff --git a/docs/LORAS.md b/docs/LORAS.md index 8ea9774..e4d4a32 100644 --- a/docs/LORAS.md +++ b/docs/LORAS.md @@ -88,7 +88,7 @@ python wgp.py --lora-preset mypreset.lset - Presets include comments with usage instructions - Share `.lset` files with other users -## CausVid Lora (Special) +## CausVid Lora (Video Generation Accelerator) CausVid is a distilled Wan model that generates videos in 4-12 steps with 2x speed improvement. @@ -125,6 +125,33 @@ WanGP supports multiple lora formats: - **Replicate** format - **Standard PyTorch** (.pt, .pth) +## AccVid Lora (Video Generation Accelerator) + +AccVid is a distilled Wan model that generates videos with a 2x speed improvement since classifier free guidance is no longer needed (that is cfg = 1). + +### Setup Instructions +1. Download the CausVid Lora: + +- for t2v models: + ``` + https://huggingface.co/Kijai/WanVideo_comfy/blob/main/Wan21_AccVid_T2V_14B_lora_rank32_fp16.safetensors + ``` + +- for i2v models: + ``` + https://huggingface.co/Kijai/WanVideo_comfy/blob/main/Wan21_AccVid_I2V_480P_14B_lora_rank32_fp16.safetensors + ``` + +2. Place in your `loras/` directory or `loras_i2v/` directory + +### Usage +1. Select a Wan t2v model (e.g., Wan 2.1 text2video 13B or Vace 13B) or Wan i2v model +2. Enable Advanced Mode +3. In Advanced Generation Tab: + - Set Guidance Scale = 1 + - Set Shift Scale = 5 +4. The number steps remain unchanged compared to what you would use with the original model but it will be two times faster since classifier free guidance is not needed + ## Performance Tips ### Fast Loading/Unloading diff --git a/requirements.txt b/requirements.txt index 526b347..8324d48 100644 --- a/requirements.txt +++ b/requirements.txt @@ -17,7 +17,7 @@ gradio==5.23.0 numpy>=1.23.5,<2 einops moviepy==1.0.3 -mmgp==3.4.7 +mmgp==3.4.8 peft==0.14.0 mutagen pydantic==2.10.6