Wan 2.1 T2V 1.3B SelfForcing VACE

--- license: cc-by-nc-sa-4.0 --- # gdhe17/Self-Forcing & Wan-AI/Wan2.1-VACE-1.3B Scopes Addon Experiment --- > [!IMPORTANT] > ⚠️ **Notice:** > This project is intended for experimental use only. > > CausVid/Self-Forcing is not natively supported in ComfyUI, proper sampling is not implemented. --- This is an addon experiment of [gdhe17/Self-Forcing](https://huggingface.co/gdhe17/Self-Forcing) and [Wan-AI/Wan2.1-VACE-1.3B](https://huggingface.co/Wan-AI/Wan2.1-VACE-1.3B) scopes. The process involved extracting VACE scopes and injecting into the target models, using scripts provided by [wsbagnsv1](https://huggingface.co/wsbagnsv1). The FP16 model weights were then quantized to specific FP8 formats (E4M3FN and E5M2) using ComfyUI custom node [ComfyUI-ModelQuantizer](https://github.com/lum3on/ComfyUI-ModelQuantizer) by [lum3on](https://github.com/lum3on). LoRA extraction was done by subtracting and saving the weight differences using the ModelMergeSubtract node and the Extract and Save LoRA node in ComfyUI. ## Usage The model files can be used in [ComfyUI](https://github.com/comfyanonymous/ComfyUI/) with the WanVaceToVideo node. Place the required model(s) in the following folders: | Type | Name | Location | Download | | ------------ | ----------------------------------- | --------------------------------- | ----------------------- | | Main Model | Wan2.1_T2V_1.3B_SelfForcing_VACE | `ComfyUI/models/diffusion_models` | Safetensors (this repo) | | Text Encoder | umt5-xxl-encoder | `ComfyUI/models/text_encoders` | [Safetensors](https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/tree/main/split_files/text_encoders) / [GGUF](https://huggingface.co/city96/umt5-xxl-encoder-gguf/tree/main) | | VAE | Wan2_1_VAE_bf16 | `ComfyUI/models/vae` | [Safetensors](https://huggingface.co/Kijai/WanVideo_comfy/blob/main/Wan2_1_VAE_bf16.safetensors) | [**ComfyUI example workflow**](https://docs.comfy.org/tutorials/video/wan/vace) ### Notes *All original licenses and restrictions from the base models still apply.* ## Reference - For an overview of Safetensors format, please see the [Safetensors format](https://huggingface.co/docs/safetensors/index#format).