Wan 2.2 TI2V FP8
This repository contains the converted Wan2.2-TI2V model, adapted for ComfyUI usage.
Fuente del modelo
- Tipo
- Text model
- Tamaño del archivo
- 10,6 GB
- Modelo base
- Wan 2.2
- Versión
- vBF16
- Actualizado
- 2 oct 2026
- Descargas
- 0
- Tareas
- Imagen a vídeo
- Fuente
- Hugging Face
Descripción de la fuente
Wan2.2-TI2V for ComfyUI
This repository contains the converted Wan2.2-TI2V model, adapted for ComfyUI usage.
✅ Model Components
| Module | Format | File |
|---|---|---|
| Transformer | FP8 + scale | wan2.2_ti2v_transformer_fp8_scaled.safetensors |
| VAE | FP16 | wan2.2_ti2v_vae_fp16.safetensors |
| Text Encoder | BF16 (shared) | wan2.2_ti2v_text_encoder_bf16.safetensors |
📦 How to Use in ComfyUI
Place the files in your ComfyUI model paths:
- Transformer →
models/diffusers/ - VAE →
models/vae/ - Text Encoder →
models/clip/(or appropriate location)
🛠️ Notes
- FP8 conversion used Tencent HunyuanVideo's
fp8_optimization.py - Safe export with
safetensors - Includes special handling of shared tensors (
shared.weight)
🔗 Credits
- Original model: Wan2.2-TI2V
- FP8 optimization: Tencent Hunyuan
Fuentes
1 fuente
Fuentes
1 fuenteVerificado 2 oct
Artefactos del modelo
1 artefacto
Artefactos del modelo
1 artefactowan2.2_ti2v_text_encoder_bf16.safetensors
safetensors · BF16 · 10,6 GB · SHA-256 d49b2a092ef1…cc1a · Hugging Face
DescargarExtractos de fuentes
2 extractos
Extractos de fuentes
2 extractos# Wan2.2-TI2V for ComfyUI This repository contains the converted [Wan2.2-TI2V](https://huggingface.co/Wan-AI/Wan2.2-TI2V-5B-Diffusers) model, adapted for **ComfyUI** usage. ## ✅ Model Components | Module | Format | File | |----------------|----------------|------| | Transformer | FP8 + scale | `wan2.2_ti2v_transformer_fp8_scaled.safetensors` | | VAE | FP16 | `wan2.2_ti2v_vae_fp16.safetensors` | | Text Encoder | BF16 (shared) | `wan2.2_ti2v_text_encoder_bf16.safetensors` | ## 📦 How to Use in ComfyUI Place the files in your ComfyUI model paths: - **Transformer** → `models/diffusers/` - **VAE** → `models/vae/` - **Text Encoder** → `models/clip/` (or appropriate location) ## 🛠️ Notes - FP8 conversion used Tencent HunyuanVideo's `fp8_optimization.py` - Safe export with `safetensors` - Includes special handling of shared tensors (`shared.weight`) ## 🔗 Credits - Original model: [Wan2.2-TI2V](https://huggingface.co/Wan-AI/Wan2.2-TI2V-5B-Diffusers) - FP8 optimization: [Tencent Hunyuan](https://github.com/Tencent-Hunyuan/HunyuanVideo)
Source context: 0 downloads · 2 likes · Repo Goldlionren00/Wan2.2-TI2V-FP8-ComfyUI
