Run this workflow on InstaSD
Get started in minutes! Run this ComfyUI workflow online - no setup required.
Description
Optimized WAN 2.1 Image-to-Video (I2V) 720P workflow using SageAttention and TeaCache for significantly improved speed and efficiency.
🔬 Benchmark Results (RTX 4090 | 33 Frames | 16 FPS | 20 Steps)
- ⏱️ Base: 542.09s
- ⚡ Optimized (SageAttention + TeaCache): 248s
- 🔥 54% Speed Boost!
✨ Key Features
✅ Drastically Faster Inference – Cut generation time in half!
✅ SageAttention Optimization – More efficient attention mechanisms
✅ TeaCache Acceleration – Reduces redundant computations
Models
| File | Destination | Source |
|---|---|---|
| wan_2.1_vae.safetensors | /ComfyUI/models/vae | Download |
| clip_vision_h.safetensors | /ComfyUI/models/clip_vision | Download |
| umt5_xxl_fp8_e4m3fn_scaled.safetensors | /ComfyUI/models/text_encoders | Download |
| wan2.1_i2v_720p_14B_bf16.safetensors | /ComfyUI/models/diffusion_models | Download |
| wanCumshot.safetensors | /ComfyUI/models/loras/wan | Download |
| i2vTittydropE26.MNmi.safetensors | /ComfyUI/models/loras/wan | Download |
| H617AT6E5H2RWZMQ1R63F9BEG02.jpg | /ComfyUI/input | Download |
Nodes
WanVideoTeaCacheKJVAEDecodeTiledNoteUNETLoaderPathchSageAttentionKJCLIPLoaderVAELoaderCLIPVisionLoaderCLIPVisionEncodeVHS_VideoCombineKSamplerLoraLoaderWanImageToVideoLoadImageCLIPTextEncode