(NEW) One-Click Triton & SageAttention installation guide: https://civitai.com/articles/12248

Tested LoRAs:

• https://civitai.com/models/1335738?modelVersionId=1514116

• https://civitai.com/models/1340141/squish-effect-wan21-i2v-lora?modelVersionId=1513385

• https://civitai.com/models/1269557?modelVersionId=1470330

Recommended Version

• ComfyUI v0.3.19 or higher

  Wan does not work on versions below that.

• ComfyUI-Manager v3.26 or higher

  There is an issue with missing nodes and conflict in previous versions

Lite v1 Released

In this version, we have significantly reduced the number of custom nodes and designed the GUI to configure only the settings you need. This has resulted in improved compatibility, fewer errors, and much more user-friendly. We have also revised the resolution adjustment mechanism to make it much easier to change. The method of improving speed by double sampling has been removed. This is because there is no significant difference between applying TeaCache and not. In fact, double sampling actually reduces quality.

Require Nodes (Lite v1 only)

• ComfyUI-Easy-Use

• ComfyUI-Florence2

• ComfyUI-VideoHelperSuite

• ComfyUI-Frame-Interpolation

V2.2 UPDATED

This update was tested with 8GB VRAM, removes the confusion between i2v and t2v, adds convenient resolution settings (thanks @redhome) and several other handy features. It also fixes a critical bug in shift order and adds perfectly support for WAN Lora.

Require Nodes (Works on Install Missing Nodes)

• ComfyUI-KJNodes (if use TeaCache need to update "1.0.7 nightly" version. Switch Version -> nightly. If you don't see the nightly, Click to [Try update]. it doesn't work 1.0.6 or 1.0.7 latest.)

• ComfyUI-GGUF (If you have other gguf custom nodes, remove them)

• ComfyUI-GIMM-VFI (need to installed cuda toolkit 12.x)

• ComfyUI-Easy-Use

• rgthree-comfy

• ComfyUI-Florence2

• ComfyUI-Impact-Pack

• ComfyUI-Custom-Scripts

• ComfyUI-VideoHelperSuite

• ComfyUI-Frame-Interpolation

• ComfyUI-HunyuanVideoMultiLora

v2 Update Notes

• Applied TeaCache

• Added Florence2 auto-captioning

• Added GIMM VFI

• Added LoRA Loader

• Introduced shift parameter

• Optimized workflow

Require Models

T2V (Q4) Model

🔗 Download
📂 Save to: models/diffusion_models

T2V Fastest(1.3B) Model

🔗 Download
📂 Save to: models/diffusion_models

I2V (Q4) Model

🔗 Download
📂 Save to: models/diffusion_models

CLIP DO NOT USE ANOTHER

🔗 Download
📂 Save to: models/clip

CLIP-VISION

🔗 Download
📂 Save to: models/clip_vision

VAE DO NOT USE ANOTHER

🔗 Download
📂 Save to: models/vae

UPSCALE MODEL

🛠 Recommended Model: 4x_foolhardy_Remacri
download via ComfyUI Model Manager