CLIP Vision encoder
clip_vision_ h. safetensors
Clip Vision H · CLIP Vision encoder for ComfyUI
- File
clip_vision_h.safetensors- Type
- CLIP Vision encoder
- Size
- 1.26 GB
- Folder
ComfyUI/models/clip_vision/- Source
- Comfy-Org/Wan-2.1
- SHA-256
64a7ef761bfc…
22 workflows use this file
What is Clip Vision H?
Clip Vision H is a CLIP Vision encoder that converts images into embeddings for conditioning or style transfer. You can run it locally in ComfyUI with full control over every parameter, or access it through Comfy Cloud. ComfyUI's node-based workflow editor lets you connect Clip Vision H with other models and custom nodes to build any pipeline you need. There are 22 official ComfyUI workflow templates that use Clip Vision H, ready to load and customize.
Read the full tutorial →Workflows for this file
- Wan2.1, ChronoEdit, Nvidia
ChronoEdit 14B
Uses this file - Wan, wan2.2 Animate
Wan2.2 Animate, Character Animation and Replacement
Uses this file - Wan2.1, Wan
Wan 2.1 Image to Video
Uses this file - Wan2.1, Wan
Wan 2.1 Fun Camera 14B
Uses this file - Wan2.1, Wan
Wan 2.1 ControlNet
Uses this file - Wan2.1, Wan
WanMove: Daydream Illusion
Uses this file - Wan2.1, Wan
Wan 2.1 Fun Camera 1.3B
Uses this file - Wan2.1, Wan
Wan2.1 ATI
Uses this file
Frequently Asked Questions
Clip Vision H is a CLIP Vision encoder that converts images into embeddings for conditioning or style transfer. You can run it locally in ComfyUI with full control over every parameter, or access it through Comfy Cloud. ComfyUI's node-based workflow editor lets you connect Clip Vision H with other models and custom nodes to build any pipeline you need. There are 22 official ComfyUI workflow templates that use Clip Vision H, ready to load and customize.
Follow the step-by-step tutorial at https://docs.comfy.org/tutorials/video/wan/wan2-2-animate. You can also load any of the 22 official ComfyUI workflow templates that use Clip Vision H directly in ComfyUI.
There are 22 official ComfyUI workflow templates that use Clip Vision H. Each template is ready to run in ComfyUI and can be customized to suit your project.
ComfyUI is free and open source. Clip Vision H weights are available to download from Hugging Face. You only pay for compute when running on Comfy Cloud; local inference on your own hardware is always free.