CLIP Vision encoder
CLIP-ViT- H- 14- laion2B- s32B- b79K. safetensors
CLIP ViT H 14 Laion2B S32B B79K · CLIP Vision encoder for ComfyUI
- File
CLIP-ViT-H-14-laion2B-s32B-b79K.safetensors- Type
- CLIP Vision encoder
- Size
- 2.53 GB
- Folder
ComfyUI/models/clip_vision/- Source
- Comfy-Org/CLIP-ViT-H-14-laion2B-s32B-b79K_repackaged
- SHA-256
6ca9667da1ca…
2 workflows use this file
What is CLIP ViT H 14 Laion2B S32B B79K?
CLIP ViT H 14 Laion2B S32B B79K 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 ViT H 14 Laion2B S32B B79K with other models and custom nodes to build any pipeline you need. There are 2 official ComfyUI workflow templates that use CLIP ViT H 14 Laion2B S32B B79K, ready to load and customize.
Workflows for this file
Frequently Asked Questions
CLIP ViT H 14 Laion2B S32B B79K 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 ViT H 14 Laion2B S32B B79K with other models and custom nodes to build any pipeline you need. There are 2 official ComfyUI workflow templates that use CLIP ViT H 14 Laion2B S32B B79K, ready to load and customize.
Open ComfyUI and browse any of the 2 official ComfyUI workflow templates that use CLIP ViT H 14 Laion2B S32B B79K. Load one as a starting point, then customize the nodes and parameters to fit your use case.
There are 2 official ComfyUI workflow templates that use CLIP ViT H 14 Laion2B S32B B79K. Each template is ready to run in ComfyUI and can be customized to suit your project.
ComfyUI is free and open source. CLIP ViT H 14 Laion2B S32B B79K 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.