ComfyUI Jina Clip v2
Single file version of Jina CLIP v2, used by NewBie-Image. It can be directly loaded in ComfyUI using the Dual CLIP Loader node with type newbie.
Model source
- Kind
- Other
- File size
- 1.04 GB
- Version
- vRevision e864905
- Updated
- Oct 6, 2026
- Downloads
- 0
- Source
- Hugging Face
Source description
Single file version of Jina CLIP v2, used by NewBie-Image. It can be directly loaded in ComfyUI using the Dual CLIP Loader node with type newbie.
Only the text encoder is included here. I'm leaving the vision encoder for future work. There is a lora in the official implementation and I've merged it into the base weights.
The tokenizer is included as the tensor spiece_model.
Sources
1 source
Sources
1 sourceVerified Sep 1
Model artifacts
1 artifact
Model artifacts
1 artifactjina_clip_v2_bf16.safetensors
safetensors · 1.04 GB · SHA-256 149c302aecd9…0d73 · Hugging Face
Download fileSource excerpts
2 excerpts
Source excerpts
2 excerptsSingle file version of [Jina CLIP v2](https://huggingface.co/jinaai/jina-clip-v2), used by NewBie-Image. It can be directly loaded in ComfyUI using the Dual CLIP Loader node with type `newbie`. Only the text encoder is included here. I'm leaving the vision encoder for future work. There is a lora in the official implementation and I've merged it into the base weights. The tokenizer is included as the tensor `spiece_model`.
Source context: 0 downloads · 1 likes · Repo woctordho/comfyui-jina-clip-v2
