---
license: mit
base_model:
- openai/clip-vit-large-patch14-336
---

# This is NOT a fine-tune.
This is the original [OpenAI CLIP ViT-L/14@336 Text Encoder](https://huggingface.co/openai/clip-vit-large-patch14-336), converted to HuggingFace 'transformers' format.
All credits to the original authors.

## Why?
- It's a normal "CLIP-L" Text Encoder and can be used as such.
- See below (Flux.1-dev, CLIP only guidance, CFG 3.5, Heun).
- For my fine-tuned KO-CLIP ViT-L/14@336 -> [see here](https://huggingface.co/zer0int/CLIP-KO-ViT-L-14-336-TypoAttack)


![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/6490359a877fc29cb1b09451/7NioKWTMgWpLuPWzka66s.jpeg)


![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/6490359a877fc29cb1b09451/ZiRkcyPO4vi-mcfxhACCB.jpeg)