According to open_clip.list_pretrained() function there are about 40 CLIP models. But all of them can be divided into main groups:

• ResNet
• ViT
• ConvNeXT
• Hybrid models

Worse to mention one of the most popular CLIP models trained by OpenAI and based on ViT architecture: clip-vit-base-patch16, clip-vit-large-patch14-336, clip-vit-large-patch14, clip-vit-base-patch32.

***CLIP models recommendation:***

- For best prompts with Stable Diffusion 1.* choose the **ViT-L-14/openai** model.
- For best prompts with Stable Diffusion 2.* choose the **ViT-H-14/laion2b_s32b_b79k** model.
- For best prompts with Stable Diffusion XL choose **ViT-L-14/openai** or **ViT-bigG-14/laion2b_s39b** model.

***CLIP demos:***

- [CLIP-Interrogator](<https://huggingface.co/spaces/pharmapsychotic/CLIP-Interrogator>)
- [CLIP-Interrogator-2](<https://huggingface.co/spaces/fffiloni/CLIP-Interrogator-2>) 
- [CLIP Interrogator Extension](<https://github.com/pharmapsychotic/clip-interrogator-ext.git>)

Credit: [clip-interrogator-github](<https://github.com/pharmapsychotic/clip-interrogator>)