search

tencent-ailab / IP-Adapter

The image prompt adapter is designed to enable a pretrained text-to-image diffusion model to generate images with image prompt.
Apache License 2.0
4.46k stars 289 forks source link

What model is downloaded under the image_encoder_path folder ？ #354

Open RobinChen007 opened 1 month ago

RobinChen007 commented 1 month ago

i don't know what's in models/image_encoder?

xiaohu2015 commented 1 month ago

clip vision model

psycherun-egonym commented 1 month ago

It is the OpenCLIP-ViT-H-14 model as listed in https://huggingface.co/h94/IP-Adapter#image-encoder.

It is downloaded (along with all the other image encoders and IP adapters) through the following commands as described in https://github.com/tencent-ailab/IP-Adapter?tab=readme-ov-file#installation.

git lfs install
git clone https://huggingface.co/h94/IP-Adapter

If you don't have lfs installed, the models are not downloaded.