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
4.48k stars 293 forks source link

A small problem in #How to train #308

Open Hickey8 opened 4 months ago

Hickey8 commented 4 months ago

Hello! Appreciate your work first! It's really impressive and inspiring. I want to ask a small question which is in #How to train part, I think maybe there's no slash(/) after --pretrained_model_name_or_path="runwayml/stable-diffusion-v1-5/". When I add the slash as you offered, there's a problem raised: HFValidationError(
huggingface_hub.utils._validators.HFValidationError: Repo id must be in the form 'repo_name' or 'namespace/repo_name': 'runwayml/stable-diffusion-v1-5/'. Use repo_type argument if needed. When I remove the slash, I can successfully download the model and scheduler_config.json. I doubt whether it's a tiny miss?