search

nateraw / stable-diffusion-videos

Create 🔥 videos with Stable Diffusion by exploring the latent space and morphing between text prompts
Apache License 2.0
4.34k stars 413 forks source link

fix from_pretrained so you don't need to pass extra kwargs to make it work #165

Closed nateraw closed 1 year ago

nateraw commented 1 year ago

Related to #162 ...rn you have to pass feature_extractor=None, safety_checker=None for from_pretrained to work properly on some models. looking into fix.

nateraw commented 1 year ago

@patrickvonplaten suggested this could potentially fix it in internal HF thread. checking...

https://github.com/huggingface/diffusers/blob/55de50921f89ec06ed51381514c2710cabab1d8e/src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion.py#L82