search

ShivamShrirao / diffusers

🤗 Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch
https://huggingface.co/docs/diffusers
Apache License 2.0
1.89k stars 505 forks source link

Train a model on a prior trained model #191

Open charliewang789 opened 1 year ago

charliewang789 commented 1 year ago

I know it can support fine tune based on a pre-trained model,

pipe = StableDiffusionPipeline.from_pretrained("./stable-diffusion-v1-5") pipe = pipe.to("cuda")

This is a trained model from huggingface.

let's say I generated a new model - stable-diffusion-me-v1.

can I then train it based on this model with other dataset?

pipe = StableDiffusionPipeline.from_pretrained("./stable-diffusion-me-v1") pipe = pipe.to("cuda")