YangLing0818 / ContextDiff

[ICLR 2024] Contextualized Diffusion Models for Text-Guided Image and Video Generation
https://openreview.net/forum?id=nFMS6wF2xq
61 stars 3 forks source link

where to get the pretrained model #7

Closed jupytera closed 3 months ago

jupytera commented 3 months ago

Excellent work. I would like to ask where could I download the pretrained models such as unet,vae,noise_scheduler,tokenizer that need to be read for model fine-tuning in the ContextDiff_image/finetune_diffusion.py code file when guiding images with text. Thank you for your help.