aduchon

This order worked for me in a colab. You basically have to turn time back to November, 2022, before the jax0.4 versions. I did not even have to restart like...

Note that the jax/tpu version can not deal with negative prompts. I ended up going back to the regular gpu version, which also seemed faster.

EDIT: a recent change in colab has broken a number of AI-related notebooks I use. So this may just be another. I'm having similar issues with colab. I couldn't figure...

be sure to put the negative prompts in the new uncond_prompt field.

Here's the setup, using SDXL ```from diffusers import StableDiffusionXLPipeline, StableDiffusionXLImg2ImgPipeline from compel import Compel, ReturnedEmbeddingsType base = StableDiffusionXLPipeline.from_pretrained( "stabilityai/stable-diffusion-xl-base-1.0", variant="fp16", use_safetensors=True, torch_dtype=torch.float16, add_watermarker=False, # no watermarker safety_checker=None, ) # memory...

I was able to get it to run stylegan3 (only) installing things in this order on a colab with gpu. `!git clone https://github.com/nupurkmr9/vision-aided-gan.git !pip install clip@git+https://github.com/openai/CLIP.git !pip install wandb !pip...