Instructions to use timbrooks/instruct-pix2pix with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use timbrooks/instruct-pix2pix with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline from diffusers.utils import load_image # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("timbrooks/instruct-pix2pix", dtype=torch.bfloat16, device_map="cuda") prompt = "Turn this cat into a dog" input_image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/cat.png") image = pipe(image=input_image, prompt=prompt).images[0] - Notebooks
- Google Colab
- Kaggle
18 gb vram? jesus, hopfully next verson can run on my 6 gb gpu
for now Im using playground
change yaml file ,load_ema and use_ema false
change yaml file ,load_ema and use_ema false
Where can I find .yaml file? Can't see one in this repo
upd. there is already fixed pix2pix yaml in A1111-webui repo, works on my GTX 1060
change yaml file ,load_ema and use_ema false
Where can I find .yaml file? Can't see one in this repo
upd. there is already fixed pix2pix yaml in A1111-webui repo, works on my GTX 1060
go to github to get the code
I converted this model to pruned ft16 ckpt & satetensor files that are only 2.13 GB. See https://huggingface.co/timbrooks/instruct-pix2pix/discussions/6 for details.
These should significantly reduce VRAM requirements and allow you to run this model eg. on Google Colab.