Instructions to use Boogu/Boogu-Image-0.1-Edit-fp8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Boogu/Boogu-Image-0.1-Edit-fp8 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("Boogu/Boogu-Image-0.1-Edit-fp8", torch_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
Please make a good edit model
Qwen image edit is slow
Klein 9b does weird things
Zimage edit is cancelled
No one cares about t2i models anymore, we already have good t2i models
We need a good edit model
Everyone wants a good edit model
We're all waiting for a good edit model
Ideogram might be releasing an edit model soon
Everyone has been asking Ideogram team "will you release an edit model?"
Because we're all waiting for a good edit model
Imo, the image quality and the instruction following are good, but the image does not look as natural as Flux Klein. The output of Klein for my old photo restoration and recoloring task seem way better and more natural than this model, even when using 4B Klein variant. The restyle or object adding/removal of this model seem solid, though I would be skeptical that this model can beat Klein 9B, but the license will make them very competitive. Kudos to the authors.
We hear you! The Boogu team is committed to continuously polishing the edit model. Thank you all for the attention and support!
BTW, our Edit-turbo is on the way. Please stay tuned🚀!