Instructions to use Boogu/Boogu-Image-0.1-Edit 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 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Boogu/Boogu-Image-0.1-Edit", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
Chinese Traditional Characters Un-supported?
I tried to prompt "changing all characters into Chinese Traditional" in demo, but failed.
Thanks for reaching out! π
The Boogu-Image-Edit model does natively support rendering Traditional Chinese characters, but it can be a bit finicky or "lazy" when given super short or vague prompts.
To get the best results and make sure the model fully understands what you want, we highly recommend turning on the "Thinking" switch in the demo and giving it a bit more detail. For example, you can try something like this:
"First, identify and extract all visible text in the image. Then, convert all identified characters into Chinese Traditional (ηΉι«δΈζ). Finally, replace the original text in the image with the converted Chinese Traditional characters, ensuring the layout, typography, and overall visual style remain consistent."
Or, if you just want to change specific words, you can tell it directly:
"Change the character 'XXX' into 'YYY' (Traditional Chinese characters)."
The Boogu Team is already on it, and we'll definitely work on improving this in our upcoming updates! Thanks a ton for supporting Boogu-Image. If you spot any other quirks or bugs, feel free to drop them in our GitHub Issues (https://github.com/boogu-project/Boogu-Image/issues) β we'd love to hear from you! π


