Instructions to use Comfy-Org/Boogu-Image with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusion Single File
How to use Comfy-Org/Boogu-Image with Diffusion Single File:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
SKin like a lizard
#8
by BoyoDiffusion - opened
so far only tried the turbo model.
It really needs a helping hand from a Z.-image upscaler or seedvr. It's a bit low res. I read it may have to do with the Flux.1 vae they use. It is 0.1, so a good base is promising. Deffo worth trying the base model.
It seems one of the beter recent models. It doesn't need 2 humans and three llm for it's prompt like IdeogramV4, it is not as blurry as hidreamO1 and it seems to do anatomy quite well AND does not turn everybody chinese, so it beats Ernie Image by miles.
Not sure where and why to chose it over Z-image. For now.
