DEV Community

AI-KSK
AI-KSK

Posted on Edited on Originally published at huggingface.co

Boogu Image 0.1: Turbo Text-to-Image and Single-Image Editing

Three Boogu Image 0.1 workflows covering the base text-to-image graph, a single-image editor, and the Turbo variant for fast iteration.

The three workflows

# Workflow Purpose
1 Base text-to-image The reference graph
2 Single-image edit Edit an existing image
3 Turbo fast T2I Accelerated generation

What Boogu Image 0.1 is like to use

It is a smaller model than the current flagship image models, and it behaves like one: faster to
load, more forgiving on VRAM, and less capable at dense prompts. The Turbo variant narrows that gap
by cutting steps rather than by changing the model.

The single-image edit graph is the one worth keeping. It handles the common case — swap an object,
change a colour, adjust a background — without needing a mask.

Where it fits

For high-volume iteration on a local GPU, the Turbo graph produces usable drafts in the time the
big models take to load.

Running Hub links

Files

Workflow JSONs and covers: https://huggingface.co/AI-KSK/ksk-video-266-comfyui-workflows

Video walkthrough (Chinese): https://youtu.be/wqJu2HlSiUo

Bilibili: https://www.bilibili.com/video/BV17ujH6eEZk/

Notes

  • ComfyUI exports that reference models present in the cloud instance; not self-contained packs.
  • Tutorial material, not a product.
  • Independent AI-KSK release. Not affiliated with or endorsed by the model authors or RunningHub.

Optional API platform - 88API (affiliate link)

Explore 88API for access to multiple AI model APIs. Available models, routes and prices are listed on the platform; Alipay top-ups are supported.

https://88api.ai/sign-up?aff=usx3

Disclosure: I may earn a commission from eligible purchases after you register through this referral link.

Top comments (0)