Skip to main content
Boogu-Image-0.1 is an Apache-2.0 open-source unified image generation and editing model family. It uses a system that integrates understanding and generation to deliver competitive performance across photography, text rendering, stylization, and image editing tasks. Model Variants:
  • Boogu-Image-0.1-Turbo โ€“ A four-step distilled text-to-image variant focused on high-quality generation and photorealism, equipped with a LoRA rank-128 module. Requires only 3-4 sampling steps. Recommended as the default for most text-to-image use cases.
  • Boogu-Image-0.1-Base โ€“ The foundation model with strong diversity and controllability, ideal for fine-tuning and ultra-dense text rendering at 2K resolution.
  • Boogu-Image-0.1-Edit โ€“ A variant fine-tuned for image editing and transformation tasks with instruction-driven control.
Model Highlights:
  • 10B parameters with efficient inference on consumer GPUs
  • Apache-2.0 license for open use and downstream development
  • Bilingual text rendering (Chinese and English) with reliable typography
  • Versatile capabilities: realistic photography, stylization, poster design, and precise text rendering
Related Links:

โ€‹
Boogu-Image-0.1-Turbo text-to-image workflow

Make sure your ComfyUI is updated.Workflows in this guide can be found in the Workflow Templates. If you canโ€™t find them in the template, your ComfyUI may be outdated.If nodes are missing when loading a workflow, possible reasons:
  1. You are not using the latest ComfyUI version (Nightly version)
  2. Some nodes failed to import at startup

โ€‹
Boogu Turbo: Text to Image

Generate high-quality images from text prompts using the Boogu Turbo model, a distilled 10B-parameter text-to-image pipeline that produces photorealistic outputs in just 4 steps. Boogu Turbo text-to-image workflow preview

Run on Comfy Cloud

Open in Comfy Cloud

Download Workflow

Download JSON or search โ€œBoogu Turboโ€ in Template Library
The Boogu-Image-0.1-Turbo workflow uses a subgraph that encapsulates the diffusion, text encoding, and VAE decode pipeline. You provide a text prompt and resolution settings, and the subgraph handles the rest.

โ€‹
Boogu-Image-0.1-Turbo model downloads

boogu_image_turbo_fp8_scaled.safetensors

Diffusion model for Boogu-Image-0.1-Turbo.

qwen3vl_8b_fp8_scaled.safetensors

Text encoder for Boogu-Image-0.1-Turbo.

ae.safetensors

VAE for Boogu-Image-0.1-Turbo.

boogu_image_turbo_lora_rank_128_bf16.safetensors

LoRA module (rank-128) for Boogu-Image-0.1-Turbo.
Model Storage Location

โ€‹
Boogu-Image-0.1-Edit image editing workflow

โ€‹
Boogu image 0.1 Edit

Edit images using Booguโ€™s instruction-driven model, taking one input image and generating an edited output alongside a side-by-side comparison view. Boogu image 0.1 Edit workflow preview

Run on Comfy Cloud

Open in Comfy Cloud

Download Workflow

Download JSON or search โ€œBoogu image 0.1 Editโ€ in Template Library
Input materials Upload this file to the matching LoadImage node:

tech_cowboy.png

LoadImage node 32 ยท tech_cowboy.png
tech_cowboy.png

โ€‹
Boogu-Image-0.1-Edit model downloads

boogu_image_edit_fp8_scaled.safetensors

Diffusion model for Boogu-Image-0.1-Edit.

qwen3vl_8b_fp8_scaled.safetensors

Text encoder for Boogu-Image-0.1-Edit.

ae.safetensors

VAE for Boogu-Image-0.1-Edit.
Model Storage Location