Boogu-Image Turbo is the speed-distilled text-to-image build in the Boogu-Image 0.1 family. It carries the same 10B-parameter backbone as Boogu-Image Base but is tuned to produce photorealistic results in just 4 steps with CFG 0, trading some of Base's diversity for a large jump in generation speed.

Originally released by the Boogu team on Hugging Face. All credit for the model goes to the Boogu project and its contributors. Civitai is hosting a mirror so creators can run it on-site without a local setup - please head to the original repo and project site for weights, updates, and to support the project directly.

Built by the Boogu project

• Boogu project - model training and release
• Hugging Face org and ModelScope org - weights and variant downloads
• Acknowledged upstream influences: Qwen-Image, Z-Image, OmniGen2, FLUX, and DeepSeek

What it does

Turbo is the build to reach for when throughput matters: fast iteration, batch work, and interactive generation. It keeps the family's strengths in photography, bilingual Chinese and English text rendering, stylization, and poster design, at a fraction of the step count. Recommended starting point is 4 steps, CFG 0.

Versions on Civitai

We mirror the v0.1 release in three diffusion builds: bf16 full precision (~20GB), fp8_scaled (~10GB), and nvfp4 (~5.7GB). The required Qwen3-VL 8B text encoder and the Flux VAE are bundled. Note: this is a full distilled checkpoint, not a LoRA.

Related Boogu models

Boogu-Image Base is the full-quality foundation model at 25 to 50 steps. Boogu-Image Edit adds image-to-image editing.

Known limitations

The Boogu team is candid that 0.1 is an early research release: limited world knowledge for brands, celebrities, and landmarks; instability in strict subject preservation; occasional text typos or layout drift; and artifacts in complex poses, small faces, and limbs.

Links

• Source: Hugging Face | GitHub | ModelScope
• Project site: boogu.org
• Gallery: boogu-gallery.netlify.app

Boogu-Image 0.1 is a research project, not an official product release. The Boogu team asks that you not build unauthorized commercial products under the Boogu name. Licensed under Apache 2.0.