Boogu-Image: Open Source Text to Image with Base + Turbo Variants

Boogu-Image is a versatile text-to-image generation model with base, turbo, and turbo hotfix variants for ComfyUI.

B

Boogu-Image

Text-to-ImageImage EditingTurboQuantized

Versatile image generation model with base, turbo (distilled), and edit variants. Available in BF16, FP8 scaled, INT8 ConvRot, and NVFP4 quantization. Uses Qwen3-VL 8B text encoder and FLUX.1 VAE.

Hugging FaceHF Org
DeveloperBoogu
Release Date2025-11
ArchitectureDiffusion Transformer
LicenseApache-2.0
Text EncoderQwen3-VL 8B (FP8)
VAEFLUX.1 VAE (BF16)
VariantsBase, Turbo, Edit, Turbo Hotfix — each in BF16/FP8/INT8/NVFP4

Guides and workflows related to this model series.

No articles found.