Boogu-Image-0.1 is a competitive Apache-2.0 open-source unified image generation and editing model family, including Base, Turbo, Edit, and other variants that provide stable, practical capabilities for high-quality text-to-image generation, fast generation, image editing, and Chinese-English text rendering. Closed-source multimodal understanding and generation systems like Nano Banana Pro and GPT-Image-2 achieve remarkable performance not because of a single model, but through a highly unified suite of system capabilities. However, under training compute that is extremely limited compared with closed-source systems, we find that systematically improving a model's understanding ability, data quality, and training pipeline can still significantly improve image generation and editing performance. Specifically, compared with some existing open-source models, our training data scale is roughly one order of magnitude smaller. We hope our empirical study and open-source release will help advance the open-source ecosystem for multimodal generation and understanding.
This repository provides checkpoints and inference code for Boogu-Image-0.1.
🏆 Boogu Arena
Since we could not evaluate on LM Arena directly, we built Boogu Arena, an LM Arena-style preference evaluation. We use an LLM to generate diverse user personas, then ask each persona to produce image generation prompts, resulting in 1K+ test prompts that we will release publicly for community reproduction. The ELO leaderboard below spans leading closed- and open-source systems. We welcome teams with questions about the results to contact us so that we can work toward a more objective, fair, and reproducible evaluation.
Boogu Arena ELO Leaderboard
✨ Highlights
📸 Beautiful and Precise Photography — Accurately understands photography prompts and generates high-quality images with natural lighting, coherent composition, and faithful details, preserving coherent subject, background, and spatial relationships even in complex real-world scenes
📝 Diverse and Stable Text Rendering — Supports a wide range of text-heavy designs — posters, stamps, documents, interfaces, brand guides, and handwritten boards — with readable structure, stable typography, and robust bilingual (Chinese/English) rendering across diverse layouts
🎨 Diverse and Beautiful Stylization — Handles stylized generation across miniature 3D scenes, Chinese-inspired gilded aesthetics, shining fantasy visuals, anime portraits, and mythic character art — not just style transfer, but stable, attractive, and prompt-aware creative generation
📊 Competitive General Performance — Demonstrates competitive performance across many scenarios and benchmarks, with the Boogu-Image-0.1 family ranking among the very top of evaluated open- and closed-source systems in Boogu Arena
📖 For the full set of practical lessons and an honest account of current limitations, see Responsible AI & Limitations below.
📣 News
2026-06-17 🔥 ComfyUI-Boogu powered by ComfyUI is released! Thank you, ComfyUI!
Boogu-Image-0.1-Base: Foundation model with strong diversity and controllability — ideal for fine-tuning and downstream development. Mainly intended for ultra-dense text rendering; for photorealism, Turbo is usually the better default.
Boogu-Image-0.1-Edit: Image editing and transformation variant.
Boogu-Image-0.1-Turbo: Distilled variant with the same parameter count, typically requiring only 3~4 steps. Focuses on high-quality generation and photorealism while preserving bilingual text rendering and prompt adherence.
🛠️ Installation
Tested environment: Python 3.10 · CUDA 12.6 · PyTorch 2.7.1
bash
1# Use a brand new conda environment2conda create -y -n boogu python=3.103conda activate boogu
4# Instal necessary dependencies5# PyTorch up to 2.11.0 with CUDA up to 12.8 is supported6# Check `requirements/<torch>_<cuda>.txt`7pip install -r requirements/torch2.7-cu126.txt
8pip install -e .9python utils/get_flash_attn.py
or
bash
1bash quick_start.sh
2conda activate boogu
Download Checkpoints
Download the model weights into a local models/ directory before running inference. We recommend using the official Hugging Face CLI:
1exportdevice="cuda:0"# Required23# Prompt enhancement is powered by an instruction reasoner, also called the rewriter.4# We provide two ways to use it:5#6# 1. Standalone external rewriter:7# See utils/t2i_external_prompt_rewriter.py. This is a pure external mode example and8# requires enough GPU memory, without advanced memory management.9# python utils/t2i_external_prompt_rewriter.py --prompt "draw a cat" --model /path/to/Qwen3-VL-32B-Instruct --lang en10#11# 2. Pipeline-integrated rewriter:12# See the scripts under `demo_scripts` whose names contain "reasoning".13# For example: demo_scripts/demo_t2i_local_reasoning.sh14# This mode supports more flexible memory management. Set the generation and15# rewriter devices manually, then pass them to inference.py:16# export device="cuda:0"17# export rewriter_device="cuda:1"18# python inference.py --device $device --rewriter_device $rewriter_device ...19# For more details, see INFERENCE_GUIDE.md.2021python inference.py \22 --pretrained_pipeline_name_or_path "models/Boogu-Image-0.1-Base"\23 --instruction "一幅国风琉金风格的山水画作，展现了桂林山水在金光普照下的壮丽景象。远山层叠，江水如镜，山峰边缘勾勒着发光的金色线条。画面采用石青石绿岩彩与鎏金质感相结合，局部有厚涂油画笔触，空中飘浮着金色粒子，营造出梦幻朦胧而又磅礴大气的意境。"\24 --num_inference_steps 50\25 --height 1024 --width 1024\26 --text_guidance_scale 4.0\27 --output_image_path "outputs/test_base/out_1.png"\28 --device "$device"
Hardware Notes
📖 For full CLI options, device setup, offload strategies, caching acceleration, Torch Compile, FP8, and batch inference details, see INFERENCE_GUIDE.md.
Torch Compile note: --enable_torch_compile can occasionally produce all-black outputs on some GPUs/models. If that happens, disable it first.
Boogu-Image-0.1 is released for research purposes and is not intended for production deployment without additional safeguards. We took responsible-AI considerations into account during data curation, training, and evaluation; however the model may still produce outputs that are inaccurate, biased, or otherwise inappropriate.
Known Limitations
🌍 World Knowledge Gap
For tasks requiring rich common sense, domain knowledge, real brands or people, famous landmarks, celebrities, products, or complex contextual understanding, Boogu still has a clear gap from strong closed-source systems
This capability is extraordinarily expensive to measure; even Arena-style evaluation struggles to assess it fully, so existing benchmarks barely quantify this dimension and the real gap is likely larger than measured scores suggest
For editing tasks requiring strict preservation of the input subject, identity, layout, or fine details, Boogu's image-to-image consistency is still not stable enough
Because our image-to-image capability focuses more on photography and text-generation applications, Boogu still trails Seedream 5.0 and Nano Banana Pro in some in-context generation scenarios
📝 Text Rendering Stability
Boogu can handle many Chinese and English text scenarios, but long text, dense typography, small fonts, and complex design layouts can still produce typos, missing characters, or layout drift
Text rendering is currently focused on Chinese and English; other languages are not specifically optimized and may degrade noticeably
🦴 Body Structure in Complex Poses
In multi-person interaction, occlusion, exaggerated motion, or unusual viewpoints, hands, limbs, and body structure may still become unnatural or inconsistent
👤 Small Faces & Small Limbs
Because we use the open-source FLUX.1 VAE, reconstruction loss is relatively large, so details such as small faces, small limbs, eyes, and text may still show artifacts or instability
📦 Limited Release Scope
Due to resource constraints, engineering complexity, and release boundaries, we are not able to open-source every training and system detail
The current open-source release aims to balance reproducibility, usability, and sustainable maintenance while providing a reliable starting point for community research and improvement
Downstream users are responsible for applying content moderation, validation, and compliance checks appropriate to their use case.
🙏 Acknowledgements
Closed-source systems such as GPT-Image, Nano Banana, and the Seedream series helped us understand the frontier capabilities and practical boundaries of unified understanding-and-generation systems. We thank the Qwen-Image, Z-Image, OmniGen2, FLUX, and broader open-source communities for the foundations they provide, and DeepSeek for strong open-source understanding models that support open-source unified multimodal systems.
-lightgrey){kind=icon}