Open Vision Banana
Open Vision Banana (OVB), by FunAILab, is FLUX.2 [klein] Base fine-tuned to answer perception tasks with an image. The prompt names the task and the output image encodes the answer: segmentation as flat colours, depth as grey, surface normals as RGB. The same weights keep image editing and text to image. LibreYOLO runs it through the LibreGen factory in 4B and 9B.
- Задачи
- image generation
- Размеры
- 4b, 9b at 1024 px
- Установка
pip install "libreyolo[gen]"- Уровень поддержки
- Смежный уровень, начиная с v1.8.0. Отдельная часть продукта со своей фабрикой и контрактом.
- Исходный проект
- Open Vision Banana от FunAILab, FLUX Non-Commercial License. Статья, исходный код
- Лицензии
- Код: Apache-2.0, веса: FLUX Non-Commercial License. Коммерческое использование
Install
pip install "libreyolo[gen]"Predict
The mirrors download once on first use. LibreYOLO loads OVB with diffusers'
Flux2KleinPipeline and adds no network code: what you write is the prompt
and a few lines of NumPy to read the colours back.
from libreyolo import LibreGen, SAMPLE_IMAGE model = LibreGen("open-vision-banana") # 4b; "open-vision-banana-9b" for 9bDEPTH = ( "Estimate a dense relative inverse-depth map for the input image. Produce exactly one output value " "for every input pixel at the same pixel location, with closer points brighter and farther points " "darker. Encode the result as neutral grayscale (R=G=B) using one consistent mapping over the " "complete image. Preserve object silhouettes, thin structures, occlusion boundaries, smooth surfaces, " "and small depth changes. Do not alter the scene or add texture, shading, color, text, labels, " "legends, borders, or objects; return only the registered depth map.")result = model(DEPTH, source=SAMPLE_IMAGE, seed=0)result.generated.save("depth.png")rgb = result.generated.array # (H, W, 3) uint8import jsonfrom libreyolo import LibreGen, SAMPLE_IMAGE model = LibreGen("open-vision-banana")legend = {"building": [255, 8, 232], "sky": [2, 204, 254], "water": [8, 4, 249]}prompt = ( "[TASK: SEMANTIC_SEGMENTATION] Generate a semantic segmentation visualization of the input image, " f"using this color mapping: {json.dumps(legend, separators=(', ', ': '))} " "Color each pixel of a listed class with its color and leave everything else black. " "Output only the segmentation visualization image.")model(prompt, source=SAMPLE_IMAGE, seed=0).generated.save("segmentation.png")from libreyolo import LibreGen model = LibreGen("open-vision-banana")model("an empty tram at a cobblestone stop on a rainy night", imgsz=1024, seed=0).generated.save("tram.png")# The CLI covers text to image only.libreyolo generate model=open-vision-banana prompt="an empty tram at a cobblestone stop on a rainy night"source takes a path, URL, PIL.Image or BGR NumPy array. The output keeps
the photo's aspect ratio, capped at one megapixel; resize it back to the
photo before reading it (nearest-neighbour for masks, so colours stay exact).
Without source it is a normal text-to-image model. Knobs: steps (28) and
guidance (3.5), the paper's settings. offload=True keeps idle parts off
the GPU.
The model was trained on many phrasings of each task. The library's Open Vision Banana guide has FunAILab's quickstart prompts and readouts for semantic, referring and instance segmentation, depth, surface normals and image editing, plus legend ensembling (several passes with shuffled colours and a per-pixel vote).
What to expect: every answer is a 28-step diffusion run, so it is slow. Use it when one model for many tasks matters more than speed. Masks have soft, slightly shifted edges after resizing; depth is relative inverse depth up to an unknown scale and shift, and normals are smooth but not metric.
Variants
| Size | Alias | Mirror | Text encoder | GPU memory (library figure) |
|---|---|---|---|---|
4b | open-vision-banana | LibreYOLO/LibreOpenVisionBanana4b | Qwen3 4B | about 16 GB |
9b | open-vision-banana-9b | LibreYOLO/LibreOpenVisionBanana9b | Qwen3 8B | about 34 GB |
Both mirrors hold the paper's non-zero-shot checkpoints, trained with the
benchmarks' training splits. Another OVB checkpoint saved as a diffusers
pipeline (the zero-shot ones) loads with
LibreGen("open-vision-banana", checkpoint_dir="path/to/folder").
Export
| Задача | ONNX | TorchScript | ExecuTorch | TensorRT | OpenVINO | Paddle | MNN | RKNN | Axelera | ncnn | TFLite | CoreML | Core AI |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Image generation | Image generation to ONNX: не поддерживается | Image generation to TorchScript: не поддерживается | Image generation to ExecuTorch: не поддерживается | Image generation to TensorRT: не поддерживается | Image generation to OpenVINO: не поддерживается | Image generation to Paddle: не поддерживается | Image generation to MNN: не поддерживается | Image generation to RKNN: не поддерживается | Image generation to Axelera: не поддерживается | Image generation to ncnn: не поддерживается | Image generation to TFLite: не поддерживается | Image generation to CoreML: не поддерживается | Image generation to Core AI: не поддерживается |
Training, export and val() are not supported.
Licensing
Проверяйте лицензию в репозитории конкретных весов на Hugging Face. Она указана для каждого чекпойнта в организации LibreYOLO и может различаться даже внутри одного семейства. Этот репозиторий считается авторитетным источником, а сводка ниже описывает условия на момент последней проверки страницы.
Это описание соответствующих лицензий, а не юридическая консультация. Если ответ важен для коммерческого использования, прочитайте лицензии самостоятельно и проконсультируйтесь с юристом.
- Оригинальная работа
- Open Vision Banana, FunAILab
- Лицензия исходного проекта
- FLUX Non-Commercial License
- Исходный код проекта
- github.com/OpenVisionBanana/OpenVisionBanana
- Код LibreYOLO
- MIT
- Веса
- FLUX Non-Commercial License, повторно опубликованы на huggingface.co/LibreYOLO
- Толкование
- The Open Vision Banana weights are fine-tunes of FLUX.2 [klein] Base 4B and 9B and are under Black Forest Labs' FLUX Non-Commercial License, a custom agreement that is not OSI-approved: no commercial or production use. Section 2(e) of that license asks for content filtering or human review of generated images before they are shared, and the same terms apply to the outputs. FunAILab's training code on GitHub is Apache-2.0, but LibreYOLO ports none of it: its adapter is its own MIT code that calls the Apache-2.0 diffusers Flux2KleinPipeline. LibreYOLO redistributes the paper's non-zero-shot checkpoints as complete pipelines at LibreYOLO/LibreOpenVisionBanana4b and LibreYOLO/LibreOpenVisionBanana9b, with FunAILab's transformer cast from float32 to bfloat16 (from FunAILab/Open-Vision-Banana at revision be5da66250cc385ff9c75ebbe4114e13ec305848) and Black Forest Labs' scheduler, Qwen3 text encoder, tokenizer and VAE byte-identical; the mirrors carry the license and are not gated. The zero-shot checkpoints and LoRA adapters stay on FunAILab's repository, under the same license.
Open Vision Banana is by FunAILab (OpenVisionBanana/OpenVisionBanana). The weights are under Black Forest Labs' FLUX Non-Commercial License: no commercial or production use, and section 2(e) asks for content filtering or human review of generated images before they are shared. FunAILab's training code is Apache-2.0, but LibreYOLO ports none of it.
The LibreYOLO mirrors are complete diffusers pipelines, not gated: FunAILab's transformer cast from float32 to bfloat16, the precision it runs in, and the rest of BFL's FLUX.2 [klein] Base pipeline byte-identical. Outputs match FunAILab's own quickstart bit for bit on the same seed.
Citation
@misc{jadon2026openvisionbananafully,
title={Open Vision Banana: A Fully Open Recipe for Generative Visual Perception},
author={Arpit Jadon and Valentinos Pariza and Jona Ruthardt and Ryousuke Yamada and A. Sophia Koepke and Andrei Bursuc and Yuki M. Asano},
year={2026},
eprint={2611.15844},
archivePrefix={arXiv},
primaryClass={cs.CV},
url={https://arxiv.org/abs/2611.15844},
}Скопировано из блока цитирования авторов на странице github.com/OpenVisionBanana/OpenVisionBanana#-citation.