LibreOpenVisionBanana9b

Open Vision Banana 9B by FunAILab: FLUX.2 [klein] Base 9B fine-tuned to answer perception tasks with an image. The prompt picks the task; segmentation comes back as flat colours, depth as grey, surface normals as RGB. It also edits images and generates from text. This is the paper's non-zero-shot checkpoint, packaged as one complete diffusers pipeline for LibreYOLO.

from libreyolo import LibreGen, SAMPLE_IMAGE

model = LibreGen("open-vision-banana-9b")   # downloads this repo
prompt = (
    "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."
)
model(prompt, source=SAMPLE_IMAGE, seed=0).generated.save("depth.png")

Install libreyolo[gen]. Prompts for every task and the NumPy readouts (class ids, masks, disparity, unit normals, legend ensembling): LibreYOLO's Open Vision Banana guide.

The folder also loads with diffusers alone:

import torch
from diffusers import Flux2KleinPipeline

pipe = Flux2KleinPipeline.from_pretrained("LibreYOLO/LibreOpenVisionBanana9b", torch_dtype=torch.bfloat16).to("cuda")

What changed from upstream

Nothing was retrained.

  • transformer/: FunAILab's FunAILab/Open-Vision-Banana at revision be5da66250cc385ff9c75ebbe4114e13ec305848, folder final_models/9B/nonzeroshot/checkpoint-avg82500-85000-87500-92500-97500_uniform/transformer, cast from float32 to bfloat16 (the precision it runs in) and otherwise unchanged. Outputs match FunAILab's quickstart, their float32 transformer loaded in bfloat16, bit for bit on the same seed.
  • scheduler/, text_encoder/ (Qwen3), tokenizer/, vae/, model_index.json: byte-identical copies of black-forest-labs/FLUX.2-klein-base-9B at revision 32773329fbe7e81a90ef971740e8ba4b0364ecf3 (FLUX Non-Commercial License).
File SHA-256
text_encoder/model-00001-of-00004.safetensors c0dc64934ae0f730ddc80d99af44968d01a89e8454df07d762096ea1356446bc
text_encoder/model-00002-of-00004.safetensors d58533b468c31caa0222540a8aefddea1d74dc6e1fee928da8556d3d85729d6e
text_encoder/model-00003-of-00004.safetensors 74927fec432e050365bf757bb30348f560a44394efac89f492680b7c910b64fd
text_encoder/model-00004-of-00004.safetensors cb73f466fade5716702bda38d4e3b321c9358c39889e46fb9d613fb038bfcb2f
transformer/diffusion_pytorch_model-00001-of-00002.safetensors 6c2d3cf13a770165a57ca8d50552353cc183e9db27093bd1ef630d454dfe8e9b
transformer/diffusion_pytorch_model-00002-of-00002.safetensors 7ab18928d1a27158971c206d4209d6d0418b3ebc912b0391862c8ac4a47501e6
vae/diffusion_pytorch_model.safetensors ca70d2202afe6415bdbcb8793ba8cd99fd159cfe6192381504d6c4d3036e0f04

Paper: Open Vision Banana: A Fully Open Recipe for Generative Visual Perception. Code: OpenVisionBanana/OpenVisionBanana.

License

The weights are derived from FLUX.2 [klein] Base and are under the FLUX Non-Commercial License (LICENSE): no commercial or production use. See NOTICE.

@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},
}
Downloads last month
-
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for LibreYOLO/LibreOpenVisionBanana9b

Finetuned
(2)
this model

Paper for LibreYOLO/LibreOpenVisionBanana9b