wowsuch ai
Live

Black Forest LabsModel

FLUX 3 Image Klein Prompt Upsampler

FLUX 3 Image Klein Prompt Upsampler is a 9B vision-language model that expands a short image request into a detailed prompt for FLUX 3 Image Klein. It can use up to 10 reference images and optional bounding boxes, and is released under the Apache License 2.0.

What it does

Use it to turn brief requests into detailed prompts for FLUX 3 Image Klein text-to-image generation, image editing, and layout workflows.

Availability
Model weights and inference instructions are provided on Hugging Face.
Pricing model
Not established
Deployment
Can be run using FLUX 3 inference code or Transformers.
Privacy
Not established
Licence
Apache License 2.0
Capability
text generation
Modality
textimage
Access
CLISDKopen weights
Deployment
on-premises
Pricing
unknown
Target user
developercreator

Evidence

6 claims
  • The 9B vision-language model expands a short image request into a detailed prompt for FLUX 3 Image Klein. [1]
    FLUX 3 Image Klein Prompt Upsampler is a 9B vision-language model that expands a short image request into the detailed prompt [FLUX 3 Image Klein](https://huggingface.co/black-forest-labs/flux-3-image-klein-base) works best with.
    Hugging Face. Quoted text is outside CC BY 4.0 and keeps its original rights.
  • It accepts up to 10 reference images and an optional list of bounding boxes. [1]
    It takes the request, up to 10 reference images and an optional list of bounding boxes, and returns one prompt.
    Hugging Face. Quoted text is outside CC BY 4.0 and keeps its original rights.
  • The model supports text-to-image, reference-image editing, and layouts with bounding boxes. [1]
    One model for text-to-image, editing with reference images and layout with bounding boxes.
    Hugging Face. Quoted text is outside CC BY 4.0 and keeps its original rights.
  • The model weights are available as a downloadable model.safetensors file on Hugging Face. [1]
  • The prompts are written for FLUX 3 Image Klein; no other image model was part of training. [1]
    - The prompts are written for FLUX 3 Image Klein; no other image model was part of training.
    Hugging Face. Quoted text is outside CC BY 4.0 and keeps its original rights.
  • The model is released under the Apache License 2.0. [1]
    Released under the Apache License 2.0.
    Hugging Face. Quoted text is outside CC BY 4.0 and keeps its original rights.

Sources

1
1
Hugging FaceOwner-controlled
https://huggingface.co/black-forest-labs/flux-3-image-klein-pup Retrieved 2026-10-27 01:40 UTC
Verified

Versions

2
VersionEffectiveChangeChanged fieldsState
22026-10-16 21:35 UTCmaterial changecapability, modality, access, deploymentCurrent
12026-10-15 22:34 UTCpublicationNoneCurrent

In briefs

1

Open in the catalog

Original catalog content is licensed under CC BY 4.0, attributed to wowsuchai. Source quotations and linked content keep their original rights.