About FLUX.3 Image Klein (base)
FLUX.3 Image Klein is Black Forest Labs' open-weights text-to-image and image-editing model, released as the base the hosted FLUX 3 Image API is built on. This entry is the fine-tunable checkpoint: train a LoRA on it, then deploy the result to generate or edit images with the same reference-image conditioning the API offers.
Fine-tuning runs through ai-toolkit on Baseten. Reference images in the training data (control image columns) teach image-to-image behaviour; text-only rows teach text-to-image. Deployed LoRAs are served through ai-toolkit's own model class, since no diffusers pipeline exists for the architecture, and accept up to three reference images per request.
The weights are gated on Hugging Face under the FLUX Kommunity License; accept it with the Hugging Face account whose token is configured for fine-tuning.
| Metric | Value |
|---|---|
| Parameter Count | 5.5B (plus 4B text encoder) |
| Mixture of Experts | No |
| Max Resolution | 2K |
| Reference Images | Up to 3 (image-to-image) |
| Quantized* | No |
*Quantization is specific to the inference provider and the model may be offered with different quantization levels by other providers.
Ready to build with FLUX.3 Image Klein (base)?
Try FLUX.3 Image Klein (base) in the Workbench to prompt it, compare outputs, and iterate on prompts without writing any code. When you're ready to ship, call the same model from our API and build your own apps on top of it.
curl -sSf -X POST https://hub.oxen.ai/api/ai/images/edit \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $OXEN_API_KEY" \
-d '{
"model": "flux-3-image-klein-base"
}'API endpoint
See the API reference for request and response formats.
https://hub.oxen.ai/api/ai/images/edit