`FLUX.2 [klein] 4B Base` is a 4 billion parameter rectified flow transformer capable of generating images from text descriptions and supports multi-reference editing capabilities. For more information, please read our blog post. This repository holds an FP8 version of FLUX.2 [klein] 4B Base. The main repository of this model (full BF16 weights) can be found here. - This model is not intended or able to provide factual information. - While the model can output text, text rendered may be inaccurate or subject to distortion. - As a statistical model, this checkpoint may represent or amplify biases observed in the training data. - The model may fail to generate output that matches the prompts. - Prompt following is heavily influenced by the prompting style.
`FLUX.2 Small Decoder` is a distilled VAE decoder that serves as a **drop-in replacement** for the standard FLUX.2 decoder. It delivers faster decoding and lower VRAM usage with minimal to zero quality loss. The encoder remains unchanged. 1. **~1.4x faster decoding** compared to the full decoder. 2. **~1.4x less VRAM** at decode time, enabling higher resolutions without running out of memory. 3. **~28M decoder parameters** (vs ~50M in the full decoder) thanks to narrower channel widths (`[96, 192, 384, 384]` vs `[128, 256, 512, 512]`). 4. **Minimal quality loss** — images are almost identical. 5. Available under the Apache 2.0 license. Compatible with all open FLUX.2 models: - FLUX.2-klein-4B - FLUX.2-klein-9B - FLUX.2-klein-9b-kv - FLUX.2-dev
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 works best with. It takes the request, up to 10 reference images and an optional list of bounding boxes, and returns one prompt. It is a fine-tune of Qwen3.5-9B. FLUX 3 Image Klein is not meant to run without a prompt upsampler in front of it, for text-to-image, editing and layout alike; a short prompt sent to the image model as typed gives generic output. This one is tuned for it, see Training. Any other LLM can do the job with the system prompts in `system_prompts.json`. The inference code in black-forest-labs/flux-3-image-klein loads it by default. With Diffusers, run the Transformers block below and pass the caption to the pipeline as `prompt`. In ComfyUI, the text-to-image templates on flux-3-image-klein-comfy have an `enable_prompt_upsampler` switch. > Full-color outdoor photograph, eye-level medium-wide shot in late afternoon sunlight, showing a man walking his dog along a neighborhood sidewalk. The low sun shines from the upper right, casting long shadows across the pavement and lighting the man's face and clothing with warm side light. Slightly left of center, a white man in his thirties with fair skin, short brown hair, and light stubble walks toward frame-left at an easy pace. He wears a faded olive overshirt over a plain grey T-shirt, dark blue jeans, and worn brown leather shoes. [...]
Fine-tuned **Qwen3** models for knaif, a local command-line tool that turns a request like *"compress holiday.mp4 for whatsapp"* into a strict JSON **action plan** (`{"plan": [...]}`). Deterministic code then validates, expands, confirms and executes the plan through skill packages. **The model only proposes the plan**; it never runs anything itself. Public names (`v1`, `v2`) are release versions and move by one per publication. The fine-tune cycle is internal provenance. Older files stay here, so a pinned install keeps working. A knaif release is bound to the models it was tested with; its bundled manifest names them, and `knaif` downloads the recommended one on first run.
