whatmodel.sh / image / FLUX.1 Krea [dev]
FLUX.1 Krea [dev]
↗ share
+ contribute
FLUX.1 Krea [dev] is an open-weights image model from Black Forest Labs / Krea, released July 2025. Its published size is 12B parameters. Licence: flux-dev-nc.
Model information sources
Release date ↗ · Weights licence ↗ · Parameter count ↗
12B = the rectified flow transformer as Black Forest Labs states it on the card; the text encoders and VAE used by the pipeline are not included (same convention as flux-1-dev).
Score within the LMArena text-to-image comparison set only.
$ how it compares
The image models ranked either side of FLUX.1 Krea [dev], out of 197 with a score.
| # | model | score | where |
|---|---|---|---|
| 112 |  SeedEdit 3.0 | 48±3 | comparison only |
| 113 |  Ovis-Image-7B | 48±7 | local |
| 114 | FLUX.1 Krea [dev] | 47±3 | api $0.025/image +local |
| 115 |  MetaQuery-XL | 47±6 | comparison only |
| 116 |  HiDream-I1-Full | 47±2 | api $0.050/image +local |
$ what it's good at
text to image▂▅▅▃▄▄█▃▁▂▁▁ #75 of 126 * · 90% of its score · 2 tests
Beats Latent Diffusion text2img-large (LDM-KL-8-G, LAION-400M), VQ-Diffusion (ITHQ) here, though they rank higher overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| ImagenWorld text-guided generation (human overall) | 82.0% ✎ | ▄··█▄·▄··▄·▄ beats 4/6 | 52% |
| GenExam (relaxed overall, GPT-5 judge) | 16.4% ✎ | ▆▆·▂▂····▂▂█ beats 0/13 | 38% |
other tests1 not in a task · 5.1% of its score
| test | result | vs the others in its run | counts |
|---|---|---|---|
| Knowledge Visualization T2I (Brief Caption, English overall) | 18.2% ✎ | ▅·▃·▃··▃·█▃▃ beats 0/9 | 5.1% |
$ where to run it
Through an API
api · Replicate · $0.025/image · replicate.com ↗ · price sourceUSD per output image on Replicate's official black-forest-labs/flux-krea-dev model (billing: $0.025 per output image, "or 40 images for $1"; hardware time not added). The current version is served from replicate-pruna/flux-krea-dev (Pruna-optimized deployment). Product: Replicate model API. API model: black-forest-labs/flux-krea-dev. Settings: one output image. Price basis: published list rate. fal's fal-ai/flux/krea bills $0.025 per megapixel, rounded up to the nearest megapixel. Currency: USD. Not a BFL or Krea direct tariff. Replicate official model page, observed 2026-09-26.
Other ways to run it
- Run it as published · needs ~41 GB, NVIDIA only · from huggingface.co/black-forest-labs (official)
uv run --with diffusers --with transformers --with accelerate --with torch --with sentencepiece python -c "import torch; from diffusers import FluxPipeline; p=FluxPipeline.from_pretrained('black-forest-labs/FLUX.1-Krea-dev', torch_dtype=torch.bfloat16); p.enable_model_cpu_offload(); p('A frog holding a sign that says hello world', height=1024, width=1024, guidance_scale=4.5).images[0].save('flux-krea-dev.png')"
Official weights and documentation: huggingface.co/black-forest-labs ↗
$ how the score was worked out · ImagenWorld: Stress-Testing I… 52%, GenExam leaderboard (OpenGVLa… 38%, Knowledge Visualization: A Be… 5%
Each result implies a score on its own, after adjusting for how hard its test is and who ran it. The score is their weighted average, with a small pull toward the middle for thinly tested models. Each test's weight is its counts column above; here it's added up by who ran the tests. How it works
| source | results | share of the score |
|---|---|---|
 ImagenWorld: Stress-Testing Image Generation Models with Explainable Human Evaluation on Open-ended Real-World Tasks | 1 | 52% |
 GenExam leaderboard (OpenGVLab/GenExam README, relaxed score) | 1 | 38% |
| Knowledge Visualization: A Benchmark and Method for Knowledge-Intensive Text-to-Image Generation (arXiv:2604.22302v1) | 1 | 5% |
| prior · pull toward the middle | 5% | |
| weighted average | = 47.0 |
$ improve this page
Use a short GitHub form or edit the data through a pull request. Every number needs a source; here's which ones we can use.
data updated · sources and licences · json