Black Forest Labs · image model · Released May 29, 2025FLUX.1 Kontext [dev]
Open-weight FLUX.1 Kontext model for instruction-based image editing.
- Arena score
- 1,151#55 of 61 · image editing
- Starting price
- —Not published
- Largest size
- —Not published
- References
- Yesinput images for editing
How it rates and what it costs
- Text to image arena
- 942 ±4#80 of 82 · 216,222 votes
- Image editing arena
- 1,151 ±3#55 of 61 · 3,639,663 votes
Arena scores come from blind, side-by-side human votes on the same prompts (higher is better; ± is the 95% range). Boards updated Oct 26, 2026 and Oct 27, 2026.
The details
- Lab
- Black Forest Labs
- Type
- Image model
- Released
- May 29, 2025
- Inputs
- Text prompts, Reference images
- Output
- Images
- Can do
- Text to image, Image editing
- Availability
- 1 API host
More image models from Black Forest Labs
About FLUX.1 Kontext [dev]
How good is FLUX.1 Kontext [dev]?
In blind side-by-side votes, FLUX.1 Kontext [dev] scores 942 for text to image (#80 of 82) and 1,151 for image editing (#55 of 61). Higher is better; scores within about 8 points of each other are effectively tied.
Who makes FLUX.1 Kontext [dev]?
FLUX.1 Kontext [dev] is an image model from Black Forest Labs, released May 29, 2025.
What can FLUX.1 Kontext [dev] do?
FLUX.1 Kontext [dev] accepts text prompts and reference images and produces images. In practice: text to image and image editing.
Is FLUX.1 Kontext [dev] open source?
Yes. Black Forest Labs publishes the weights under the FLUX.1 [dev] Non-Commercial License, so you can run it on your own hardware.
Where can I use FLUX.1 Kontext [dev]?
It is listed by 1 API host we track.
What are the alternatives to FLUX.1 Kontext [dev]?
The closest image models from other labs, by release date, are Lucid Origin (Leonardo.Ai, Jun 1, 2025), Imagen 4 Ultra (Google, May 24, 2025), GPT Image 1 (OpenAI, Apr 24, 2025) and Qwen-Image (Alibaba (Qwen), Aug 7, 2025).