FLUX.1 Kontext, not served here yet
FLUX.1 Kontext takes an image and a text instruction and returns the edited image: local edits, character and style reference, and successive edits with little drift. OpenRelay does not serve it yet; tell us if you want it.
- Text and image in, image out
- Not served yet
- No public rate
Not served yet.
GET /v1/models lists FLUX.1 Kontext with status request_access, but nothing serves it: there is no backend behind the id and no public rate. A request tells us someone wants it.
openrelay/flux.1-kontextTell us you want FLUX.1 Kontext
Leave a work email. We email you if we start serving it, and nothing else goes to this list.
The spec sheet.
What Black Forest Labs has published about the model, with the source on each row.
- On OpenRelay
- openrelay/flux.1-kontext: Text and image in, image out. Listed with status request_access, not served. GET /v1/models
- Task
- In-context image generation and editing, prompted with text and images together Black Forest Labs, May 29, 2025
- Consistency
- Character, style and object reference without fine-tuning; successive edits with minimal visual drift Black Forest Labs model card
- [pro] and [max]
- Served through Black Forest Labs and its partners Black Forest Labs, May 29, 2025
- [dev]
- Open weights, a 12B rectified flow transformer, under the FLUX.1 [dev] Non-Commercial License Black Forest Labs model card
- Announced
- May 29, 2025 Black Forest Labs, May 29, 2025
FLUX.1 Kontext, answered.
Can I edit images with FLUX.1 Kontext on OpenRelay?
Not today. openrelay/flux.1-kontext appears on GET /v1/models as text and image in, image out with status request_access, but nothing serves it, and there is no image endpoint or rate. The form on this page tells us you want it.
How is Kontext different from FLUX.1?
FLUX.1 generates an image from text. Kontext takes an image and an instruction and edits it, keeping characters, styles and objects consistent from one edit to the next.