Black Forest Labs releases Flux 3 Image with multi-step editing
Black Forest Labs has released Flux 3 Image, the image generation component of its Flux 3 model family. The company states that the model supports multi-step editing capabilities that allow users to modify specific parts of an image without altering the rest of the picture. It handles text-to-image, image-to-image conversion, text rendering, and photorealistic outputs.
Key points
- Flux 3 Image supports multi-step edits without changing other parts of the image, BFL claims.
- Users can include up to ten reference images and output up to 4K resolution.
- API access is 50 percent off through October 8; open weights expected in coming weeks.
The model offers several advanced features, including scene composition via bounding boxes and the ability to include up to ten reference images. Outputs can reach up to 4K resolution. A free demo is currently available for users to test the system. For developers, API access is discounted by 50 percent through October 8.
Commercially, companies can license the weights to run and fine-tune the model on their own infrastructure. Black Forest Labs expects to release an open-weight version in the coming weeks. This launch follows closely on the heels of Ideogram announcing its own editing-focused model, version 4.5, which is also planned for an open-weight release soon.
Model page: Flux 3 Image →
The story so far
2 episodes →- Black Forest Labs releases Flux 3 Image with multi-step editingthis story
Black Forest Labs launches Flux 3 Image with multi-step editing that leaves the rest of your picture alone
The Decoder · 2 October 2026
Loading the full article…
This text was published by The Decoder and written by Matthias Bastian. It is reproduced here with attribution so you can read it in full; the rights remain with the publisher. Read it at the source ↗
The headline, key points and digest above were generated by Digest AI's editorial model from the linked sources. Automated summaries can contain errors: the sources are the record. Spotted a mistake? Tell us. Published by Martin K., who runs Digest AI and handles corrections.
More in Generative AI & Models
All →- Anthropic commits $518 billion in AI infrastructure spending over next decade · 4 src
- Perplexity AI releases decision model pplx-decider-v1-27b fine‑tuned from Qwen3.8-27B · 1 src
- OpenAI releases GPT-6.1 Sol, says it nearly matches Astra on agentic coding at one-fifth the price · 37 src
- Author finds 'just right' prompt range speeds GPT-6 Luna High · 1 src
- Google rolls out Gemini 4 Argon, its most advanced AI model · 16 src
Comments
via GitHub Discussions