The image model just learned to lay out pages. black forest labs' flux 3, out oct 8, renders 4k…
the image model just learned to lay out pages. black forest labs' flux 3, out oct 8, renders 4k output with bounding-box layouts and up to 10 reference images.
the compositor now lives inside the model.
Context
Verified source: Black Forest Labs' documentation says FLUX 3 Image can generate images from text, edit specific details, combine up to ten references and draw bounding boxes to place each element. Its bounding box guide says each element can be recolored, moved, replaced or removed box by box while the rest of the image stays unchanged.
Black Forest Labs announced FLUX 3 as a multimodal model for video, audio, images and actions on Jul 23, 2026 (GlobeNewswire, Jul 23), with Early Access at launch.
The bounding-box layouts and up to ten reference images match the FLUX 3 Image docs. The Oct 8 release date and the 4K output were not seen in the sources read, so unsupported here, not refuted. The sources read date the FLUX 3 announcement to Jul 23, 2026 in Early Access, so Oct 8 may refer to a later image release; that is not confirmed here. 'The compositor now lives inside the model' is the author's.
'the image model just learned to lay out pages' is the author's opinion.
Related work
Watch next
- Check the FLUX 3 Image release date and the maximum output size in the docs.
Sources
Provenance
The note above is reproduced unedited from the original post, first published on Threads on 11 October 2026 at 12:02 IST. Sources are the papers and datasets the note draws on.
View the original post ↗Embed this note
More notes
The air is now being asked to keep its own ledger
the air is now being asked to keep its own ledger: ecmwf’s aifs compo becomes the first ai model to forecast atmospheric composition globally every three hours, cleanair simulates 365 days of pm2.5 over china in ten seconds, and a unified framework maps six pollutants at one kilometer across the whole country. the air now files its own composition report.
read the note →The current is now being asked to draw its own map
the current is now being asked to draw its own map: china’s langya 2.0 predicts six ocean phenomena including internal waves and mesoscale eddies, a deep net called wenhai resolves eddies globally with air sea flux formulas built in, and scripps infers surface currents from the way temperature patterns deform in satellite images. the ocean now files its own circulation report.
read the note →The soil is now being asked to report its own carbon
the soil is now being asked to report its own carbon: a nix color sensor paired with generative data augmentation predicts soil organic carbon without a lab, random forest drives 74 percent of soil health mapping studies, and sentinel 2 tracks five year carbon change across france and italy from 922 samples. the dirt now files its own carbon account.
read the note →