Seedream 5.5 launches on fal with multi-turn editing, in-image text edits, and layer separation
Jamez_Chi · x · 2026-11-12
fal announces that ByteDance's Seedream 5.5 image model is now live, bringing three notable new capabilities:
- Multi-turn editing: iteratively refine images across turns
- Direct text editing inside generated images
- Layer separation: split images into independently editable layers
These features are particularly useful for e-commerce assets, poster design, and other creative workflows.
More from Multimodal
- Webcam feedforward 4D Gaussian Splatting livestream runs at 30+ fps — janusch_patas · 2026-11-12
- MiniMax H3 powers Live Film, letting audiences steer the story in real time — MiniMax_AI · 2026-11-12
- Blender MCP adds World Labs Marble integration to generate 3D worlds inside Blender — sidahuj · 2026-11-12
- 99% AI-made music video: full toolchain from Claude to Suno v6 — LinusEkenstam · 2026-11-12
- Archive dig: 1967 'Computers and Automation' contest and the turning point of computer art — Merzmensch · 2026-11-12
- MiniMax H3 Image models launch on Picsart with 10-second 4K generation — MiniMax_AI · 2026-11-12