FLUX 3 teaser hints at a multimodal generator with 20-second video clips
eyishazyer · x · 2026-07-23
Black Forest Labs’ apparent FLUX 3 teaser suggests a full multimodal generator with image, video, audio, and motion generation.
- The post says the model briefly surfaced as a preview and may be open if the usual pattern holds.
- It is described as supporting up to 20 seconds of video in a single generation.
- The author argues that, if released openly, it could give creators a major new capability boost.
More from Multimodal
- Open-source FableCut lets AI agents edit a real video timeline via remote MCP — FastPresence9799 · 2026-10-27
- Anima user struggles to keep generated lanterns in the distance via prompts — MadaleineSakurai · 2026-10-27
- MOSS-Image ecosystem roundup: sharpness slider, manga alpha LoRA, box inpainting — optimisticalish · 2026-10-27
- Wan2.2 image-to-video Space trends on Hugging Face — JCisHERE · 2026-10-27
- PlayCanvas' open-source splat-transform tool hits ~35K weekly NPM downloads — willeastcott · 2026-10-27
- Creator builds Snorricam video series with Seedance 2.5, sharing prompts — LudovicCreator · 2026-10-27