Flux 3 is rumored to add image, 20-second video, and reasoning support
mark_k · x · 2026-07-23
Flux 3 is reportedly coming today from @bflai, and the rumor is that it will be multimodal.
The claimed features include:
- image generation
- video generation up to 20 seconds
- reasoning
If true, it would be a notable expansion beyond still-image generation into longer-form video and multimodal reasoning.
Related event: Black Forest Labs Teases FLUX 3 with Multimodal Capabilities(2 posts)→
More from Multimodal
- Alibaba launches Qwen-Audio-3.0-TTS with 16 languages and 3-minute one-pass audio — Alibaba_Qwen · 2026-07-23
- Kling AI is said to handle close-up facial expressions better — burny_tech · 2026-07-23
- A reusable ChatGPT image prompt for a realistic portrait plus doodle-shadow twin — SimplyAnnisa · 2026-07-23
- Qwen-Image-3.0 aims for practical image generation, but still needs prompt tuning — 量子位 · 2026-07-23
- User showcases LTX 2.3 animations with a cinematic ogre-at-the-cake scene — Wise_Revolution385 · 2026-07-23
- MineExplorer shows top multimodal models collapse on long-horizon open-world tasks — 美团技术团队 · 2026-07-23