Black Forest Labs (BFL), a company founded by former Stability AI researchers, has released its new image and video generation model, Flux 3. The model is trained on a combination of still images, video, and audio to develop a more comprehensive visual intelligence. This approach aims to improve temporal consistency and object understanding, as demonstrated by examples like a horse in motion and a person being panned around. BFL's work is inspired by the potential seen in models like Stable Diffusion, with a focus on efficient training and practical applications, including restoring old family photos. AI
IMPACT Sets a new direction for multimodal AI training by integrating audio and video, potentially improving object understanding and temporal consistency.
RANK_REASON New model release from a notable AI lab (BFL, spun out from Stability AI). [lever_c_demoted from frontier_release: ic=1 ai=1.0]
- Andreas Blattmann
- Black Forest Labs
- Deepgram
- Dustin Podell
- Flux 3
- FLUX 3 Video
- Latent diffusion model
- Stability AI
- Stable Diffusion
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →