Black Forest Labs previews multimodal model Flux 3

// 1h agoMODEL RELEASE

Black Forest Labs previews multimodal model Flux 3

Black Forest Labs has previewed Flux 3, a unified multimodal foundation model designed to natively integrate image creation, audio synthesis, 720p video generation with up to 20 seconds of synchronized sound, and robotics action prediction. Early access features text-to-video, image-to-video, and keyframe transitions, with an open-weight community release planned.

// ANALYSIS

Unifying video generation, synchronized audio, and robotics action prediction into a single foundation model marks a major shift towards true cross-modal physical and generative AI intelligence.

* Combining audio and video generation natively eliminates secondary lip-syncing and sound design pipelines.

* Incorporating robotics action prediction signals a broader move from digital content creation into embodiment and real-world interaction.

* Extending video duration to 20 seconds at 720p resolution sets a strong benchmark for production-ready generative clips.

// TAGS

flux-3black-forest-labsmultimodalvideo-genaudio-genroboticsai

DISCOVERED

1h ago

2026-07-26

PUBLISHED

1h ago

2026-07-26

RELEVANCE

9/ 10

AUTHOR

AI Search

// KEEP READING

More AI developer news from the feed

EXPLORE FULL FEED

OPEN SOURCE1h ago

Homie brings multi-view consistency to AI video

Homie is an open-source reference-to-video framework designed to solve subject and object identity drift in AI video generation. By leveraging multi-view image inputs alongside multimodal intelligent guidance, Homie maintains consistent visual features and realistic physical interactions between subjects and objects across generated video frames.

MODEL1h ago

Microsoft releases Mage Flow 4B image model

Microsoft has released Mage Flow, an open-source 4-billion parameter model family designed for high-efficiency text-to-image synthesis and fine-grained editing. Combining a one-step latent tokenizer (Mage-VAE) with a Native-Resolution Multimodal Diffusion Transformer (NR-MMDiT), the MIT-licensed suite supports resolutions from 512 to 2048 pixels alongside sub-second Turbo variants.

MODEL5h ago

Inflect-Micro-v2 ships standalone 9.36M parameter TTS

Inflect-Micro-v2, released by developer Owen Song on Hugging Face, is an open-weight text-to-speech (TTS) model designed for efficient local execution. Packing a complete end-to-end speech generation pipeline into 9.36 million parameters (~37.5 MB FP32), it generates 24 kHz English speech directly on CPU or CUDA hardware without external vocoders.