Arbor uses hull, avoidance, and touch regions as native 3D control interfaces to guide latent generation.
The model uses a new dataset of 20,774 clips and a Motion Adapter to ensure view-consistent video generation.
A 201M-parameter SemanTok AR model matches or outperforms a VideoFlexTok AR model 3.4x its size.
Stable-Layers fine-tunes an image layer decomposition model without paired data through reinforcement learning that leverages feedback from a VLM.
**OCTOPUS**, which maximizes transformer KV Cache compression performance by combining octahedral parameterization with joint quantization, has been released.
Released Stable Audio 3, a fast latent diffusion model for variable-length audio generation and editing.
Foley Control attaches only a small video cross-attention to a frozen T2A model to learn video synchronization.
It generates consistent PBR materials and normals from a single image to support relighting.
By combining Reservoir Sampling with SWD, it reduces high-variance estimation and unstable gradients.
By dividing professional video generation into 4 control axes, it exposed the limitations of 10+ models.
AI in music is expanding into a co-creation tool, medium, and performance format.
SD3.5-Flash is a lightweight distillation framework that produces high-quality images in just a few steps.
SP4D generates RGB and kinematic part videos together from a single-view input.
By finding material embeddings in CLIP-space, it implements material blending and fine-grained attribute control.
ARC post-training generates 12 seconds of 44.1kHz stereo audio in 75ms on an H100.
It generates 4D face avatars with multi-view consistency and expressions from just a single image.
SV4D 2.0 is a Multi-View Video Diffusion model that generates high-quality dynamic 3D assets by enhancing spatio-temporal consistency.
SD3-Turbo, which generates high-resolution images with just 4 sampling steps, was introduced through LADD technology.
Stable Virtual Camera is a general-purpose diffusion model that generates highly consistent multi-view videos through 3D camera control.
SPAR3D leverages a point diffusion model to reconstruct high-precision 3D objects from a single image in just 0.7 seconds.
SF3D reconstructs a high-quality 3D mesh with UV unwrapping and light disentanglement from a single image in just 0.5 seconds.
SV4D is a unified diffusion model that generates dynamic 3D content from a single video while maintaining multi-frame and multi-view consistency.
Stable Audio Open, an open-weight text-to-audio model trained on Creative Commons data, has been released.
Moving beyond the aesthetic limitations of existing 3D generative AI, this work proposes developing models that reflect physical constraints necessary for actual fabrication.
AI Briefing