Type a name, or just describe what you need. Results blend keyword and meaning-based search. 13 matches, each with an EU availability status.
Research
Research method that trains one-step image generators by matching feature distributions under frozen encoders.
Model · Nvidia
NVIDIA one-step refiner that upscales low-resolution generated video to up to 4K across different base video generators.
Model · ByteDance
ByteDance's open-weights one-step diffusion transformer for restoring and upscaling video and images.
Model
One- and two-step image generation model distilled from Z-Image-Turbo using text-stream adversarial distillation.
Research model for real-time, audio-driven talking-head video generation from a reference image, using one-step inference.
Research · ByteDance
ByteDance research method for few-step diffusion distillation, adding a one-line projection to the DMD update.
Model · ACE Studio
Open-source local music generation model with a 4B-parameter DiT decoder, extending ACE-Step 1.5 with higher audio quality.
Open-source diffusion-based music generation foundation model with lyric-aligned vocals and editing controls.
Research framework adding sole pressure-insole tactile sensing to humanoid locomotion policies, tested on Unitree G1.
Model · StepFun
StepFun's Step 5 Preview: a large MoE model (reported ~600B total, 27B active, 1M context) for coding and reasoning.
Open-weights multimodal flash model from StepFun for agentic tasks involving images, interfaces, web search and long runs.
8-step distillation LoRA for MOSS-Image-SFT that runs without CFG, for ComfyUI.
ByteDance and Texas A&M research method distilling image and video diffusion models into few-step generators adversarially.
