Type a name, or just describe what you need. Results blend keyword and meaning-based search. 9 matches, each with an EU availability status.
Model · Nvidia
NVIDIA pixel-diffusion decoder that turns latents into 2K–4K images, replacing VAE decode plus a separate upscaler.
Model
Pixel-space text-to-image diffusion model transferred from latent diffusion models, without a VAE, supporting 4K output.
Rank-asymmetric flow method for pixel-space image generation, incl. AsymFLUX.2 klein finetuned from FLUX.2 klein 9B.
Library
Training-free staged sampling method that speeds up pretrained flow-matching text-to-image diffusion models.
Research · ByteDance
ByteDance research method for post-training image diffusion models using on-policy self-distillation from reward signals.
Feed-forward single-image relighting model with physically based light control, using intrinsic conditioning from a coarse 3D scene.
Diffusion model from Speridlabs that turns a single image into a 3D Gaussian splat object at adjustable detail levels.
Model · Linum AI
2B-parameter pixel-space text-to-image diffusion model from Linum AI, trained from scratch for about $21K; Apache 2.0.
Nvidia research model that understands and generates images and video directly in pixel space, with no VAE or vision encoder.
