PixelDiT2: pixel-space diffusion matches latent SOTA with per-pixel control
CurieuxExplorer · x · 2026-11-07
PixelDiT2 is a new model that implements pixel-space diffusion efficiently, achieving nearly the same performance as state-of-the-art latent-space models while offering control over individual pixels — something latent diffusion struggles with. Relevant for fine-grained local editing and controllable generation.
More from Multimodal
- Local pipeline showcase: MiniMax H3 refMod generations from reference image to 4K upscale — edisson75 · 2026-11-13
- Gaussian splats may be the best way to capture how 3D displays like LKG Portrait look IRL — nptacek · 2026-11-13
- AI-generated 'not canon' clip of Schwarzenegger driving with Michael Jordan — alanskimp · 2026-11-13
- H3-Image API gotcha: server keeps billing on client timeout — set max_retries=0 — xiaohu · 2026-11-13
- MiniMax open-sources H3-Image: native 16MP output, up to 16 reference images — xiaohu · 2026-11-13
- Daily AI painting made with GPT-6 Images 2.6 shows painterly winter village — DeryaTR_ · 2026-11-13