Marigold V2 repurposes diffusion Transformers for dense prediction, trainable on a single GPU in days
RexDouglass · x · 2026-09-14
- Marigold V2 adapts diffusion Transformers for dense prediction by finetuning Qwen-Image-Edit-2509 with 4-bit quantization and Rank-128 QLoRA.
- Estimates depth, normals, albedo and more in a single step.
- Training runs on a single GPU within days; video applications (with STeR) hinted at.
More from Multimodal
- Element Forge: open-source editable AI VFX for real footage in ComfyUI — zitroffell · 2026-10-30
- Claymation body horror on 8GB: three wrong settings, not the GPU, made local renders slow — roro9- · 2026-10-30
- AI-generated Haribo Starmix bean bag product shot looks like a real catalog page — Delahuntagram · 2026-10-30
- MiniMax LoRA creator ships open-source ComfyUI alternative to Higgsfield's Influencer Studio — infroy28 · 2026-10-30
- Scenario open-sources 3D OS: 80 agent skills taking sketches to game-ready assets — Scobleizer · 2026-10-30
- Open-source ComfyUI app reshoots footage keeping camera and framing, swapping scenes — 3dkvisual · 2026-10-30