Marigold V2 launches at SIGGRAPH Asia 2026: sharp diffusion-transformer depth estimation
AntonObukhov1 · x · 2026-09-09
Anton Obukhov announced Marigold V2, accepted to SIGGRAPH Asia 2026.
- V1 recap: Marigold post-trains an image generator into a depth estimator on a single GPU — an accessible research recipe.
- V2 upgrade: the backbone moves to a diffusion transformer (DiT), producing very sharp edges with stronger versatility.
Paper, code, weights, and a demo are all available, and the author has shared a low-cost fine-tuning path (4-bit quantization + QLoRA on one consumer GPU).
Related event: Marigold V2 Released: Single-GPU Fine-tuned DiT for Depth Estimation(5 posts)→
More from Multimodal
- Seedance 2.5 lands in CapCut desktop with 30-second generations and bulk editing — future_coded · 2026-09-09
- Combining two Seedance 2.5 prompt techniques for continuous shots and multi-cut sequences — techhalla · 2026-09-09
- 100 rule-based verifiers and 300 tasks: team builds a working RL recipe for video models — DanielKhashabi · 2026-09-09
- H3 MAX as a rendering engine? Demo promised with the right prompting — gorkem · 2026-09-09
- Gradium launches Voice Design: prompt-to-voice generation, free in API and Studio — ThePeterMick · 2026-09-09
- Making a self-correcting walking robot in Spline with GPT 6 Astra — dunkhippo33 · 2026-09-09