Creator builds temporally coherent AI depth-of-field on Marigold V2, fixing chronic flicker

AntonObukhov1 · x · 2026-09-30

Creator @breakdownart shared a first serious fine-tune based on Anton Obukhov's team's Marigold V2. AI-generated depth of field has historically lacked detail and temporal coherence; Marigold V2 solved detail, and he set out to fix coherence.

Training route: targeted passes targeting large-scale morphing and flicker first, then boundary/edge detection, finally reintroducing detail using Marigold V2's Sink Loss technique. The result, while imperfect, is a clear step up; he plans to expand a personal library of high-quality CGI/photo assets. Obukhov voiced appreciation for the community adoption.

Original post →

More from Multimodal

Multimodal channel →