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.
More from Multimodal
- Four imaginary tokens for Midjourney v8.2 produce memory ghosts and bone echoes — LudovicCreator · 2026-09-30
- Hyper-personalized music is BS: music is culture and inherently social, argues developer — jordiponsdotme · 2026-09-30
- NUS Proposes StoryEngine: A State-Grounded Agentic Framework for Coherent Long-Form Video Storytelling — NationalUniversityofSingapore · 2026-09-30
- One Year of Local Image Generation: Why Civitai and ComfyUI Both Fall Short — BenDLH · 2026-09-30
- Opus made a launch video for Violetto 1B in 50 minutes amid zero media coverage — tensorqt · 2026-09-30
- LoRA adapters break on distilled video models, long post explains why — burkov · 2026-09-30