REPA-G accepted at NeurIPS: training-free test-time conditioning for REPA-style diffusion
abursuc · x · 2026-10-10
The REPA-G paper has been accepted at NeurIPS and will be presented at the Paris site. It introduces test-time conditioning of REPA-style diffusion models with visual features, requiring no extra training.
More from Multimodal
- SGLang-Diffusion serving framework for diffusion models to be unveiled at PyTorch Conference 2026 — PyTorch · 2026-10-10
- image-blaster repo turns a single photo into a fully explorable 3D world in five minutes — anthara_ai · 2026-10-10
- MoMA commissions Holly Herndon and Mat Dryhurst for dual-venue AI art show — matdryhurst · 2026-10-10
- Open-source creative harness Voyager adds 8 languages, drives Blender, Resolve and 100+ tools — ravisparikh · 2026-10-10
- Full AI video made at home on a single RTX 3090 with Qwen, FLUX, MiniMax and YuE2 — solyarisoftware · 2026-10-10
- Building Blender Scenes Entirely With AI, Without Ever Touching Blender — RexDouglass · 2026-10-10