T-DIG policies zero-shot transfer, beat GPT-5.5 prompt expansion on diversity
simi_97k · x · 2026-10-28
T-DIG requires no access to image-model weights, so policies trained on open models transfer zero-shot to proprietary ones. TPIPSv gains over i.i.d.: Qwen-Image policy +0.27 (GPT Image 2) / +0.20 (Gemini 3.1 Flash Image); FLUX.2[klein] +0.26/+0.19; SD3.5 L +0.23/+0.17 — all beating proprietary LLM prompt expansion via GPT-5.5 (+0.19) and Gemini 3.8 Flash (+0.15).
Related event: T-DIG Policy Transfers Zero-Shot to Boost GPT Image 2 and Gemini Diversity(2 posts)→
More from Multimodal
- AI band Techhalla reimagines Slipknot's 'Wait and Bleed' as a 1971 soul performance — Mother-Pear-2392 · 2026-10-28
- Inside the Hailuo H3 Max retro-MV workflow: 15-second chunks, one reference image, multi-shot prompts — techhalla · 2026-10-28
- Open-source pipeline turns Seedance AI video into real PBR textures on your 3D mesh — OdinLovis · 2026-10-28
- AI-generated cyberpunk short 'VHS Sirens' shows off consistent characters and neon city detail — brythehuman · 2026-10-28
- First-time creator makes full animated music video with 40 clips via MiniMax H3 — Capable-Insurance-58 · 2026-10-28
- Midjourney sref combo 138606468+1306896884 yields textured flat illustration — sergeantsref · 2026-10-28