T-DIG ships full release: paper, code, demo, and first text-conditioned image diversity dataset
simi_97k · x · 2026-10-28
Resource roundup for T-DIG by author Simran Khanuja (CMU), crediting collaborators Rohit Gandikota, Gaurav Parmar, and Graham Neubig, and noting the project only became feasible once the TPIPS eval metric was released.
Included resources: project website, paper, code, data & models, policies page, a live demo, and a results gallery. The framework trains an LLM policy with GRPO to write axis-conditioned prompts/edit instructions for frozen text-to-image models, enabling user-controllable batch image diversity.
Related event: CMU Open-Sources T-DIG: Text-Conditioned Diversity for Image Generation(7 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