T-DIG uses an LLM to control any text-to-image model without weight access
simi_97k · x · 2026-10-31
Researchers present T-DIG, an LLM that learns to control ANY text-to-image model—GAN or diffusion, open or closed source—without requiring access to the image model's weights. Users can request things like "varied backgrounds" and dial in how much variation they want, making hard-to-explore image generators controllable via natural language.
More from Research
- LLM judges harbor systematic errors that silently corrupt model rankings and training pipelines — burkov · 2026-10-31
- New paper quantifies ineffable concepts: 65 of 1,270 can never be taught to LLMs via language — sanmikoyejo · 2026-10-31
- Unsupervised Method Measures Whether LLM Messages Are Received — sanmikoyejo · 2026-10-31
- Neural net flies a drone in Acro mode from streamed game footage on a tiny board — yacineMTB · 2026-10-31
- llmlip-rs: Rust MLIP inference engine runs 6000-atom sims 17.7x faster than PyTorch MACE — CatAstro_Piyush · 2026-10-31
- AdaPRA: a process-reward agent with adaptive rubrics audits data science agents as they work — dan_fried · 2026-10-31