Scaling Properties of Text Conditioning in Visual Generation
We study empirical scaling properties for text conditioning in visual generation. Such properties have rarely been measured because diffusion loss does not scale with the number of tokens in natural-language prompts. Surprisingly, we find that the converged diffusion loss scales with the amount of structured language in the prompt. To quantify structured language, we adapt two complementary measures: a white-box likelihood metric (GPG) and a black-box attribute metric (ED). Across controlled training runs, the converged diffusion loss decreases approximately linearly with GPG and follows a power law with ED. Guided by these scaling properties, we improve \emph{diffusability} by constructi...
| Authors | Zilong Chen, Chaorui Deng, Kunchang Li et al. |
|---|---|
| Primary category | cs.CV |
| Published | 31 July 2026 |
| Last updated at source | 31 July 2026 |
Connected in the knowledge graph
- heheyas/Qwen-Image-SPModel · cited by
Models and datasets referencing this paper
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.