AI Paper Atlas

Research map / Image generation / Text-to-image diffusion

DICE: Distilling Classifier-Free Guidance into Text Embeddings

Zhenyu Zhou, Defang Chen, Can Wang, Chun Chen, Siwei Lyu

AAAI 2026 · Image generation › Text-to-image diffusion · approach: Compositional text-to-image guidance · 3 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
sharpen text embeddings with lightweight sharpener (CFG-distilled)unguided SD15 sampling · MS-COCOFID: 32.80 -> 22.22Improved
sharpen text embeddingsunguided SDXL · MS-COCOFID: 61.19 -> 28.01Improved
sharpen text embeddingsunguided Pixart-α · MS-COCOCLIP score: 25.30 -> 29.51Improved
sharpen text embeddingsunguided DreamShaper · MS-COCOFID: 24.17 -> 30.36No clear effect
naive scaling of text embeddings instead of learned sharpener (ablation)unguided sampling · MS-COCOCLIP score: 21.99 -> 22.89 (SD15, vs DICE 28.54)No clear effect
DICE versus GD on SD15DICE · MS-COCOFID: 23.54 -> 22.22Improved
sharpen padding embedding versus semantic embedding (ablation)DICE · qualitativeimage quality: cosine similarity 0.23 (padding) vs 0.75 (semantic)Improved
DICE versus guided samplingDICE · MS-COCO (SDXL)CLIP score: 32.10 -> 30.63Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy