SenseNova U1.5-Lite full release: expert training, OPD distillation, one model at inference
英文标题：SenseNova U1.5-Lite full release: expert training, OPD distillation, one model at inference
Benchmarks: Benchmark U1 Preview Full Qwen-Image-Bench 47.14 55.20 (PE) 60.18 (PE) ImgEdit 3.9 4.37 4.59 GEdit-Bench-EN 7.47 8.14 8.26 Instead of just scaling up, they train task-specialized expert models for text rendering and infographics, aesthetic quality, and image editing. The
打开原文相关 4 · 机会 0
中文
Benchmarks: Benchmark U1 Preview Full Qwen-Image-Bench 47.14 55.20 (PE) 60.18 (PE) ImgEdit 3.9 4.37 4.59 GEdit-Bench-EN 7.47 8.14 8.26 Instead of just scaling up, they train task-specialized expert models for text rendering and infographics, aesthetic quality, and image editing. The
中文全文翻译正在补齐，可先查看下方英文原文。
English / 原文
Benchmarks: Benchmark U1 Preview Full Qwen-Image-Bench 47.14 55.20 (PE) 60.18 (PE) ImgEdit 3.9 4.37 4.59 GEdit-Bench-EN 7.47 8.14 8.26 Instead of just scaling up, they train task-specialized expert models for text rendering and infographics, aesthetic quality, and image editing. The