⚡ 923 h early
D-OPSD diffusion self-distillation paper
D-OPSD: On-Policy Self-Distillation for Continuously Tuning Step-Distilled Diffusion Models
3 experts across 2 network communities independently surfaced this.
3 experts
2 communities
1 sources clustered
“D-OPSD transforms training for step-distilled diffusion models, enabling on-policy self-distillation to learn new concepts without sacrificing efficient few-step inference. This enhances image quality and response speed for AI-generated content. https://arx…”
“absolutely goated paper for anyone working with distilled diffusion models lately: arxiv.org/abs/2605.05204”