Bridging Diffusion Pruning and Step Distillation with Teacher-Aligned Repair
Diffusion models generate high-quality images, but their inference cost comes from two sources: large denoising networks and repeated denoising steps. Existing compression pipelines usually attack these costs separately. Pruning reduces the network, but most pruning methods still rely on a long post-pruning retraining stage to recover a many-step sampler. Step distillation reduces the number of denoising steps, but it usually assumes a student that can already follow the teacher well enough to receive useful distillation gradients. This paper asks whether post-pruning retraining can be replace
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- FuzzySimilar title/name (fuzzy) · 59%stabilityai/stable-diffusion-xl-base-1.0 →
“Fuzzy title match (0.73): “Bridging Diffusion Pruning and Step Distillation with Teache” ≈ “stabilityai/stable-diffusion-xl-base-1.0””
- FuzzySimilar title/name (fuzzy) · 59%CompVis/stable-diffusion-v1-4 →
“Fuzzy title match (0.73): “Bridging Diffusion Pruning and Step Distillation with Teache” ≈ “CompVis/stable-diffusion-v1-4””
- FuzzySimilar title/name (fuzzy) · 59%stabilityai/stable-diffusion-3.5-large →
“Fuzzy title match (0.73): “Bridging Diffusion Pruning and Step Distillation with Teache” ≈ “stabilityai/stable-diffusion-3.5-large””
- LinkedLinked via arxiv author · 85%Jincheng Ying →
“Bridging Diffusion Pruning and Step Distillation with Teacher-Aligned Repair”
- LinkedLinked via arxiv author · 85%Li Wenlin →
“Bridging Diffusion Pruning and Step Distillation with Teacher-Aligned Repair”
- LinkedLinked via arxiv author · 85%Minghui Xu →
“Bridging Diffusion Pruning and Step Distillation with Teacher-Aligned Repair”
- LinkedLinked via arxiv author · 85%Yinhao Xiao →
“Bridging Diffusion Pruning and Step Distillation with Teacher-Aligned Repair”
- FuzzyOverlapping authors or contributors · 62%sgl-project/sglang →
“Shared author/contributor keys: ying”