arXiv (All)
open access
Freeze What Is Settled, Cache What Is Smooth: Spatial Freezing Keeps Step Caching in Its Low-Error Regime
Instruction-based image editors built on diffusion transformers run tens of denoising steps. Training-free acceleration either reuses features across steps (step caching) or stops computing the regions an edit leaves untouched (region freezing), and the two have been combined before. We ask how a hi
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- Beyond Temporal Smoothing: Spatial Energy Budgets Stabilize One-Step Diffusion Editing#1117172
- Fixed State, Long Reach: What a Constant-Size Cache Buys Block Diffusion at Scale#999980
- Refinement Is Inherently Editable: Training-Free Prompt-to-Prompt Image Editing with Generative Refinement Network#1048811
- The Golden Path Hypothesis: Reusable Schedules in Diffusion Caching#1144310
- Frequency-Step Cache: Separating Synchronization and Repair for Efficient Autoregressive Video Diffusion#1327512
Record · ID 1457000
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive