Z-Erase: Enabling Concept Erasure in Single-Stream Diffusion Transformers
Z-Erase: Enabling Concept Erasure in Single-Stream Diffusion Transformers explores A novel framework for stable concept erasure in single-stream text-to-image diffusion models, overcoming generation collapse and achieving state-of-the-art performance.. Commercial viability score: 7/10 in Generative Image Safety.
BUILDER'S SANDBOX
Build This Paper
Use an AI coding agent to implement this research.
OpenAI CodexAI Agent
Lightweight coding agent in your terminal.
Claude CodeAI Agent
Agentic coding tool for terminal workflows.
AntiGravity IDEScaffolding
AI agent mindset installer and workflow scaffolder.
CursorIDE
AI-first code editor built on VS Code.
VS CodeIDE
Free, open-source editor by Microsoft.
Recommended Stack
Startup Essentials
Estimated $9K - $13K over 6-10 weeks.
See exactly what it costs to build this -- with 3 comparable funded startups.
7-day free trial. Cancel anytime.
Discover the researchers behind this paper and find similar experts.
7-day free trial. Cancel anytime.
Related Papers
- Builds On ThisLocalized Concept Erasure in Text-to-Image Diffusion Models via High-Level Representation MisdirectionViability: 5.0
- Builds On ThisTINA: Text-Free Inversion Attack for Unlearned Text-to-Image Diffusion ModelsViability: 5.0
- Prior WorkPrototype-Guided Concept Erasure in Diffusion ModelsViability: 7.0
- Prior WorkNeighbor-Aware Localized Concept Erasure in Text-to-Image Diffusion ModelsViability: 7.0
- Prior WorkPROBE: Diagnosing Residual Concept Capacity in Erased Text-to-Video Diffusion Models