InstantFusion: A Shared Latent Interface for Heterogeneous Image Generators
cs.CV
Submitted: 2026-10-09
Updated: 2026-10-15
Comments: 26 pages, 19 figures
Code: https://github.com/InternLM/InstantFusion
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Sources
- All Roads Lead to Rome? Exploring Representational Similarities Between Latent Spaces of Generative Image Models
- Z-Image: An Efficient Image Generation Foundation Model with Single-Stream Diffusion Transformer
- Flow-OPD: On-Policy Distillation for Flow Matching Models
- Any-OPD: Heterogeneous On-Policy Distillation for Flow-Matching Models via Representation-Space Bridging
- Poly-OPD: Heterogeneous Multi-Teacher On-Policy Distillation for Capability-Selectable Flow Models
- MiniLLM: On-Policy Distillation of Large Language Models
- D-OPSD: On-Policy Self-Distillation for Continuously Tuning Step-Distilled Diffusion Models
- GenEval 2: Addressing Benchmark Drift in Text-to-Image Evaluation
- DiffusionOPD: A Unified Perspective of On-Policy Distillation in Diffusion Models
- Flow Matching for Generative Modeling
- Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference
- Relative representations enable zero-shot latent space communication
- Cross-Space Distillation: Teaching One-Step Students with Modern Diffusion Teachers
- Progressive Distillation for Fast Sampling of Diffusion Models
- Consistency Models
- Score-Based Generative Modeling through Stochastic Differential Equations
- Qwen-Image Technical Report
- Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesis
- FlowInOne:Unifying Multimodal Generation as Image-in, Image-out Flow Matching
- Vision-OPD: Learning to See Fine Details for Multimodal LLMs via On-Policy Self-Distillation
Related papers
- Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
- AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
- Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
- MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
- TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
- A Survey on Efficient Vision-Language-Action Models