awesome-conditional-diffusion-models
github.com/zju-pi/awesome-conditional-diffusion-models ↗This repository maintains a collection of important papers on conditional image synthesis with diffusion models (Survey Paper published in TMLR2025)
193
GitHub Stars
160
Curated Resources
2
Categories
2 hours ago
Last Refreshed
Condition Integration in Denoising NetworksCondition Integration in the Sampling Process
Use this list with your AI agent
Add the Context Awesome MCP server to Claude, Cursor, or any MCP client, then ask:
"Show me condition integration in the re-purposing stage resources from awesome-conditional-diffusion-models"
Installation instructions →What's inside
Condition Integration in Denoising Networks
- Adding conditional control to text-to-image diffusion modelsCondition Integration in the Re-purposing Stage
Visual signal to image
- A morphology focused diffusion probabilistic model for synthesis of histopathology imagesCondition Integration in the Training Stage
Medical image synthesis
- An image is worth one word: Personalizing text-to-image generation using textual inversionCondition Integration in the Specialization Stage
Customization
- A novel unified conditional scorebased generative framework for multi-modal medical image completionCondition Integration in the Training Stage
Medical image synthesis
- Anydoor: Zero-shot object-level image customizationCondition Integration in the Re-purposing Stage
Image composition
- Blip-diffusion: pre-trained subject representation for controllable text-to-image generation and editingCondition Integration in the Re-purposing Stage
Customization
Condition Integration in the Sampling Process
- Add-it: Training-Free Object Insertion in Images With Pretrained Diffusion ModelsAttention Manipulation
Image editing
- A latent space of stochastic diffusion models for zero-shot image editing and guidanceInversion
Image editing
- An edit friendly ddpm noise space: Inversion and manipulationsInversion
Image editing
- Blended diffusion for text-driven editing of natural imagesGuidance
Image restoration
- Classifier-free diffusion guidanceNoise Blending
/
- Come-closer-diffuse-faster: Accelerating conditional diffusion models for inverse problems through stochastic contractionConditional Correction
Image restoration
Showing a sample of 160 resources. View the full list on GitHub →