Diffusion Categories
Image Generation
321 models
ComfyUI Extensions
Extensions, nodes, and optimization tools for ComfyUI workflows including model integration, performance tuning, and specialized task implementations. Does NOT include general diffusion model training, standalone inference frameworks, or non-ComfyUI-specific tools.
245 models
Diffusion Model Frameworks
215 models
AI Image Generation Platforms
Full-stack web applications and platforms for generating images from text prompts, including user accounts, image galleries, credit systems, and community features. Does NOT include standalone image generation models, inference tools, editing software, or prompt engineering utilities.
207 models
Diffusion Model Implementations
Educational and foundational implementations of diffusion models across various frameworks and domains (PyTorch, C++, biomedical signals, 2D shapes). Does NOT include applications that primarily use pre-built diffusion models for specific tasks (image generation, segmentation, denoising) or domain-specific adaptations without emphasis on the core implementation.
205 models
Multimodal Conditioned Generation
Tools that generate images from non-text inputs (voice, speech, captions, parameters, specifications) or combine multiple input modalities to drive image generation. Does NOT include pure text-to-image, video generation, or image editing tools.
166 models
Image Generation Frameworks
Tools and libraries for programmatically generating images from code, templates, or structured data (React/HTML/canvas-based). Does NOT include standalone diffusion models, editing tools, or image manipulation software.
140 models
Video Editing Diffusion
Advanced video editing and manipulation using diffusion models, including motion control, composition, object editing, and frame interpolation. Does NOT include general video generation from text, basic inpainting tools, or video segmentation without editing capabilities.
135 models
Compositional T2I Generation
Tools for enhancing spatial reasoning, multi-concept composition, and fine-grained control in text-to-image diffusion models through architectural improvements and guidance techniques. Does NOT include general T2I generation, LoRA training, or personalization fine-tuning methods.
133 models
Image-to-3D Generation
Tools for generating 3D models, scenes, and reconstructions from 2D images using diffusion models. Includes single-image to 3D object generation, multi-view synthesis, scene reconstruction, and related 3D synthesis tasks. Does NOT include general 3D modeling, 2D image generation, or video generation.
129 models
SD WebUI Extensions
Extensions and plugins for AUTOMATIC1111's Stable Diffusion WebUI that add features, effects, and utilities (temporal processing, segmentation, pose control, regional editing, zoom effects, etc.). Does NOT include standalone WebUI forks, theme/UI modifications, or tools for other diffusion interfaces like ComfyUI.
122 models
Computational Imaging Diffusion
Diffusion models applied to specialized imaging tasks including medical image segmentation/reconstruction, computational imaging (CT, spectral imaging, RAW), and domain restoration (deconvolution, rolling shutter). Does NOT include general image generation, super-resolution as primary task, or text-conditional applications.
111 models
Diffusion Deployment Serving
Tools for serving, deploying, and operationalizing diffusion models (APIs, containers, frameworks). Does NOT include model training, fine-tuning, or research implementations of novel diffusion architectures.
106 models
Diffusion Deployment Infrastructure
Tools and configurations for deploying diffusion models in containerized environments (Docker, Kubernetes) and cloud platforms (AWS, RunPod, Jetson). Includes setup guides, infrastructure-as-code, and GPU optimization. Does NOT include model training, fine-tuning, or user-facing applications beyond basic WebUI deployment.
103 models
Diffusion Web Interfaces
Web applications and UI frontends for running diffusion models locally or remotely, emphasizing interactive exploration, parameter tuning, and real-time generation. Does NOT include model training, infrastructure/compute sharing, or specialized domain applications (music, 3D, video editing handled elsewhere).
89 models
Image-to-Image Translation
Tools for translating images between domains, styles, or paired/unpaired datasets using GANs and neural networks. Does NOT include text-guided editing, style transfer as a standalone service, or general image generation from scratch.
77 models
Style Transfer Diffusion
Tools for transferring, enhancing, or manipulating artistic styles, colors, and visual attributes using diffusion models. Does NOT include general image generation, video synthesis, or style analysis without generative capability.
76 models
Multi-Modal AI Assistants
Unified chat and content creation platforms that integrate multiple AI capabilities (LLMs, image generation, video creation) through a single interface. Does NOT include specialized tools for individual tasks, API wrappers without UI, or model-specific implementations.
69 models
Diffusion Sampling Inference
Advanced sampling algorithms, inference optimization, and acceleration techniques for diffusion models including distillation, trajectory optimization, and exact inversion methods. Does NOT include application-specific implementations, downstream task adaptations, or training methodologies.
68 models
GAN Architectures Implementations
Educational implementations and benchmarks of core GAN variants (Vanilla GAN, DCGAN, WGAN-GP, etc.) for image generation. Does NOT include diffusion models, VAEs, style transfer as primary focus, or production deployment tools.
67 models
ONNX Runtime Inference
Cross-platform inference implementations of diffusion models using ONNX Runtime across C#, C++, Java and web frameworks. Does NOT include training tools, UI frameworks, or model conversion utilities—only optimized runtime inference engines.
64 models
Colab Notebook Implementations
Ready-to-run Google Colab notebooks for diffusion models and related tasks, requiring minimal setup or code knowledge. Includes pre-configured notebooks for image/video generation, fine-tuning, and inference. Does NOT include standalone applications, libraries meant for local installation, or tutorials without executable notebook implementations.
64 models
Prompt Optimization Extensions
WebUI extensions and tools for refining, managing, testing, and analyzing prompts in Stable Diffusion workflows. Includes prompt syntax highlighting, generation, post-processing, tokenization visualization, and prompt management. Does NOT include prompt engineering methodologies, general prompt databases, or non-WebUI prompt tools.
59 models
GAN-Based T2I
GAN implementations for text-to-image synthesis using adversarial training (StackGAN, DCGAN, conditional GANs). Does NOT include diffusion-based text-to-image, evaluation metrics, or non-generative synthesis methods.
57 models
Video Diffusion Models
Curated collections, surveys, and benchmarks for diffusion-based video generation, editing, and synthesis tasks. Does NOT include low-level vision processing, general image diffusion, or non-diffusion video generation methods.
56 models
Diffusion Adversarial Robustness
Tools for adversarial attacks, defenses, and robustness evaluation of diffusion models, including unlearning, poisoning resistance, and safety-driven model hardening. Does NOT include general model evaluation, watermarking, or domain adaptation techniques.
56 models
Text-to-Image Wrappers
Simple wrapper applications and web interfaces that integrate existing text-to-image APIs (OpenAI, Stability AI, etc.) without implementing core diffusion models. Does NOT include custom model implementations, fine-tuning tools, or advanced features like face-swapping or style transfer.
54 models
Diffusion RLHF Alignment
Tools and methods for aligning diffusion models using reinforcement learning and human feedback, including preference optimization, reward modeling, and RLHF fine-tuning techniques. Does NOT include general diffusion model training, inference optimization, or non-RL-based fine-tuning methods like LoRA.
53 models
3D Object Generation
51 models
T2I Evaluation Benchmarks
Benchmarks, datasets, and metrics for evaluating text-to-image generation quality and alignment. Does NOT include tools for generating images, training models, or prompt optimization.
50 models
Speech Synthesis Diffusion
Diffusion models for speech and audio generation including TTS, voice conversion, singing synthesis, and vocoding. Does NOT include general image diffusion, music generation without speech focus, or non-diffusion audio processing.
50 models
LoRA Training Tools
Tools and frameworks for fine-tuning diffusion models using LoRA (Low-Rank Adaptation) techniques, including trainers, preprocessors, and GUIs. Does NOT include inference tools, deployment utilities, or general model fine-tuning methods outside the LoRA adapter paradigm.
47 models
Flux Model Tools
Tools, wrappers, and applications built specifically around Flux diffusion models for image generation and editing. Does NOT include general text-to-image generation tools, LoRA training frameworks, or non-Flux model implementations.
44 models
Text-to-Image Generation
Tools and implementations for generating images from text prompts using diffusion models, GANs, or CLIP-guided approaches. Does NOT include image editing tools, inpainting, video generation, or evaluation benchmarks.
43 models
Molecular Structure Generation
Diffusion models for generating 3D molecular structures, materials, and chemical compounds with equivariance constraints and physics-informed priors. Does NOT include general graph generation, protein folding, or text-to-molecule without structural focus.
42 models
Discord Image Generation Bots
Discord bots that generate images from text prompts using Stable Diffusion or similar models. Does NOT include non-Discord applications, image editing tools, model training frameworks, or bots focused on other generative tasks (text, audio, video).
41 models
Gan Image Generation
40 models
Image Gallery Managers
Tools for organizing, browsing, searching, and displaying AI-generated images locally with metadata extraction and analysis capabilities. Does NOT include image generation, editing, or evaluation/comparison voting interfaces.
40 models
Medical Image Diffusion
Diffusion models applied to medical imaging tasks including segmentation, synthesis, generation, and disease progression modeling of brain MRI, tumors, and histopathology. Does NOT include general medical AI, non-diffusion medical image processing, or non-medical image applications.
40 models
Low Light Image Restoration
36 models
Interactive Image Editing
Tools for pixel-level image manipulation through direct interaction methods (dragging, masking, region selection, prompting) that preserve content fidelity. Does NOT include general text-to-image generation, video editing, or style transfer without spatial control.
34 models
DALL-E Playground Apps
Self-contained web and desktop applications built around OpenAI's DALL·E API for interactive image generation. Does NOT include DALL·E wrappers/libraries, general text-to-image tools using other models, or prompt engineering utilities.
34 models
Diffusion Trajectory Planning
Tools for motion planning, trajectory optimization, and autonomous control using diffusion models. Includes applications to robotics, autonomous driving, and multi-agent coordination. Does NOT include general image/video generation or reinforcement learning without explicit trajectory planning focus.
32 models
Nano Banana Tools
Specialized tools, editors, and integrations for Nano Banana image generation models (Gemini-based). Includes UI applications, prompt collections, API SDKs, and skill implementations. Does NOT include general text-to-image tools, other diffusion models, or non-Nano-Banana-specific AI frameworks.
32 models
Text-Guided Inpainting
Tools for selectively replacing, editing, or regenerating masked regions of images using text descriptions and diffusion models. Does NOT include general image generation, semantic segmentation tools, or face-specific applications like deepfakes.
32 models
Flow Matching Models
Implementations and variants of flow matching generative models for image, video, motion, and physics synthesis. Does NOT include general diffusion models, score-based methods, or non-generative flow-based architectures like normalizing flows for density estimation.
31 models
Score-Based Generative Models
Theoretical implementations and research of score-based diffusion models, including SDE formulations, training objectives (score matching, ELBO), and foundational algorithmic variants. Does NOT include application-specific models, inference optimizations, or domain-specific adaptations (use medical-image-diffusion, molecular-structure-generation, etc. instead).
31 models
Image Restoration Diffusion
Diffusion-based methods for restoring degraded images (deblurring, denoising, inpainting, artifact removal, underwater/medical imaging). Does NOT include general image generation, style transfer, or image-to-image translation without restoration objectives.
30 models
Text-to-Video Generation
Tools for generating videos from text prompts, scripts, or descriptions using AI models. Includes short-form video automation, video synthesis pipelines, and end-to-end video production platforms. Does NOT include video editing tools, video enhancement, music generation, or general video processing without generative AI.
30 models
Telegram Image Bots
Telegram bot implementations for AI image generation and manipulation. Includes bots that interface with diffusion models, style transfer, and image generation APIs through Telegram's chat interface. Does NOT include non-Telegram chat platforms, standalone image generation tools, or bots without image generation as primary function.
29 models
Virtual Try-On
Tools for generating photo-realistic images of clothing and fashion items on people or models using diffusion models. Includes virtual try-on, try-off, garment transfer, and fashion visualization. Does NOT include general fashion design tools, sketch-to-image translation, or AR preview systems without generative AI.
27 models
Image Inpainting
26 models
Stable Diffusion Implementations
26 models
AI Skill Integrations
Skills and plugins that extend Claude Code, Cursor, and similar IDEs with AI generation capabilities (images, video, audio, text). Does NOT include standalone models, inference frameworks, or tools designed for direct image/video creation outside of IDE environments.
25 models
Variational Autoencoders
Tools and implementations of VAEs and related latent-space generative models (WAEs, etc.) for image generation. Does NOT include GANs, diffusion models, or other non-autoencoder generative architectures.
25 models
DreamBooth Fine-Tuning
Implementations and frameworks for personalizing diffusion models through DreamBooth fine-tuning on custom image sets. Does NOT include general model fine-tuning, LoRA training tools, or inference optimizations without subject personalization focus.
24 models
3D Scene Reconstruction
22 models
Image Denoising Networks
22 models
Computer Vision Learning
Educational repositories and implementation guides for core computer vision and deep learning models (CNNs, Vision Transformers, GANs, autoencoders, segmentation). Does NOT include production tools, inference frameworks, or domain-specific applications like autonomous driving or medical imaging.
22 models
AI Story Generation
Tools that generate complete narratives (text + visuals + audio) into illustrated or animated stories, often personalized for children. Does NOT include general text-to-image, video generation, or comic/animation tools without story narrative focus.
21 models
Face Generation GANs
Tools and implementations for generating synthetic face images using GANs and related generative models. Includes face synthesis from scratch, conditional face generation, and anime/stylized face generation. Does NOT include face detection, recognition, deepfakes, or AI-generated image detection.
21 models
Diffusion Language Models
18 models
AI Marketing Automation
End-to-end platforms and workflows that automate marketing content creation, campaign generation, and deployment across multiple channels (social media, ads, blogs) using AI. Does NOT include standalone image/video generation tools, prompt engineering utilities, or individual diffusion model implementations.
17 models
Multimodal Vision Language
16 models
ControlNet Tools
Tools for training, fine-tuning, deploying, and applying ControlNet models to images and videos for conditioned generation. Includes ControlNet variants, conditioning strategies, and optimization techniques. Does NOT include general diffusion model training, prompt engineering, or non-ControlNet conditioning methods.
14 models
Character Motion Animation
13 models
Neural Radiance Fields
12 models
Binding Affinity Prediction
11 models
Mixup Augmentation Frameworks
11 models
Vision Transformer Optimization
8 models
Game Playing Agents
8 models
Cartoon Style Transfer
8 models
Video Frame Interpolation
7 models
Monocular Depth Estimation
7 models
Neural Style Transfer
6 models
Medical Image Registration
6 models
3D Vision Transformers
6 models
Anomaly Detection Systems
6 models
Grayscale Image Colorization
5 models
Gaussian Splatting Rendering
5 models
Domain Adaptation Frameworks
5 models
Stable Diffusion Tools
4 models
Clip Vision Language
4 models
Human Pose Estimation
4 models
Neural Differential Equations
3 models
Knowledge Distillation Frameworks
3 models
Visual Slam Systems
3 models
Image Prompt Engineering
3 models
Comfyui Node Extensions
3 models
Causal Inference Ml
3 models
Multimodal Search Engines
2 models
Fastspeech Tts Models
2 models
Image Super Resolution
2 models
Audio Noise Reduction
2 models
Deepfake Detection Systems
2 models
Molecular Structure Design
2 models
Multi View Clustering
2 models
Vision Language Models
2 models
Nlp Paper Repositories
2 models
Uncertainty Quantification Deeplearning
2 models
Wireless Signal Processing
2 models
Variational Autoencoder Implementations
2 models
Text To Image Applications
2 models
Synthetic Data Generation
2 models
Normalizing Flows Pytorch
2 models
Neural Data Compression
2 models
Face Swapping Tools
2 models
Backdoor Attack Defenses
2 models
Knowledge Distillation Compression
2 models
Data Augmentation Techniques
2 models
Optimal Transport Ml
2 models
Ml Robustness Frameworks
2 models
Trajectory Prediction Ml
2 models
Medical Image Segmentation
2 models
Chemical Property Ml
1 models
Text To Speech Frameworks
1 models
Robotics Control Optimization
1 models
Transformer Interpretability Mechanistic
1 models
Ai Children Storytelling
1 models
Variational Autoencoders Nlp
1 models
Llm Compression Optimization
1 models
Ai Video Generation
1 models
Nano Gpt Variants
1 models
Point Cloud Processing
1 models
Self Supervised Learning
1 models
Generative Ai Learning Projects
1 models
Semantic Segmentation Techniques
1 models
Llm Implementation Tutorials
1 models
Gpt Multilingual Training
1 models
Vision Language Instruction Tuning
1 models
Uncategorized
1 models
Neural Vocoder Implementations
1 models
Neural Architecture Search
1 models
Audio Music Learning
1 models
Safety Robustness Evaluation
1 models
Unet Segmentation Pytorch
1 models
Adversarial Attack Frameworks
1 models
Healthcare Rag Systems
1 models
Gpt Model Fine Tuning
1 models
Graph Language Models
1 models
Llm Fine Tuning
1 models
Continual Learning Frameworks
1 models
Julia Ml Frameworks
1 models
State Space Model Architectures
1 models
Model Confidence Calibration
1 models
Personal Llm Companions
1 models
Rag Starter Projects
1 models
Gaussian Process Frameworks
1 models
Handwritten Text Recognition
1 models
Person Reidentification Datasets
1 models
Protein Engineering Design
1 models
Semantic Segmentation Models
1 models
Fashion Recommendation Systems
1 models
Aerial Robot Reinforcement Learning
1 models
Llm Reasoning Research
1 models
Clinical Llm Tools
1 models
Fashion Mnist Classification
1 models
Mixture Of Experts Llms
1 models
Graph Neural Networks
1 models
Autonomous Driving Projects
1 models
Dimensionality Reduction Techniques
1 models
Clinical Code Embeddings
1 models