Rui CarmoThis page is a collection of notes and links related to AI image generation technologies, including Stable Diffusion, DALL-E, Midjourney, and other generative image models that have become prominent in the modern AI space.
Resources
| Field | Category | Date | Link | Notes |
|---|---|---|---|---|
| 3D Rendering | NeRF Tools | 2022 | nerfstudio | A tool for manipulating Neural Radiance Fields (NeRF) and rendering the scenes out as video |
| General | Tools | 2024 | upscayl | an AI-based image upscaler |
| Generative AI | 3D Asset Models | 2025 | Hunyuan3D-2 | a 3D textured asset generation model |
| Diffusion Models | miniDiffusion | a minimalistic implementation of diffusion models in Python |
||
| Frame Prediction | FramePack | a next-frame (next-frame-section) prediction neural network structure that generates videos progressively. |
||
| Image Generation Models | Lumina-Image-2.0 | Another image generation model |
||
| Video Generation Models | 2024 | HunyuanVideo | A pretty impressive open source video generation model |
|
| Web Interface | 2025 | gpt-image-1-playground | a simple web-based interface for generating images using GPT-IMAGE-1 |
|
| Image Generation | Apple Optimization | 2022 | CoreML Stable Diffusion | Apple’s optimizations for CoreML |
| Diffusion Acceleration | 2024 | NitroFusion | a high-fidelity, fast (single-step) SDXL diffusion model |
|
| 2022 | Fast Stable Diffusion | Another tactic to accelerate inference |
||
| Vector Graphics | 2025 | NeuralSVG | An Implicit Representation for Text-to-Vector Generation |
|
| Web Interface | 2022 | Stable Diffusion WebUI | Nearly always the best, bleeding edge WebUI for SD |
|
| Multi-modal Models | Samples | 2024 | ml-mgie | instruction-based image self-editing |
| Stable Diffusion | Apps | 2023 | swift-coreml-diffusers | Hugging face’s own app, using Swift and CoreML for Apple Silicon |
| 2022 | Draw Things | Pre-packaged app for iOS, downloads and allows re-use of .ckpt files. |
||
| DiffusionBee | Pre-packaged app for macOS (M1 and Intel) |
|||
| CGI | 2023 | Blender-ControlNet | A Blender plugin to generate ControlNet inputs for posing figures |
|
| 2022 | dream-textures | A Blender plugin for texturing models based on a text description. |
||
| Implementations | 2023 | OnnxStream | Stable Diffusion XL 1.0 Base on a Raspberry Pi Zero 2 (or in 298MB of RAM) |
|
| Libraries | 2024 | sd4j | a Java library for Stable Diffusion that uses ONNX |
|
| Models | SDXL-Lightning | an SDXL flavor that works on only a few steps |
||
| 2023 | Upscale Model Database | Too wide a choice, perhaps |
||
| Reference | 2024 | comflowy | a set of reference workflows and documentation for ComfyUI |
|
| flux | minimal inference examples for FLUX.1 models |
|||
| Tools | comflowyspace | a ComfyUI desktop wrapper |
||
| 2023 | ComfyUI-AnimateDiff-Evolved | An AnimateDiff integration for ComfyUI |
||
| ComfyUI | pretty impressive node-based UI |
|||
| InvokeAI | A polished UI |
|||
| stable-diffusion.cpp | stable diffusion inference on the CPU, in pure C++ |
|||
| ComfyUI-Manager | A component manager for ComfyUI |
|||
| Opendream | A layer-oriented, non-destructive editor |
|||
| 2022 | imaginAIry | Works well on Apple Silicon, pure CLI interface to all SD models.
Does not reuse |
||
| Upscaling | Video Enhancement | 2025 | video2x | a tool for upscaling videos using RealESRGAN and other models |