Stable Diffusion
Open-source image generation with full control — run locally or in the cloud, free to use.
Stable Diffusion is an open-source text-to-image model by Stability AI. Because it is open weight, it can run locally on your own GPU, be fine-tuned, and is the foundation of countless tools (AUTOMATIC1111, ComfyUI, Leonardo). It offers unmatched flexibility, negative prompts and community checkpoints.
Key Features
- Open source & self-hostable
- Negative prompts
- Community models & LoRA
- ComfyUI / AUTOMATIC1111 support
- Inpainting & img2img
Ratings & Reviews
Loading reviews…
Prompts & Skills for Stable Diffusion
Skills
Monocolor Editorial Print — one-ink & two-ink poster skill
A one-ink and controlled two-ink editorial image skill for posters, zines, portraits, packaging, and visual field notes. Turn any theme, phrase, object, or photo into an original editorial print with warm paper, halftone texture, and sharp typographic contrast.
Punk Cover — generate article cover images from 32 curated visual styles
Turn articles, notes, tweets, and topic drafts into polished cover images for Xiaohongshu, WeChat public accounts, X/Twitter, and more. Selects exactly one reusable style from a shared library of 32 curated visual styles — including minimalist black-and-white, retro torn collage, pixel art metaphor, industrial OSB blueprint, business magazine front page, avant-garde geometry, layered paper-cut concept, and more — then fuses the style atom into a complete cover-specific prompt. Supports custom aspect ratios, multi-size suites, and prompt-only output mode.
Punk Avatar — generate profile pictures, pet portraits, and surreal paper-art from 8 styles
Generate avatar images from photos or text descriptions for people, pets, and objects. Choose from 8 curated styles including pixel avatar, grotesque soul sketch, messy crayon pet portrait, fashion sketch observation, polaroid keepsake card, minimal paper acrylic block illustration, and surreal pop-up paper landscape. Preserves recognizable subject traits while translating them into the selected style. Default 1:1 ratio with custom ratio support.
Related Tools
Midjourney
The gold standard for aesthetic AI image generation — cinematic, artistic and stylized results.
Midjourney is a research lab's AI image generation service known for outstanding artistic quality and style control. It runs inside Discord (and now the web app), where you describe a scene and iterate with parameters like --ar, --stylize and --cref to keep character consistency across images.
Hugging Face
Open-source AI community and platform with 500k+ models, datasets and Spaces for ML collaboration.
Hugging Face is the leading open-source AI community and machine learning platform. It hosts 500,000+ pre-trained models, 100,000+ datasets and interactive Spaces (demos). The platform offers the Transformers library, Inference Endpoints, AutoTrain and enterprise solutions. Hugging Face is the GitHub of machine learning, used by researchers, developers and companies worldwide.
HyperFrames
Write HTML. Render video. Built for agents — deterministic MP4 from HTML/CSS/animation
An open-source framework from HeyGen for turning HTML, CSS, media, and seekable animations into deterministic MP4 videos. Use it locally with the CLI, from AI coding agents with 20 on-demand skills, or as the rendering core behind hosted authoring workflows. Supports GSAP, CSS, Lottie, Three.js, Anime.js, WAAPI. No build step — index.html plays as-is. Deterministic rendering for CI and automated pipelines. Includes a catalog of reusable blocks, Studio editor, AWS Lambda distributed rendering, and frame.md design system.