Top Builders

Explore the top contributors showcasing the highest number of app submissions within our community.

Stable Diffusion

Latent diffusion models (LDMs) are a type of image generation technique that work by iteratively "de-noising" data in a latent representation space, and then decoding the representation into a full image. This is in contrast to other popular image synthesis methods such as generative adversarial networks (GANs) and the auto-regressive technique used by DALL-E. The Stable Diffusion model is created by a collaboration between engineers and researchers from CompVis, Stability AI, and LAION and released under a Creative ML OpenRAIL-M license, wich means that it can be used for commercial and non-commercial purposes.

The release of this file is the culmination of many hours of collective effort to compress the visual information of humanity into a few gigabytes. Furthermore, the model also supports image-to-image style transfer, as well as upscaling and generating an images from a simple sketch. Included is also an AI-based Safty Classifier, which understands concepts and other factors in generations to remove outputs that may not be desired by the model user.

General
Relese dateAugust 22, 2022
Research Paperhttps://ommer-lab.com/research/latent-diffusion-models/
TypeDeep learning text to image model

Stable diffusion Tutorials

Knowledge Base

Find out how it is working!

  • Research Paper The Stable Diffusion paper describes the model and its training process in detail.
  • Stable Diffusion Demo You can play around with Stable Diffusion on Hugging Face
  • GitHub Repository Visit the Stable Diffusion v2 repository on GitHub
  • dreamstudio Online stable diffusion interface with a lot of optional configurations

Models

There are plenty of Stable Diffusion models, which are taiolred to deliver various art styles, animation styles and more. We encourage you to experiment with many of them and choose the one which you like the most. Here are some of the finest ones:

Boilerplates

Get started with technology!

Edit on GitHub

Stability AI Stable Diffusion AI technology Hackathon projects

Discover innovative solutions crafted with Stability AI Stable Diffusion AI technology, developed by our community members during our engaging hackathons.

ReelBudget

ReelBudget

The Vision Pre-production is one of the most expensive and time-consuming phases of video creation. Whether you are an independent filmmaker pitching a short film or an enterprise marketing team designing a high-budget commercial, the process requires weeks of sketching, planning, and budgeting before a single frame is ever shot. Reelbudget was built to completely automate this process, acting as your autonomous AI creative director and line-producer. How it Works Users simply input a raw text creative brief. Our multi-agent backend instantly parses the creative intent and breaks the script down into structured scenes, characters, and semantic camera directions. The AMD MI300X Advantage To bring these storyboards to life, we needed massive, uncompromised compute power. We proudly deployed our True AI Video Engine on the AMD MI300X Cloud Instance. Rather than relying on simple static images, our pipeline leverages the MI300X's incredible speed to run two state-of-the-art models on the fly: Stable Diffusion XL generates hyper-realistic, anatomically correct base frames. Stable Video Diffusion instantly animates those frames into true moving video clips, physically matching the AI's camera directions. The system then automatically stitches these clips together, burns in dialogue subtitles, and overlays a background soundtrack, outputting a highly polished, ready-to-pitch movie animatic. Feasibility & Cost Estimation Finally, our AI Feasibility Agent analyzes the generated shot list to provide accurate, real-world cost estimations and suggests cheaper production alternatives, saving businesses thousands of dollars in pre-production overhead. Reelbudget proves that with AMD hardware, AI can handle the heavy lifting of video production, allowing creators to focus entirely on the story.

Gemma Captioner: Four Voices, One Truth

Gemma Captioner: Four Voices, One Truth

Most video captioning agents write all four styles in a single pass, so one visual mistake poisons every caption. And the funnier a caption tries to be, the more it tends to invent: a tech joke reaches for packets and uptime that were never there, a sarcastic line flips what actually happened. Track 2 scores both accuracy and tone, so a caption that reads well can still be wrong. We built it the other way around. Instead of adding style at the end, the agent uses Google Gemma-4-31B to look at the video once. It turns sampled frames into a grounded record of what is actually there: it transcribes on-screen text like signs and lane numbers, names concrete colors and counts, and flags whatever it cannot be sure of. A self-check drops anything the frames do not support, and those facts are frozen. Only then do four parallel Gemma-4 text passes rewrite the same verified facts into formal, sarcastic, humorous-tech, and humorous-non-tech voices. A joke can change the tone, but never the events, because the humor voice has to map its metaphor onto a real visible detail. The hard part of this task is speed. Long UHD clips are the trap: a clip that finishes too late is graded as a placeholder. So the agent streams only the frames it needs from each video instead of downloading the whole file, which takes a 97MB two-minute clip from a 20-to-40-second download down to about ten seconds, and it captions clips concurrently while always leaving a complete results.json on disk. Every requested style is always filled, so a slow call never costs a zero. Gemma does the real work. Every scene fact and every caption comes from Gemma-4-31B; take it out and there is no product. It ships as a public linux/amd64 Docker image that runs on its own, reading /input/tasks.json and writing /output/results.json, and it captions the full set of clips well inside the 10-minute budget.

ForgeAi

ForgeAi

ForgeAI is a hardware-aware AI model optimization platform that automatically finds the fastest, most efficient version of a model for a specific GPU — starting with AMD MI300X. Instead of manually tuning models for each accelerator, ForgeAI runs a 7-phase optimization pipeline: architecture search finds the best candidate structures, knowledge distillation transfers accuracy from a teacher model, pruning removes redundant weights, quantization compresses from FP32 to INT8, benchmarking measures real performance on target hardware, Pareto analysis identifies optimal latency-accuracy tradeoffs, and Optuna hyperparameter tuning auto-optimizes across 6 parameters with 50 trials and early stopping. The platform consists of a FastAPI backend with 9 optimization modules, a Next.js 14 frontend, and WebSocket-based live progress streaming. Users upload a PyTorch checkpoint, select target hardware, set constraints (max latency, max memory, min accuracy), and watch the pipeline execute in real time. Results include a Pareto frontier chart, before/after performance comparison, and export to ONNX or TorchScript. ForgeAI targets the $100B+ AI inference market where hardware-specific optimization is still done manually. Unlike Neural Magic and OpenVINO (CPU-focused, tool-by-tool), ForgeAI is AMD-native, full-pipeline, and open source under Apache 2.0.

Framure Forge: Text-to-PBR Materials on AMD GPU

Framure Forge: Text-to-PBR Materials on AMD GPU

Framure Forge turns a text prompt into a game-ready PBR material. You describe a surface — "weathered copper, oxidized patina" — and SDXL, running on an AMD Radeon PRO W7900 (gfx1100) through ROCm, renders the albedo. The normal and roughness maps are then derived on the CPU, and the full set is applied live to hero objects in a Three.js showroom, where you can inspect each map and download a zip ready for any engine. It is built for indie game developers, 3D and environment artists, archviz, and students learning PBR — anyone who needs surfaces fast without the asset-store rabbit hole or per-texture licensing. The output is standard PBR maps: nothing proprietary, nothing locked in. It works with Unreal, Unity, Blender, and Godot. The AMD GPU does the real work: a warm 1024px generation takes about ten seconds, verified with rocm-smi and a live /health endpoint reporting gfx1100 and model_loaded:true. The seven materials were proven end-to-end by importing them into Unreal Engine 5. Both frontend and backend are containerized. The public demo runs in a transparent mock mode so judges can try it instantly, with a popover that says so.

x402 Bazaar Agent

x402 Bazaar Agent

Today's AI agents hit a wall the moment they need data behind a paywall. The x402 Bazaar Agent tears that wall down. The agent takes a plain-English question, searches a catalog of 42 premium endpoints across 17 domains using Gemini semantic embeddings, selects the cheapest APIs that can answer, pays for each call via x402 micropayments on Base Sepolia, and composes a cited final answer — no human in the loop. DISCOVER — Gemini text-embedding-005 indexes the catalog at startup. Queries rank by cosine similarity; entries below a relevance floor return zero results, giving the agent a clean stop signal rather than hallucinated answers. PAY — The x402 HTTP client intercepts the 402 response, signs a USDC micropayment with an EVM wallet, and retries. The LLM never sees the payment handshake. VERIFY — After every paid call, an independent Gemini Flash model judges whether the response served the stated purpose. Off-topic data is flagged before the reasoning model builds on it. COMPOSE — Gemini 2.5 Pro weaves results across endpoints and domains into a cited answer. Demo: "Will container ALPHA-99 arrive at Genoa on time?" triggers three paid calls — container ETA, port congestion, marine weather — producing a synthesized delay forecast. Guardrails prevent runaway behavior: hard budget cap, empty-search streak, no-progress streak, duplicate-call detection, and an iteration backstop. The catalog mirrors the real Coinbase Bazaar's discovery schema exactly — switching to the live Bazaar is one function change. All 42 endpoints have mock fallbacks so the demo works with zero mandatory signups. The browser UI streams every agent action live.