Stable Diffusion

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 date	August 22, 2022
Research Paper	https://ommer-lab.com/research/latent-diffusion-models/
Type	Deep learning text to image model

Stable diffusion Tutorials

👉 Discover more Stable Diffusion Tutorials on lablab.ai

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!

Stable Diffusion Colab A Colab notebook that shows how to use Stable Diffusion with GPU!
Stable Diffusion & Whisper Colab A Colab notebook that shows how to use Stable Diffusion with Whisper!
Stable Diffusion Interpolation V2.2 A Colab notebook about Stable Diffusion Interpolation!

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.

NourAI : Your AI Recovery Companion

Eating disorders affect over 70 million people globally, yet most digital recovery tools are either clinically sterile or dangerously naive about the psychological complexity of recovery. Nourish bridges that gap. Nourish is a multi-agent AI system that meets you exactly where you are emotionally — every single morning. It reads your mood, then delivers a personalized Daily Card: a warm hype line written just for you, a mood-matched meal suggestion that respects your safe and trigger food boundaries, a curated color palette and real museum artwork chosen to help you feel grounded and seen, and a heartfelt progress note from your AI recovery pal, Nour. What makes Nourish genuinely different is the combination of art therapy and eating disorder recovery in one system. Research consistently shows that engagement with art and aesthetics supports emotional regulation, identity formation, and body neutrality — all critical pillars of ED recovery. Nourish gives patients something beautiful to look forward to every morning — not a symptom tracker, not a calorie log, but a moment of color, warmth, and encouragement that says: you are more than your disorder. The system never mentions calories, weights, or body appearance. Food is framed around taste, warmth, color, and curiosity. Nour — the AI companion — validates your emotional struggles without judgment, celebrates every small act of courage, and stays with you across a 30, 60, or 90 day recovery arc. Built on AMD GPU using Qwen 2.5-7B and FLUX.1-schnell, Nourish runs entirely on open-source models — making it accessible, private, and scalable.

CLOAK-AI

CLOAK-AI is a high-performance privacy-preserving engine designed to bridge the gap between enterprise data utility and strict PII/PCI compliance. Built specifically for the AMD Hackathon, the project addresses the critical risk of sensitive data leakage in Generative AI workflows. By leveraging the massive 192GB VRAM of the AMD Instinct™ MI300X and optimizing inference via ROCm™ 6.1, CLOAK-AI achieves an industry-leading scrubbing latency of just 0.08 seconds. The system utilizes a multi-layer neural architecture: a Llama-3.3-70B model serves as the intelligent reasoning core to identify complex data clusters, while a specialized NLP masking engine handles high-speed scrubbing. The infrastructure is deployed on the AMD Developer Cloud, ensuring that data never leaves the secure environment. Key features include real-time identification of identity documents (Passport/CNIC), financial credentials (IBAN/Credit Cards), and cybersecurity tokens. CLOAK-AI empowers organizations to adopt LLMs safely without compromising user trust or regulatory standards (GDPR/HIPAA).

NemoFlix Studio

Nemoflix Studio is an agent-native media runtime built for AMD GPUs. It combines ComfyUI-native image generation, Wan 2.2 video synthesis, and identity-preserving LoRA training into a single API-first platform. Built around the AMD MI300X, Nemoflix lets you train character LoRAs directly on AMD hardware with ROCm 7.2, generate photorealistic images with FLUX.2, and animate them into cinematic video with Wan 2.2 I2V — all through a clean REST API designed for AI agents, not humans clicking buttons. The Studio frontend provides a complete creative pipeline: write scene outlines, generate shot images, animate them into motion, and stitch everything together into a final film with automated TTS voiceover. Every output is tracked in a persistent media database with full metadata provenance.

Venice

Venice reimagines research as a branching canvas: each node captures a focused question, offers suggested follow-up branches, and keeps an evidence trail. Links: https://huggingface.co/spaces/lablab-ai-amd-developer-hackathon/venice https://venice.indexd.app/ Retrieval is web-grounded via SerpAPI (Google results) so summaries and “visual fact” chips map to real URLs, while the heavy generative workload runs on AMD Instinct MI300X using ROCm, PyTorch, and Hugging Face diffusers, pulling Qwen from the Hub as Qwen-Image-2512 for high-quality per-node PNG “visual pages”. The UI is a Next.js (App Router) client; the orchestration layer is FastAPI with CORS, health checks, and deterministic output paths for demos. Originality is the hybrid: search-grounded knowledge graph + diffusion-native visuals, not a generic chat wrapper. Business value: faster, more auditable desk research for product, finance, and technical comparisons where sources matter as much as the image.",

OncoTriage AMD-Boosted Uncertainty-Aware CT Triage

OncoTriage is a clinical decision support system designed to detect and triage lung nodules in chest X-rays with high reliability. Developed solo for the 2026 AMD Hackathon, it addresses the lack of transparency in automated diagnostics by implementing Bayesian Deep Learning. The system utilizes a Bayesian EfficientNet-B4 backbone. By employing MC Dropout, the model generates a predictive distribution rather than a single point estimate, allowing for the calculation of epistemic uncertainty. This effectively quantifies the model's confidence for every detection. In clinical settings, this allows the system to flag low-confidence predictions for priority human review, reducing the risk of false negatives inherent in standard "black-box" AI. In addition to this, in order to handle the intensive computational requirements of Bayesian inference, OncoTriage is optimized for AMD Instinct MI300X instances. Leveraging AMD’s high-bandwidth memory (HBM3) and the ROCm stack, the system achieves the rapid inference times necessary for real-time clinical triage. The environment is fully containerized via Docker, ensuring seamless scalability across high-performance compute clusters. The Mission: OncoTriage represents a shift toward accountable, transparent AI. By bridging the gap between raw computational power and clinical safety, it provides radiologists with a reliable partner in oncological screening—transforming raw data into uncertainty-aware medical intelligence.

Qubic Liquidation Guardian

Qubic Liquidation Guardian is a hybrid Track 1 + Track 2 project built by CrewX that brings real-time liquidation protection, institutional-grade risk analysis, and automated alerting to the Qubic Network. The problem is simple: DeFi liquidations happen instantly, but users do not get instant signals. As a result, borrowers lose capital, protocols lose liquidity, and investors hesitate to adopt new systems without safety infrastructure. Inspired by this gap, Qubic Liquidation Guardian provides a complete safety layer over lending protocols deployed on the Nostromo Launchpad. At its core, the system includes an on-chain event listener and a real-time risk scoring engine, which analyzes: • Health Factor • Liquidation Proximity • Total Debt Exposure • Active Positions These metrics are combined into a 0–100 Risk Score, dynamically updated for each borrower. Based on the score, users are automatically classified into Low, Medium, High, and Critical risk tiers, enabling rapid decision-making. The platform also includes advanced features such as: • Whale Watch: Detect large-value transactions to anticipate market shifts • Smart Alerts: Severity-based notifications connected to any tool • Auto-Airdrop: Rewards for users who resolve high-risk positions • Crash Simulator: A built-in testing environment to simulate -70% market dumps, rebounds, and full resets to verify protocol safety Qubic Liquidation Guardian is designed to strengthen the Nostromo ecosystem by improving investor confidence, increasing protocol safety, and enabling risk-aware liquidity management. With over 35 production-ready API endpoints, an edge-distributed database, and a Next.js 15 architecture, the application is fully deployable and already live for testing. Ultimately, this project delivers exactly what new chains and protocols need: speed, stability, transparency, and automation—making Qubic safer for everyone.