S
Stable Diffusion
by Stability AI
Widely-used open-source image and video generation ecosystem with extensive community models, LoRAs, and customization options. Also includes Stable Audio for music and sound generation.
imagevideoaudio
Models (7)
SDXL 1.0
The most popular open-source image generation model.
Community ecosystemCustom modelsLoRA fine-tuning
SD 3 Medium
Next-gen architecture with improved text and composition.
Text renderingImproved compositionNext-gen quality
Stable Cascade
Efficient multi-stage generation architecture.
Efficient generationResearchNovel architecture
SD 3.5 Large
Latest Stable Diffusion with 8B parameters for top quality.
Open-source qualityFine detailsText rendering
SDXL Turbo
Real-time SDXL generation in a single step.
Real-time generationInteractive toolsRapid iteration
Stable Video Diffusion
Open-source image-to-video generation model.
Image-to-videoOpen-source workflowsCamera motion
Stable Audio 2.0
Stability AI's open-source music and sound generation model with 3-minute high-quality output.
Music productionSound effectsBackground music
Related Guides
Generate with Stable Diffusion
Try Stable Diffusion models directly in Creative Fabrica Studio.