Stable Diffusion
OverseasFreeImage Generation
Open-source image generation model for local deployment and custom development
Developer:Stability AI
Stable DiffusionIntroduction
Open-source image generation framework supporting text-to-image, img2img, and inpainting. Available for online use or local deployment with a rich ecosystem of community plugins. Ideal for developers, designers, and users prioritizing data privacy. The models are free and open-source; cloud service pricing is subject to official rates.
Main Features of Stable Diffusion
Key Product Features
- 1Text-to-Image, Image-to-Image, Inpainting, and Model Fine-Tuning
Stable Diffusion Pricing Plans
Free Tier, Paid Plans, Billing Options, Private Deployment & Enterprise Pricing
- 1The model is open-source and free; cloud services and computing resources are billed based on usage.
- 2On-premise and Enterprise: Supports local and private cloud deployment with full offline capability.
The above is compiled from publicly available information on "Pricing Models" and "Enterprise & Deployment." For complete tiers and discounts, please refer to the official pricing page.
Stable Diffusion User Guide
Entry URL, Registration Requirements, Brief Operation Steps, and API / Client Support
Entry Point:stability.ai
- 1Availability in Mainland China: Models can be downloaded directly; users must provide their own GPU compute resources.
- 2Supported formats: Text prompts input, image output
Information compiled from public sources. Registration requirements and procedures are subject to official documentation.
Stable DiffusionParameter Overview
Information compiled from public sources; official information prevails.
- Is data used for training?
- Data is fully controlled by the user during local deployment and is not uploaded to third parties.
- Underlying model
- Stable Diffusion Series Open-Source Models
- Context length
- Not applicable (primarily based on prompt and image dimensions)
- Multi-modal support
- Text prompt input, image output
- Search Online
- Offline mode enabled
- File Parsing
- Support uploading reference images
- Enterprise Edition and Deployment
- Supports on-premise and private cloud deployment; fully offline capable.
- Compliance Certification
- Open source license follows the corresponding model agreement.
- Domestic Availability
- Models are available for direct download in mainland China; you must provide your own GPU compute power.
Field Description:Will my input be used for model training, and can I turn this off?
Field Description:Primary models supported by the product, or the range of switchable models
Field Description:The maximum context size per conversation determines the length of documents it can read.
Field Description:Supported input and output formats, including text, images, audio, video, and files
Field Description:Supports real-time web search and provides source links?
Field Description:Supports uploading files and parsing capabilities, such as PDFs, spreadsheets, and code.
Field Description:Does it offer an enterprise edition, on-premises deployment, and team permission management?
Field Description:Publicly disclosed security compliance certifications and generative AI service filing status
Field Description:Convenience of access and supported payment methods in mainland China