Skip to main content
Stability AIReleased June 12, 2024

Stable Diffusion 3

Open Source8B parameters

Stable Diffusion 3 is Stability AI's entry in a crowded field.

Context

N/A (image)

Input

Free (open)

Key Specifications

🏆

Arena Rank

Not disclosed

📐

Context Window

N/A (image)

📥

Input Price

per 1M tokens

Free (open)

📤

Output Price

per 1M tokens

Free (open)

🧠

Parameters

8B

🔓

Open Source

Yes

Best For

Image generationart creationdesign

About Stable Diffusion 3

Stable Diffusion 3, developed by Stability AI, is an open-source image generation model with 8 billion parameters using the MMDiT (Multimodal Diffusion Transformer) architecture. The model generates images from text descriptions with improved prompt following, text rendering, and compositional understanding compared to previous Stable Diffusion versions. Its transformer-based architecture replaces the UNet design of earlier versions, enabling better scaling and quality. As a fully open-source model, Stable Diffusion 3 can be self-hosted, fine-tuned, and integrated into custom applications without API costs. It supports various aspect ratios, styles, and resolutions. The model's release expanded the already massive Stable Diffusion ecosystem of community tools, LoRA adapters, and specialized variants. It remains a foundation for accessible AI image generation in both research and commercial applications.

Pricing per 1M tokens

Input Tokens

Free (open)

Output Tokens

Free (open)

Frequently Asked Questions

What is Stable Diffusion 3?
Stable Diffusion 3, developed by Stability AI, is an open-source image generation model with 8 billion parameters using the MMDiT (Multimodal Diffusion Transformer) architecture. The model generates images from text descriptions with improved prompt following, text rendering, and compositional understanding compared to previous Stable Diffusion versions. Its transformer-based architecture replaces the UNet design of earlier versions, enabling better scaling and quality. As a fully open-source model, Stable Diffusion 3 can be self-hosted, fine-tuned, and integrated into custom applications without API costs. It supports various aspect ratios, styles, and resolutions. The model's release expanded the already massive Stable Diffusion ecosystem of community tools, LoRA adapters, and specialized variants. It remains a foundation for accessible AI image generation in both research and commercial applications.
How much does Stable Diffusion 3 cost?
Stable Diffusion 3 costs Free (open) per 1M input tokens and Free (open) per 1M output tokens. You pay only for what you use, which keeps costs predictable.
What is Stable Diffusion 3's context window?
Stable Diffusion 3 has a context window of N/A (image) tokens. This determines how much text the model can process in a single request — bigger windows mean longer documents and richer conversation history.
Is Stable Diffusion 3 open source?
Yes, Stable Diffusion 3 is open source. The model weights are publicly available, so developers can download, fine-tune, and self-host it. Open-source models give teams more control over data privacy and deployment.
What is Stable Diffusion 3 best for?
Stable Diffusion 3 is best suited for: Image generation, art creation, design. These use cases play to the model's strengths in capability, speed, and cost within Stability AI's lineup.