Stable Diffusion 3.5 Medium

Stable Diffusion 3.5 Medium is a Multimodal Diffusion Transformer with improvements (MMDiT-X) text-to-image model that features improved performance in image quality, typography, complex prompt understanding, and resource-efficiency.
Key Features

• At 2.5 billion parameters, with improved MMDiT-X architecture and training methods, this model is designed to run “out of the box” on consumer hardware, striking a balance between quality and ease of customization. It is capable of generating images ranging between 0.25 and 2 megapixel resolution.
• Diverse Outputs: Creates images representative of the world, not just one type of person, with different skin tones and features, without the need for extensive prompting. 
• Versatile Styles: Capable of generating a wide range of styles and aesthetics like 3D, photography, painting, line art, and virtually any visual style imaginable.

Introducing Stable Diffusion 3.5 // https://stability.ai/news/introducing-stable-diffusion-3-5

---

The model is a component of the image generation pipeline, consisting of:

• CLIP text encoder: ~124M parameters,
• CLIP text encoder: ~695M parameters,
• T5 text encoder: ~5B parameters,
• Transformer: ~2.5B parameters,
• VAE: ~84M parameters.

Total: ~8B parameters

---

The 'VRAM requirements' line is calculated based on the size of the weights in the specified precision, with an additional +10% coefficient for inference:
  model_parameters_count * bytes_per_parameter * 1.1 / 1024^3 
where model_parameters_count is number of model parameters, bytes_per_parameter is number of bytes used to store one parameter. For 16 bit = 2, 8 bit = 1, 4 bit = 0.5.

Announce Date: 29.10.2024
Parameters: 2.5B
Context: 256
VRAM requirements: 4.2 GB using 4 bits quantization, 8.3 GB using 8 bits quantization, 16.7 GB using 16 bits quantization
Developer: Stability AI
License: StabilityAI Community

Use our pre-built public endpoints for free to test inference and explore Stable Diffusion 3.5 Medium capabilities. You can obtain an API access token on the token management page after registration and verification.

Rent your own physically dedicated instance with hourly or long-term monthly billing.

We recommend deploying private instances in the following scenarios:

• maximize endpoint performance,
• enable full context for long sequences,
• ensure top-tier security for data processing in an isolated, dedicated environment,
• use custom weights, such as fine-tuned models or LoRA adapters.

Contact our dedicated neural networks support team at nn@immers.cloud or send your request to the sales department at sale@immers.cloud.