Stable Diffusion XL-refiner-1.0

Refiner Model specializes in the final stages of noise reduction and enhances the visual accuracy of images generated by the base model.

Key features include:

• Utilizes the SDEdit technique (also known as "img2img") to process hidden tensors generated by the base model using the same text prompt.
• Improves locally low-quality regions, such as distorted faces, eyes, or lips.
• Applied after the base model — you can generate an image with Base and then refine it using Refiner.

Announce Date: 26.07.2023
Parameters: 3.1B
Context: 77
Developer: Stability AI
License: OpenRail++

Use our pre-built public endpoints to test inference and explore Stable Diffusion XL-refiner-1.0 capabilities.

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.