Dreamshaper XL v2 Turbo

This is an image generation model based on text prompts (text-to-image), built on the architecture of Stable Diffusion XL (SDXL). It represents a fine-tuned version of the base model stabilityai/stable-diffusion-xl-base-1.0.

Key features:

• Designed to create detailed and artistic images, including anime-style art and portraits.
• Optimized for accelerated generation (Turbo version), using the DPM Solver Multistep Scheduler algorithm to balance speed and quality.

Announce Date: 07.02.2024
Parameters: 3.5B
Context: 77
VRAM requirements: 1.9 GB using 4 bits quantization, 3.8 GB using 8 bits quantization, 7.6 GB using 16 bits quantization
Developer: Lykon
License: OpenRail++

Use our pre-built public endpoints for free to test inference and explore Dreamshaper XL v2 Turbo 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.