SDXL LoRA

SDXL is a text-to-image generative AI model developed by Stability AI that creates beautiful images. It is the successor to Stable Diffusion.

Features

SDXL-LoRA is a text-to-image generative AI model developed by Stability AI that creates beautiful images. LoRA, which stands for Low-Rank Adaptation, is a technique used to fine-tune pre-trained models efficiently.SDXL-LoRA can be used alone or in combination with a refiner dedicated to the final denoising step to produce higher quality images.

Key Features

• Performance Improvement: The SDXL-LoRA base model performs significantly better than the previous variants, and the model combined with the refinement module achieves the best overall performance.
• Powerful text comprehension skills: SDXL-LoRA uses two fixed, pretrained text encoders (OpenCLIP-ViT/G and CLIP-ViT/L) to improve the understanding of complex cue words, thus generating more closely described images.
• High-quality generation: Base model is used to generate (noisy) latents, which are then further processed with a refinement model, suitable for tasks that require a higher level of detail.

ComfyUI

SDXL-LoRA image to video is available on ComfyUI, providing local inference capabilities through a node-based workflow, ensuring flexible and efficient image generation on your system.

Use Cases

• Generate art illustrations, character designs and more.
• Research on model structure optimization, training method research, visual understanding tasks, etc.
• Building AI mapping tools, content generation platforms, assisted creativity products and more.

Accelerated Inference

Our accelerated inference approach leverages advanced optimization technology from WavespeedAI. This innovative fusion technique significantly reduces computational overhead and latency, enabling rapid image generation without compromising quality. The entire system is designed to efficiently handle large-scale inference tasks while ensuring that real-time applications achieve an optimal balance between speed and accuracy. For further details, please refer to the blog post.

Authentication

For authentication details, please refer to the Authentication Guide.

API Endpoints

Submit Task & Query Result

# Submit the task
curl --location --request POST "https://api.wavespeed.ai/api/v2/wavespeed-ai/sdxl-lora" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}" \
--data-raw '{
    "prompt": "A pixel art scene of a rugged man riding a sleek, futuristic motorcycle across a desert landscape. The man is wearing a classic leather jacket and a helmet with a reflective visor. The motorcycle has glowing blue exhaust pipes and a streamlined design. In the background, there are rolling sand dunes and a bright orange sunset. Add some pixelated cacti and a distant mountain range for depth.",
    "image": "",
    "strength": 0.8,
    "loras": [
        {
            "path": "nerijs/pixel-art-xl",
            "scale": 1
        }
    ],
    "size": "1024*1024",
    "num_inference_steps": 30,
    "guidance_scale": 5,
    "num_images": 1,
    "seed": -1,
    "enable_base64_output": true,
    "enable_safety_checker": true
}'

# Get the result
curl --location --request GET "https://api.wavespeed.ai/api/v2/predictions/${requestId}/result" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}"

Parameters

Task Submission Parameters

Request Parameters

Response Parameters

Result Query Parameters

Result Request Parameters

Result Response Parameters