Dreamshaper XL Lightning is a fine-tuned Stable Diffusion XL model optimized for fast text-to-image generation with few inference steps. It is based on stabilityai/stable-diffusion-xl-base-1.0.

More details about this model can be found on the original Hugging Face model card: Lykon/dreamshaper-xl-lightning.

This model repo contains the optimized ONNX models required to run the image generation pipeline for Dreamshaper XL Lightning on AMD NPUs.

Model Details

The folder structure is organized to mirror the main components of the SDXL-style diffusion pipeline (scheduler, text encoders, tokenizers, UNet, and VAE decoder).

text

├─ scheduler/
├─ text_encoder/
├─ text_encoder_2/
├─ tokenizer/
├─ tokenizer_2/
├─ unet/
└─ vae_decoder/

The scheduler folder contains the scheduler configuration (timesteps, betas, alphas, etc.) used during the diffusion sampling process.

The text_encoder and text_encoder_2 folders contain the text encoder models used to convert the input prompt into conditioning embeddings for the diffusion model.

The tokenizer and tokenizer_2 folders contain the tokenizer configuration and vocabulary files required to preprocess text prompts before they are fed to the text encoders.

The unet folder contains the UNet model used in the diffusion process. The UNet is exported and structured specifically to leverage the AMD NPU accelerator for the denoising steps.

The vae_decoder folder contains the VAE decoder model used to map latent representations back to the image space. The VAE decoder is also structured to make use of the NPU accelerator for efficient image reconstruction.

Note: UNet and VAE decoder models are optimized and structured to run on AMD NPUs. The other components (text encoders, tokenizers and scheduler) are shared between GPU and NPU pipelines, but are provided here for completeness.

Model Details	Description
Person or organization developing model	Benjamin Consolvo (AMD), makn87amd (AMD)
Original model authors	Lykon
Model date	April 2026
Model version	1.8.0
Model type	Fine-tuned SDXL Lightning text-to-image generation model
Information about training algorithms, parameters, fairness constraints or other applied approaches, and features	SDXL model fine-tuned for fast generation with few steps (Lightning / LCM-style workflow). See the original model card for usage recommendations.
License	OpenRAIL++ — see Lykon/dreamshaper-xl-lightning
Where to send questions or comments about the model	Community Tab and AMD Developer Community Discord

⚡ Intended Use

Getting Started

To get started with this model, visit github.com/amd/sd-sandbox.

⚓ Ethical Considerations

AMD is committed to conducting our business in a fair, ethical and honest manner and in compliance with all applicable laws, rules and regulations. You can find out more at the AMD Ethics and Compliance page.

⚠️ Caveats and Recommendations

Please visit the original model card for more details: Lykon/dreamshaper-xl-lightning.

📌 Citation Details

Please cite stabilityai/stable-diffusion-xl-base-1.0 and refer to Lykon/dreamshaper-xl-lightning for model-specific attribution.

amd/dreamshaper-xl-lightning-amdnpu

🚀 Dreamshaper XL Lightning on AMD AI PC NPU