stable-diffusion-xl-lora

Model overview

stable-diffusion-xl-lora is published by hunz as a text-to-image LoRA. Hub tags list stabilityai/stable-diffusion-xl-base-1.0 as base model and adapter with diffusers library support. According to the model card, the weights were trained with DreamBooth on a photo of flying ironman, with text-encoder LoRA disabled and a special VAE noted.

Recorded capabilities

Use cases in the source record

• Text-to-image workflows that apply this LoRA adapter over the tagged stabilityai/stable-diffusion-xl-base-1.0 base.
• DreamBooth-style subject experiments reproducing the publisher's documented flying-ironman example setup.

Limitations and unknowns

• No evaluation results were extracted from this record.
• No parameter count was extracted for this LoRA record.
• Training detail is limited to brief publisher card claims and has not been independently verified by Ethen.
• Provider state is historical snapshot data, not independently refreshed current availability.

Source and provenance

Source: hunz/stable-diffusion-xl-lora

Captured: Unknown. Processed: 2026-09-07T19:34:46.651633+00:00.

LoRA DreamBooth - hunz/stable-diffusion-xl-lora These are LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0. The weights were trained on a photo of flying ironman using DreamBooth . You can find some example images in the following. LoRA for the text encoder was enabled: False. Special VAE used for training: madebyollin/sdxl-vae-fp16-fix.