docs/source/en/api/pipelines/stable_diffusion/image_variation.md

Image variation

The Stable Diffusion model can also generate variations from an input image. It uses a fine-tuned version of a Stable Diffusion model by Justin Pinkney from Lambda.

The original codebase can be found at LambdaLabsML/lambda-diffusers and additional official checkpoints for image variation can be found at lambdalabs/sd-image-variations-diffusers.

Make sure to check out the Stable Diffusion Tips section to learn how to explore the tradeoff between scheduler speed and quality, and how to reuse pipeline components efficiently!

StableDiffusionImageVariationPipeline

[[autodoc]] StableDiffusionImageVariationPipeline - all - call - enable_attention_slicing - disable_attention_slicing - enable_xformers_memory_efficient_attention - disable_xformers_memory_efficient_attention

StableDiffusionPipelineOutput

[[autodoc]] pipelines.stable_diffusion.StableDiffusionPipelineOutput