stable_diffusion_3
__all__ = ['StableDiffusion3ImageGenerationPipelineDriver']
module-attribute
StableDiffusion3ImageGenerationPipelineDriver
Bases: BaseDiffusionImageGenerationPipelineDriver
Image generation model driver for Stable Diffusion 3 models.
For more information, see the HuggingFace documentation for the StableDiffusion3Pipeline: https://huggingface.co/docs/diffusers/main/en/api/pipelines/stable_diffusion/stable_diffusion_3
Attributes:
Name | Type | Description |
---|---|---|
width |
int
|
The width of the generated image. Defaults to 1024. Must be a multiple of 64. |
height |
int
|
The height of the generated image. Defaults to 1024. Must be a multiple of 64. |
seed |
Optional[int]
|
The random seed to use for image generation. If not provided, a random seed will be used. |
guidance_scale |
Optional[float]
|
The strength of the guidance loss. If not provided, the default value will be used. |
steps |
Optional[int]
|
The number of inference steps to use in image generation. If not provided, the default value will be used. |
torch_dtype |
Optional[dtype]
|
The torch data type to use for image generation. If not provided, the default value will be used. |