Saltar al contenido principal

SDXLTurboModel

GenerativeModel
DashAI.back.models.hugging_face.SDXLTurboModel

Distilled SDXL model for near real time text-to-image generation.

Wraps stabilityai/sdxl-turbo, a version of Stable Diffusion XL trained with Adversarial Diffusion Distillation (ADD) by Stability AI. ADD transfers knowledge from a large teacher model into a student that can produce photorealistic 512 px images in as few as one denoising step, up to 30x faster than standard SDXL.

Because ADD bakes guidance directly into the model weights, classifier free guidance is disabled (guidance_scale=0 is enforced internally) and negative prompts have minimal effect.

Ideal for interactive and real time applications where latency matters more than absolute peak quality.

References​

Parameters​

negative_prompt
num_inference_steps : integer, default=1
Number of denoising steps. SDXL Turbo is a distilled model that generates high quality images in just 1-4 steps. Using 1 step is fastest; 2-4 steps improve quality slightly. Values above 4 provide diminishing returns for this model.
device : string, default=CPU
Hardware device for inference. SDXL Turbo is fast enough that CPU inference is feasible (30-60 seconds per image). GPU is still recommended for real time or batch generation.
seed : integer, default=-1
Random seed for reproducible generation. A fixed positive integer will always produce the same image for identical settings. Use a negative value (e.g. -1) for a random seed on each run.
width : integer, default=512
Width of the output image in pixels. Must be a multiple of 8. SDXL Turbo's optimal resolution is 512x512 px. Larger resolutions may reduce quality as the model was trained at 512 px.
height : integer, default=512
Height of the output image in pixels. Must be a multiple of 8. SDXL Turbo's optimal resolution is 512x512 px.
num_images_per_prompt : integer, default=1
How many images to generate from a single prompt in one batch. Since SDXL Turbo is fast, generating multiple images per prompt is very efficient.

Methods​

generate(self, input: str) -> List[Any]

Defined on SDXLTurboModel

Generate images from a text prompt using single step distillation.

Parameters

input : str
Text prompt to generate an image from.

Returns

List[Any]
Generated output images in a list.

component_dir(cls) -> pathlib.Path

Defined on DownloadableMixin

Return this component's own storage directory.

Returns

pathlib.Path
<COMPONENT_PATH>/<ClassName>.

delete(cls) -> None

Defined on DownloadableMixin

Remove the component's downloaded artifacts.

download(cls, report: Optional[Callable[[Optional[float], Optional[str]], NoneType]] = None) -> None

Defined on HFDownloadableMixin

Download all repos listed in hf_repos() into component_dir().

Parameters

report : ProgressReporter, optional
Callback invoked before each repo download with report(None, "Downloading <repo_id>"). None means no progress reporting.

get_metadata(cls) -> Dict[str, Any]

Defined on BaseGenerativeModel

Get metadata values for the current generative model.

Returns

Dict[str, Any]
Dictionary indicating whether the model requires a download before use and the expected download size in bytes.

get_schema(cls) -> dict

Defined on ConfigObject

Generates the component related Json Schema.

Returns

dict
Dictionary representing the Json Schema of the component.

hf_repos(cls)

Defined on HFPretrainedDownloadMixin

Derive the single repo entry from MODEL_NAME.

Returns

list of tuple of (str, str)
[(MODEL_NAME, "model")] or an empty list when unset.

is_downloaded(cls) -> bool

Defined on HFDownloadableMixin

Return whether all repo directories exist and are non-empty.

Returns

bool
True when every repo listed in hf_repos() has a non-empty local directory; False otherwise (including when the list is empty).

validate_and_transform(self, raw_data: dict) -> dict

Defined on ConfigObject

It takes the data given by the user to initialize the model and returns it with all the objects that the model needs to work.

Parameters

raw_data : dict
A dictionary with the data provided by the user to initialize the model.

Returns

dict
A validated dictionary with the necessary objects.

Compatible with​