StableDiffusion3ImageToImage model

[source]

StableDiffusion3ImageToImage class

keras_hub.models.StableDiffusion3ImageToImage(backbone, preprocessor, **kwargs)

An end-to-end Stable Diffusion 3 model for image-to-image generation.

This model has a generate() method, which generates images based on a combination of a reference image and a text prompt.

Arguments

• backbone: A keras_hub.models.StableDiffusion3Backbone instance.
• preprocessor: A keras_hub.models.StableDiffusion3TextToImagePreprocessor instance.

Examples

Use generate() to do image generation.

image_to_image = keras_hub.models.StableDiffusion3ImageToImage.from_preset(
    "stable_diffusion_3_medium", height=512, width=512
)
image_to_image.generate(
    {
        "images": np.ones((512, 512, 3), dtype="float32"),
        "prompts": "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k",
    }
)

# Generate with batched prompts.
image_to_image.generate(
    {
        "images": np.ones((2, 512, 512, 3), dtype="float32"),
        "prompts": ["cute wallpaper art of a cat", "cute wallpaper art of a dog"],
    }
)

# Generate with different `num_steps`, `guidance_scale` and `strength`.
image_to_image.generate(
    {
        "images": np.ones((512, 512, 3), dtype="float32"),
        "prompts": "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k",
    }
    num_steps=50,
    guidance_scale=5.0,
    strength=0.6,
)

# Generate with `negative_prompts`.
text_to_image.generate(
    {
        "images": np.ones((512, 512, 3), dtype="float32"),
        "prompts": "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k",
        "negative_prompts": "green color",
    }
)

[source]

from_preset method

StableDiffusion3ImageToImage.from_preset(preset, load_weights=True, **kwargs)

Instantiate a keras_hub.models.Task from a model preset.

A preset is a directory of configs, weights and other file assets used to save and load a pre-trained model. The preset can be passed as one of:

1. a built-in preset identifier like 'bert_base_en'
2. a Kaggle Models handle like 'kaggle://user/bert/keras/bert_base_en'
3. a Hugging Face handle like 'hf://user/bert_base_en'
4. a path to a local preset directory like './bert_base_en'

For any Task subclass, you can run cls.presets.keys() to list all built-in presets available on the class.

This constructor can be called in one of two ways. Either from a task specific base class like keras_hub.models.CausalLM.from_preset(), or from a model class like keras_hub.models.BertTextClassifier.from_preset(). If calling from the a base class, the subclass of the returning object will be inferred from the config in the preset directory.

Arguments

• preset: string. A built-in preset identifier, a Kaggle Models handle, a Hugging Face handle, or a path to a local directory.
• load_weights: bool. If True, saved weights will be loaded into the model architecture. If False, all weights will be randomly initialized.

Examples

# Load a Gemma generative task.
causal_lm = keras_hub.models.CausalLM.from_preset(
    "gemma_2b_en",
)

# Load a Bert classification task.
model = keras_hub.models.TextClassifier.from_preset(
    "bert_base_en",
    num_classes=2,
)

backbone property

keras_hub.models.StableDiffusion3ImageToImage.backbone

A keras_hub.models.Backbone model with the core architecture.

[source]

generate method

StableDiffusion3ImageToImage.generate(
    inputs, num_steps=50, guidance_scale=7.0, strength=0.8, seed=None
)

Generate image based on the provided inputs.

Typically, inputs is a dict with "images" and "prompts" keys. "images" are reference images within a value range of [-1.0, 1.0], which will be resized to self.backbone.height and self.backbone.width, then encoded into latent space by the VAE encoder. "prompts" are strings that will be tokenized and encoded by the text encoder.

Some models support a "negative_prompts" key, which helps steer the model away from generating certain styles and elements. To enable this, add "negative_prompts" to the input dict.

If inputs are a tf.data.Dataset, outputs will be generated "batch-by-batch" and concatenated. Otherwise, all inputs will be processed as batches.

Arguments

• inputs: python data, tensor data, or a tf.data.Dataset. The format must be one of the following:
  • A dict with "images", "prompts" and/or "negative_prompts" keys.
  • A tf.data.Dataset with "images", "prompts" and/or "negative_prompts" keys.
• num_steps: int. The number of diffusion steps to take.
• guidance_scale: float. The classifier free guidance scale defined in Classifier-Free Diffusion Guidance. A higher scale encourages generating images more closely related to the prompts, typically at the cost of lower image quality.
• strength: float. Indicates the extent to which the reference images are transformed. Must be between 0.0 and 1.0. When strength=1.0, images is essentially ignore and added noise is maximum and the denoising process runs for the full number of iterations specified in num_steps.
• seed: optional int. Used as a random seed.

preprocessor property

keras_hub.models.StableDiffusion3ImageToImage.preprocessor

A keras_hub.models.Preprocessor layer used to preprocess input.