prompt_image_generation_task
Adapted from the Griptape AI Framework documentation.
Bases:
BaseImageGenerationTask
Attributes
Name | Type | Description |
---|---|---|
image_generation_driver | BaseImageGenerationDriver | The engine used to generate the image. |
negative_rulesets | list[Ruleset] | List of negatively-weighted rulesets applied to the text prompt, if supported by the driver. |
negative_rules | list[Rule] | List of negatively-weighted rules applied to the text prompt, if supported by the driver. |
output_dir | Optional[str] | If provided, the generated image will be written to disk in output_dir. |
output_file | Optional[str] | If provided, the generated image will be written to disk as output_file. |
Source Code in griptape/tasks/prompt_image_generation_task.py
@define class PromptImageGenerationTask(BaseImageGenerationTask): """Used to generate an image from a text prompt. Accepts prompt as input in one of the following formats: - template string - TextArtifact - Callable that returns a TextArtifact. Attributes: image_generation_driver: The engine used to generate the image. negative_rulesets: List of negatively-weighted rulesets applied to the text prompt, if supported by the driver. negative_rules: List of negatively-weighted rules applied to the text prompt, if supported by the driver. output_dir: If provided, the generated image will be written to disk in output_dir. output_file: If provided, the generated image will be written to disk as output_file. """ DEFAULT_INPUT_TEMPLATE = "{{ args[0] }}" _input: Union[str, TextArtifact, Callable[[BaseTask], TextArtifact]] = field( default=DEFAULT_INPUT_TEMPLATE, alias="input" ) @property def input(self) -> TextArtifact: if isinstance(self._input, TextArtifact): return self._input if isinstance(self._input, Callable): return self._input(self) return TextArtifact(J2().render_from_string(self._input, **self.full_context)) @input.setter def input(self, value: TextArtifact) -> None: self._input = value def try_run(self) -> ImageArtifact: image_artifact = self.image_generation_driver.run_text_to_image( prompts=self._get_prompts(self.input.to_text()), negative_prompts=self._get_negative_prompts(), ) if self.output_dir or self.output_file: self._write_to_file(image_artifact) return image_artifact
DEFAULT_INPUT_TEMPLATE = '{{ args[0] }}'
class-attribute instance-attribute_input = field(default=DEFAULT_INPUT_TEMPLATE, alias='input')
class-attribute instance-attributeinput
property writable
try_run()
Source Code in griptape/tasks/prompt_image_generation_task.py
def try_run(self) -> ImageArtifact: image_artifact = self.image_generation_driver.run_text_to_image( prompts=self._get_prompts(self.input.to_text()), negative_prompts=self._get_negative_prompts(), ) if self.output_dir or self.output_file: self._write_to_file(image_artifact) return image_artifact
- On this page
- Attributes
- try_run()
Could this page be better? Report a problem or suggest an addition!