Skip to content

Latest commit

 

History

History
27 lines (22 loc) · 8.8 KB

texttoimageparams.md

File metadata and controls

27 lines (22 loc) · 8.8 KB

TextToImageParams

Example Usage

import { TextToImageParams } from "@livepeer/ai/models/components";

let value: TextToImageParams = {
  prompt: "<value>",
};

Fields

Field Type Required Description
modelId string Hugging Face model ID used for image generation.
loras string A LoRA (Low-Rank Adaptation) model and its corresponding weight for image generation. Example: { "latent-consistency/lcm-lora-sdxl": 1.0, "nerijs/pixel-art-xl": 1.2}.
prompt string ✔️ Text prompt(s) to guide image generation. Separate multiple prompts with '|' if supported by the model.
height number The height in pixels of the generated image.
width number The width in pixels of the generated image.
guidanceScale number Encourages model to generate images closely linked to the text prompt (higher values may reduce image quality).
negativePrompt string Text prompt(s) to guide what to exclude from image generation. Ignored if guidance_scale < 1.
safetyCheck boolean Perform a safety check to estimate if generated images could be offensive or harmful.
seed number Seed for random number generation.
numInferenceSteps number Number of denoising steps. More steps usually lead to higher quality images but slower inference. Modulated by strength.
numImagesPerPrompt number Number of images to generate per prompt.