import { BodyGenImageToImage } from "@livepeer/ai/models/components";
// No examples available for this model| Field | Type | Required | Description |
|---|---|---|---|
image |
File | Blob | components.Image | ✔️ | Uploaded image to modify with the pipeline. |
prompt |
string | ✔️ | Text prompt(s) to guide image generation. |
guidanceScale |
number | ➖ | Encourages model to generate images closely linked to the text prompt (higher values may reduce image quality). |
imageGuidanceScale |
number | ➖ | Degree to which the generated image is pushed towards the initial image. |
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}. |
modelId |
string | ➖ | Hugging Face model ID used for image generation. |
negativePrompt |
string | ➖ | Text prompt(s) to guide what to exclude from image generation. Ignored if guidance_scale < 1. |
numImagesPerPrompt |
number | ➖ | Number of images to generate per prompt. |
numInferenceSteps |
number | ➖ | Number of denoising steps. More steps usually lead to higher quality images but slower inference. Modulated by strength. |
safetyCheck |
boolean | ➖ | Perform a safety check to estimate if generated images could be offensive or harmful. |
seed |
number | ➖ | Seed for random number generation. |
strength |
number | ➖ | Degree of transformation applied to the reference image (0 to 1). |