Wiro - Text To Image Sd Lora icon

Wiro - Text To Image Sd Lora

A text-to-image tool capable of generating images using a Stable Diffusion model and LoRA

Wiro - Text To Image Sd Lora

AI-generated

Overview

This node, named 'Wiro - Text To Image Sd Lora', is designed to generate images from text prompts using a Stable Diffusion model enhanced with LoRA (Low-Rank Adaptation) models. It is useful for scenarios where users want to create AI-generated images based on descriptive text inputs, with options to customize the model, LoRA models, image dimensions, inference steps, guidance scale, and other parameters. Practical examples include generating artwork, concept designs, or visual content for creative projects.

Use Case Examples

  1. Generating an image of a futuristic cityscape by providing a detailed text prompt and selecting a specific Stable Diffusion model with LoRA enhancements.
  2. Creating multiple image samples from a single prompt with customized width, height, and inference steps to explore different visual outputs.

Properties

Name Meaning
Select Model The primary Stable Diffusion model to use for image generation.
Select Model Private A private Stable Diffusion model option for image generation.
Select Lora Model One or more LoRA models to apply during image generation to modify or enhance the output.
Select Lora Model Private Private LoRA models to apply during image generation.
Lo RA Model Url A direct URL to a LoRA model file (.safetensors) to apply during generation, supporting public file hosts like Google Drive or AWS S3.
Prompt The text prompt describing the desired image content. This is a required input.
Negativeprompt Text describing elements to avoid in the generated image.
Numberofoutputs The number of image samples to generate.
Inferencesteps The number of inference steps to perform during image generation, affecting quality and speed.
Guidancescale The guidance scale parameter to control adherence to the prompt during generation.
Seed A seed value for random number generation to allow reproducible outputs.
Clip Skip The number of layers to skip in the CLIP model, affecting image generation.
Width The width of the generated image in pixels.
Height The height of the generated image in pixels.
Scheduler The scheduler algorithm to use during the diffusion process, with options like DDIMScheduler, DDPMScheduler, and others.

Output

JSON

  • taskid - The unique identifier of the image generation task.
  • url - The URL of the generated image if the task completed successfully.
  • status - The status of the image generation task, e.g., 'completed' or 'failed'.

Dependencies

  • An API key credential for the Wiro API

Troubleshooting

  • If the API response does not include a valid task ID or socket access token, the node throws an error indicating an invalid response from the Wiro API. Ensure the API credentials are correct and the API service is operational.
  • If the task status returned from polling is '-1', '-2', '-3', or '-4', the node marks the task as 'failed'. This indicates the image generation process encountered an error or was aborted. Check the prompt and parameters for validity and retry.

Links

Discussion