prunaai/p-image-edit-trainer

Fast LoRA trainer for p-image-edit, a super fast text-to-image model developed by Pruna AI. Use LoRAs here: https://replicate.com/prunaai/p-image-edit-lora. Find or contribute LoRAs here: https://huggingface.co/collections/PrunaAI/p-image-edit

101 runs

Playground API Examples README

Run prunaai/p-image-edit-trainer with an API

Use one of our client libraries to get started quickly. Clicking on a library will take you to the Playground tab where you can tweak different inputs, see the results, and copy the corresponding code to use in your own project.

Input schema

The fields you can use to run this model with an API. If you don't give a value for a field its default value will be used.

Field	Type	Default value	Description
image_data	string		Zip archive with pairs of images for edit training. Images should be named ROOT_start.EXT and ROOT_end.EXT (e.g., photo_start.jpg and photo_end.jpg). Can include multiple reference images: ROOT_start.EXT, ROOT_start2.EXT, ROOT_start3.EXT, ..., ROOT_end.EXT. Can also contain text files (ROOT.txt) to specify edit instructions for each image pair. You can also pass a URL pointing to the zip file instead of uploading a file directly.
steps	integer	1000 Min: 100 Max: 5000	Number of steps to train for
learning_rate	number	0.0001 Min: 0.00001 Max: 0.01	Learning rate for LoRA parameters
default_caption	string		Default caption to use when caption files are missing. If not provided and captions are missing, training will fail.

{
  "type": "object",
  "title": "Input",
  "required": [
    "image_data"
  ],
  "properties": {
    "steps": {
      "type": "integer",
      "title": "Steps",
      "default": 1000,
      "maximum": 5000,
      "minimum": 100,
      "x-order": 1,
      "description": "Number of steps to train for"
    },
    "image_data": {
      "type": "string",
      "title": "Image Data",
      "format": "uri",
      "x-order": 0,
      "description": "Zip archive with pairs of images for edit training. Images should be named ROOT_start.EXT and ROOT_end.EXT (e.g., photo_start.jpg and photo_end.jpg). Can include multiple reference images: ROOT_start.EXT, ROOT_start2.EXT, ROOT_start3.EXT, ..., ROOT_end.EXT. Can also contain text files (ROOT.txt) to specify edit instructions for each image pair. You can also pass a URL pointing to the zip file instead of uploading a file directly."
    },
    "learning_rate": {
      "type": "number",
      "title": "Learning Rate",
      "default": 0.0001,
      "maximum": 0.01,
      "minimum": 1e-05,
      "x-order": 2,
      "description": "Learning rate for LoRA parameters"
    },
    "default_caption": {
      "type": "string",
      "title": "Default Caption",
      "x-order": 3,
      "nullable": true,
      "description": "Default caption to use when caption files are missing. If not provided and captions are missing, training will fail."
    }
  }
}

Output schema

The shape of the response you’ll get when you run this model with an API.

Schema

{
  "type": "string",
  "title": "Output",
  "format": "uri"
}