Skip to main content
Image Editing fine-tuning trains a LoRA adapter on paired images so the model learns to apply specific edits, styles, or object transformations.

​
Prerequisites

  • An EigenAI account with available credits.
  • A training dataset as a .zip file containing paired source and target images.

​
Create an image editing job

Click Fine-Tune a Model on the Fine-tuning page, then select the Image Editing tab to open the 3-step wizard.

​
Step 1 — Upload

Provide your dataset name and upload your image pairs.
FieldDescription
Dataset NameA name to identify this dataset. Required.
Use an existing datasetPick a previously uploaded image editing dataset instead of uploading a new zip.
Dataset File (.zip)A .zip file up to 10 GB containing your image pairs.
Zip file structure Your zip must follow this layout: 
your_dataset.zip
├── edit_images/          # Folders with input (source) images
│   ├── image_0001/       # Folder name = target image name
│   │   ├── 001.png       # One or more reference images
│   │   ├── 002.png
│   │   └── 003.png
│   └── image_0002/
│       ├── 001.png
│       └── 002.png
├── images/               # Target images (the desired edited results)
│   ├── image_0001.png    # Filename matches folder name in edit_images/
│   └── image_0002.png
└── prompts.json          # {"image_0001": "prompt...", "image_0002": "prompt..."}
Key requirements
  • Folder names in edit_images/ must match the target image filenames in images/ (without extension).
  • Each folder can contain one or more reference images.
  • Supported formats: PNG, JPG, JPEG, WebP.
  • prompts.json keys must match image names (without extension).

​
Step 2 — Configure

Configure the base model and training hyperparameters. Base model
ModelDescription
Qwen-Image-EditStandard image editing model with balanced performance.
Qwen-Image-Edit-2509Updated model with improved editing capabilities.
Training parameters
ParameterOptionsDefaultDescription
LoRA Rank8, 16, 32, 64, 12832Controls the capacity of the LoRA adapter. Higher rank = more expressive but slower to train.
Training Epochs1, 2, 3, 4, 53How many times the model trains over the full dataset.
Learning RateConservative (5×10⁻⁵), Balanced (1×10⁻⁴), Aggressive (2×10⁻⁴)BalancedControls how quickly the model adapts.
Advanced options
FieldDescription
Output NameCustom name for the trained LoRA. Auto-generated if left blank.

​
Step 3 — Review

Review the training summary before launching.
FieldDescription
DatasetThe dataset name you provided.
ModelThe selected base model.
LoRA RankThe selected rank value.
EpochsNumber of training epochs.
Learning RateThe selected learning rate.
AcceleratorHardware used for training (H200 × 8).
Estimated costCredit cost for this training run (Beta pricing).
Click Confirm & Create to submit the job.