Pruna Ai P Image Edit Trainer

Pruna Ai P Image Edit Trainer

Playground

Pruna AI P-Image Edit Trainer is a fast AI model training workflow for customizing image editing models with user-provided data. Ready-to-use REST inference API for training custom edit styles, character-consistent edits, product image updates, brand-specific visuals, marketing assets, and personalized AI image editing workflows with simple integration, no coldstarts, and affordable pricing.

Features

Pruna AI P-Image Edit Trainer

Pruna AI P-Image Edit Trainer is a fast training workflow for creating custom LoRAs for the Pruna image editing stack. Upload your training image data, choose the number of training steps, optionally provide a default caption, and generate a LoRA for downstream edit workflows such as style transfer, character-consistent edits, product edits, and other prompt-guided image editing tasks.

Why Choose This?

• Fast custom edit LoRA training Train LoRAs specifically for image editing workflows rather than text-to-image generation.

• Simple training interface Provide training image data and set training steps without a complex setup process.

• Optional caption guidance Use default_caption to provide consistent text guidance across the training data.

• Flexible training depth Adjust steps to balance speed, cost, and how strongly the LoRA learns your dataset.

• Built for the Pruna edit stack Trained outputs are intended for downstream use with Pruna edit LoRA workflows.

• Production-ready API Suitable for custom edit styles, character-consistent edits, branded asset pipelines, and repeatable editing workflows.

Parameters

How to Use

1. Upload your training data — provide the image dataset you want to use for training.
2. Set training steps — choose how many steps to run based on your desired balance of speed and training strength.
3. Add a default caption (optional) — use a short caption if you want more consistent text conditioning during training.
4. Submit — start the training job.
5. Use the trained LoRA — apply the resulting LoRA in downstream Pruna edit LoRA workflows.

Example Workflow

Train a custom edit LoRA for scene-to-scene style transfer, then use the resulting weights in Pruna AI P-Image Edit LoRA for guided image editing.

Pricing

Pricing is based on the selected steps value.

Billing Rules

• Pricing scales linearly with steps
• Cost is $4.00 per 1,000 steps
• Higher steps values increase total training cost proportionally
• default_caption does not affect pricing

Best Use Cases

• Custom edit style training — create LoRAs for specific editing aesthetics or transformations
• Character-consistent editing — train reusable LoRAs for recurring character edits
• Product edit workflows — build LoRAs for consistent product transformations and asset updates
• Brand asset editing — create custom edit models for repeatable branded visual workflows
• Personalized image editing — train LoRAs tailored to a specific subject, look, or edit direction

Pro Tips

• Use a clean, focused training dataset for better LoRA quality.
• Start with a moderate number of steps before scaling to larger training runs.
• Use default_caption when you want consistent conditioning across the dataset.
• Keep the dataset aligned with the type of edits you want the LoRA to perform later.
• Test the trained LoRA in downstream edit workflows before increasing training volume.

Notes

• image_data is required.
• steps defaults to 101.
• default_caption is optional.
• Pricing depends only on the selected steps value.
• LoRAs trained here are intended for Pruna edit LoRA usage.
• If you don’t know the format, please see the official file: https://huggingface.co/datasets/davidberenstein1957/enhance/resolve/main/input.zip

Related Models

• Pruna AI P-Image Edit LoRA — Edit images with prompt guidance and a trained edit LoRA.
• Pruna AI P-Image Text-to-Image Trainer — Train LoRAs for text-to-image generation workflows.
• Pruna AI P-Image Text-to-Image LoRA — Generate images from prompts using a trained LoRA.
• Pruna AI P-Image Edit — Edit images with natural-language instructions without a LoRA.

# Submit the task
curl --location --request POST "https://api.wavespeed.ai/api/v3/pruna-ai/p-image/edit-trainer" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}" \
--data-raw '{
    "steps": 101
}'

# Get the result
curl --location --request GET "https://api.wavespeed.ai/api/v3/predictions/${requestId}/result" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}"