MiniMax H3 Open Weights | Try in Video Generator →

P Image Edit Trainer | Custom Model Training API

pruna-ai/

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.

training
Input

Idle

$4per run

Related Models

README

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

ParameterRequiredDescription
image_dataYesTraining image data used to create the edit LoRA.
stepsNoNumber of training steps. Higher values generally increase training time and cost. Default: 101.
default_captionNoOptional default caption applied to the training workflow for more consistent edit conditioning.

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.

StepsCost
100$0.40
101$0.404
250$1.00
500$2.00
1000$4.00
2000$8.00

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

Related Models

Note:This website uses AI models provided by third parties.

P Image Edit Trainer API — Quick start

Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/pruna-ai/p-image/edit-trainer with your input as JSON. The endpoint returns a prediction id. Start polling the result endpoint around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. On completed, read output values from data.outputs. Examples for P Image Edit Trainer below.

HTTP example
set -euo pipefail

: "${WAVESPEED_API_KEY:?Set WAVESPEED_API_KEY}"

REQUEST_BODY=$(cat <<'JSON'
{
    "image_data": "https://github.com/mdn/interactive-examples/archive/refs/heads/main.zip",
    "steps": 101
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/pruna-ai/p-image/edit-trainer" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $WAVESPEED_API_KEY" \
  -d "$REQUEST_BODY")

TASK=$(printf '%s' "$SUBMIT_RESPONSE" | jq 'if has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "$TASK" | jq -r '.id')
if [ -z "$PREDICTION_ID" ] || [ "$PREDICTION_ID" = "null" ]; then
  printf 'Submission response did not contain a prediction id
' >&2
  exit 1
fi
RESULT_URL=$(printf '%s' "$TASK" | jq -r '.urls.get // empty')
if [ -z "$RESULT_URL" ]; then
  RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/$PREDICTION_ID/result"
fi

# 2. Poll until the prediction finishes.
while true; do
  RESPONSE=$(curl --silent --show-error --fail-with-body "$RESULT_URL" \
    -H "Authorization: Bearer $WAVESPEED_API_KEY")
  RESULT=$(printf '%s' "$RESPONSE" | jq 'if has("data") then .data else . end')
  STATUS=$(printf '%s' "$RESULT" | jq -r '.status')
  case "$STATUS" in
    completed) printf '%s\n' "$RESULT" | jq '.outputs'; break ;;
    failed|cancelled|timeout) printf '%s\n' "$RESULT" | jq . >&2; exit 1 ;;
    created|processing) sleep 2 ;;
    *) printf 'Unexpected status: %s
' "$STATUS" >&2; exit 1 ;;
  esac
done
Node.js example
const submitUrl = "https://api.wavespeed.ai/api/v3/pruna-ai/p-image/edit-trainer";
const apiKey = process.env.WAVESPEED_API_KEY;
if (!apiKey) throw new Error('Set WAVESPEED_API_KEY');

async function requestJson(url, options = {}) {
  const response = await fetch(url, options);
  if (!response.ok) throw new Error(await response.text());
  return response.json();
}

// 1. Submit the prediction.
const body = await requestJson(submitUrl, {
  method: "POST",
  headers: {
    "Authorization": `Bearer ${apiKey}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
        "image_data": "https://github.com/mdn/interactive-examples/archive/refs/heads/main.zip",
        "steps": 101
}),
});
const task = body.data ?? body;
if (!task.id) throw new Error("Submission response did not contain a prediction id");
const resultUrl = task.urls?.get ||
  `https://api.wavespeed.ai/api/v3/predictions/${task.id}/result`;

// 2. Poll until the prediction finishes.
while (true) {
  const resultBody = await requestJson(resultUrl, {
    headers: { "Authorization": `Bearer ${apiKey}` },
  });
  const result = resultBody.data ?? resultBody;
  if (result.status === "completed") {
    console.log(result.outputs);
    break;
  }
  if (["failed", "cancelled", "timeout"].includes(result.status)) throw new Error(JSON.stringify(result));
  if (!["created", "processing"].includes(result.status)) throw new Error("Unexpected status: " + result.status);
  await new Promise(resolve => setTimeout(resolve, 2000));
}
Python example
import json
import os
import time
from urllib.request import Request, urlopen

api_key = os.environ["WAVESPEED_API_KEY"]
headers = {"Authorization": f"Bearer {api_key}", "Content-Type": "application/json"}
payload = {
    "image_data": "https://github.com/mdn/interactive-examples/archive/refs/heads/main.zip",
    "steps": 101
}

def request_json(url, data=None):
    request = Request(url, data=data, headers=headers, method="POST" if data else "GET")
    with urlopen(request) as response:
        return json.load(response)

# 1. Submit the prediction.
body = request_json("https://api.wavespeed.ai/api/v3/pruna-ai/p-image/edit-trainer", json.dumps(payload).encode())
task = body.get("data", body)
if not task.get("id"):
    raise RuntimeError("Submission response did not contain a prediction id")
result_url = task.get("urls", {}).get("get") or f"https://api.wavespeed.ai/api/v3/predictions/{task['id']}/result"

# 2. Poll until the prediction finishes.
while True:
    result_body = request_json(result_url)
    result = result_body.get("data", result_body)
    status = result.get("status")
    if status == "completed":
        print(result.get("outputs", []))
        break
    if status in {"failed", "cancelled", "timeout"}:
        raise RuntimeError(result)
    if status not in {"created", "processing"}:
        raise RuntimeError(f"Unexpected status: {status}")
    time.sleep(2)

P Image Edit Trainer API — Frequently asked questions

What is the P Image Edit Trainer API?

P Image Edit Trainer is a Pruna Ai model for AI inference, exposed as a REST API on WaveSpeedAI. 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. You can call it programmatically or try it from the playground above.

How do I call the P Image Edit Trainer API?

POST your input parameters to the model's REST endpoint (shown in the API tab of this playground) with your WaveSpeedAI API key in the Authorization header. Submission returns a prediction ID. Poll the result endpoint starting around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. The playground generates production-oriented Python, JavaScript, and cURL examples with timeouts, transient-error handling, and safe GET retries. Full request/response shape is documented at https://wavespeed.ai/docs/docs-api/pruna-ai/pruna-ai-p-image-edit-trainer.

How much does P Image Edit Trainer cost per run?

P Image Edit Trainer starts at $4.00 per run. That figure is the base price — the final charge scales with the parameters you set in the form (output size, length, count, references, or whatever knobs this model exposes), so a higher-quality or larger output costs more than a minimal one. The exact cost for your current input is shown live next to the Generate button before you submit, and the actual per-call charge is recorded on the prediction afterwards.

What inputs does P Image Edit Trainer accept?

Key inputs: `default_caption`, `image_data`, `steps`. The full JSON schema (types, defaults, allowed values) is rendered above the Generate button and mirrored in the API reference at https://wavespeed.ai/docs/docs-api/pruna-ai/pruna-ai-p-image-edit-trainer.

How do I get started with the P Image Edit Trainer API?

Sign up for a free WaveSpeedAI account to claim starter credits, copy your API key from /accesskey, then call the endpoint shown in the API tab of the playground. The playground also auto-generates a code sample in Python, JavaScript, or cURL for the parameters you've set.

Can I use P Image Edit Trainer outputs commercially?

Commercial usage rights depend on the model's license, set by its provider (Pruna Ai). The license summary appears on the model card above; see WaveSpeedAI's Terms of Service for platform-level conditions.