Krea 2 Turbo LoRA API

Introduction

Krea 2 Turbo LoRA Image to image redraws one source image on Krea 2 Turbo, Krea's eight-step open-weight image model, guided by your prompt and up to three of your own LoRA files. A strength value from 0 to 1 decides how far the result moves from the source.

Choose a mode by starting material

Key features

A style LoRA does the restyling

The prompt describes the scene; the LoRA supplies the look.

Strength acts early

At 0.3 a photo already changes in its details, around 0.5 clothing and light follow the prompt, and from 0.8 the model replaces the setting. The default is 0.6, which kept the composition in all four of our examples when the prompt described the same scene; 0.45 restyles more lightly.

The shape follows the source

The result always keeps the source's aspect ratio. The resolution tier only sets the pixel count: about one megapixel on 1k, about four megapixels on 2k.

Request parameters

Pricing

Prices are in credits, the same credits you use on the website (1 credit = $0.01). The hold is taken when the task is accepted and settled to the actual charge when it finishes; failed tasks are refunded.

Each task is rounded up to whole credits, so one run at the lowest tier costs 4 credits per image ($0.04).

For an exact number before you run, send the same body to POST /jobs/quote.

Use cases

Photos in a house style

Turn portraits, location shots or stills into one custom style while the layout stays put, for covers, posters and social posts that share a look.

Alternate takes of a shot

At 0.6 to 0.7 the model keeps the people and framing of a photo but changes clothing, light and time of day to match the prompt.

One style across mixed sources

Run a folder of images through the same LoRA, strength and seed so pictures from different cameras end up in one consistent style.

Prompt guide & pro tips

Trigger phrase first, then the whole picture

Start with the LoRA's trigger, then write what the final image contains. The model regenerates the entire frame, so anything left out of the prompt is left to chance.

Move strength in small steps

If the source shows through too much, raise strength by 0.05; if the pose or the face drifts, lower it. Keep the seed fixed while you compare.

Describe the people as they are

Name the age, hair and clothing you see in the source. At higher strength the model fills gaps on its own, and in our tests faces drifted older or younger when the prompt said nothing about them.

Send a clean source

One clear subject and no borders, captions or watermarks. The model redraws everything it sees, including things you did not mean to keep.

API quick start

Call the Krea 2 Turbo LoRA API in three steps

1. Create an API key. Sign in to PopNow and create a key in the API console. Keys start with sk-popnow- and use the same credits as the website.
2. Send the request. POST /jobs/createTask with model krea/2-turbo-lora/edit and an input object that follows the parameter table. The response returns a task ID straight away.
3. Get the result. Poll GET /jobs/recordInfo with the task ID, or pass a callBackUrl and we post the result to it. Download the output links when the task succeeds.

# 1. Create the task. Keep the Idempotency-Key if you retry after a network error.
export IDEMPOTENCY_KEY="$(uuidgen)"
curl -X POST https://api.popnow.ai/api/v1/jobs/createTask \
  -H "Authorization: Bearer $POPNOW_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $IDEMPOTENCY_KEY" \
  -d '{
  "model": "krea/2-turbo-lora/edit",
  "input": {
    "prompt": "A ceramic teapot on a linen cloth, soft window light, muted palette",
    "image_url": "https://media.popnow.ai/influencer/examples/marco.webp",
    "resolution": "1k"
  }
}'

# 2. Copy data.taskId from the response, then poll until state is succeeded, failed, canceled or expired.
TASK_ID="TASK_ID_FROM_RESPONSE"
curl "https://api.popnow.ai/api/v1/jobs/recordInfo?taskId=$TASK_ID" \
  -H "Authorization: Bearer $POPNOW_API_KEY"

Replace the prompt and any links with your own. The API tab has the response, polling and callback reference.

Krea 2 Turbo LoRA API questions

All Krea models

Krea 2 Large has the highest detail in the line, without LoRA support.

• Krea 2 Turbo LoRA APIKrea 2 Turbo images and restyles with your own LoRAsFrom 4 credits per image
• Krea 2 Large APIKrea's most detailed tier for cinematic key framesFrom 9 credits per image
• Krea 2 Medium APIEveryday Krea images for steady volume workFrom 5 credits per image
• Krea 2 Medium Turbo APIQuick Krea frames guided by up to ten style referencesFrom 3 credits per image

Other image APIs

• Qwen Image 2.1 LoRA APIQwen Image 2.1 images and edits with up to three of your LoRAsFrom 5 credits per image
• MiniMax H3 Image LoRA APIH3 stills and edits with up to three of your LoRAsFrom 7 credits per image
• Anima Turbo LoRA APIAnime art with your own style or character LoRAsFrom 3 credits per image
• P-Image LoRA APIFast P-Image renders and edits with one LoRA of your ownFrom 1 credit per image
• Z-Image Base LoRA APIZ-Image Base with up to three of your own LoRAsFrom 3 credits per image
• FLUX.2 Klein 9B LoRA APIFast FLUX.2 Klein 9B that loads up to three of your LoRAsFrom 3 credits per image

More about Krea 2 Turbo LoRA

Try it

Krea 2 Turbo LoRA AI Image Generator onlineCreate images with Krea 2 Turbo LoRA in PopNow

Docs

Krea 2 Turbo LoRA model ID and input schema in the API docsPopNow API quickstart: your first request in five minutesImage generation guide for the PopNow APIWebhooks: get Krea 2 Turbo LoRA results without polling