Prefect Pony XL API

Introduction

The endpoint takes a prompt of up to 5,000 characters, one of seven native SDXL sizes, an optional seed and JPEG, PNG or WebP output, and returns one image per call.

Key features

Keep an established tag workflow productive

Pony XL is a text-to-image option for creators who already work in deliberate, descriptive tag sequences. Put the subject, visual style, composition and lighting in a stable order so a prompt library remains understandable to the people maintaining it.

Iterate one creative decision at a time

Establish a composition that works, then change one meaningful visual idea per iteration: gesture, wardrobe, environment or lighting. Compare outputs side by side and retain the prompt version that preserves the intent, rather than treating every run as an unrelated concept.

Review suitability before publishing

Judge anatomy, composition, text rendering and visual consistency at the intended delivery resolution.

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 3 credits per image ($0.03).

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

Use cases

Start from a written brief

Choose the size first — seven native SDXL shapes from 1024*1024 to 1344*768 — then build the prompt from quality tags, subject and wardrobe, and pin a seed once the pose works.

Fan art and social posts

The WebP option means the image can go straight into a page or a feed without a re-encode step in between.

Character sheets and references

Generate the same character across the seven shapes — square for an avatar, 2:3 for a full-body sheet, 16:9 for a banner — reusing the seed and swapping only the framing tags. It gives a consistent-enough reference set without a training run.

Prompt guide & pro tips

Pin the seed once a frame is worth keeping

Store the seed with the prompt. Without it, the exact frame cannot be rebuilt — a near-identical prompt on a fresh seed gives a different character, not a variation of the same one.

Lead with quality tags, then the subject

This lineage responds to the score/quality tag conventions of the Pony ecosystem far more than to descriptive sentences. Put those tags first, then subject and wardrobe, then lighting, lens and background. Prose still works, it just steers less.

Adapt the included example

Start with the published example using output_format: png, size: 1216*832. Replace the subject and creative direction while keeping the input contract for this mode intact.

score_9, score_8_up, 1girl, solo, silver twin tails, oversized varsity jacket, denim shorts, standing on a neon-lit city street at night, rain reflections, looking at viewer, cinematic lighting, detailed background

The wide shape and the neon are both in the prompt: this lineage reads lighting tags as readily as wardrobe tags.

Check the result before iterating

Four fields, no more: prompt, size, seed and output_format. There is no image input, no negative-prompt field, no step or guidance control, no LoRA slot and no batch count — the checkpoint's own sampler settings are fixed and not exposed. Sizes are limited to the seven native SDXL shapes; arbitrary width and height are not accepted. Output is a single image per call. Photoreal prompts will come back stylised: this is an anime merge, not a general-purpose model.

API quick start

Call the Prefect Pony XL 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 prefect/pony-xl/text-to-image 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": "prefect/pony-xl/text-to-image",
  "input": {
    "prompt": "A ceramic teapot on a linen cloth, soft window light, muted palette",
    "size": "1024*1024",
    "output_format": "png"
  }
}'

# 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.

Prefect Pony XL API questions

All Prefect Pony XL models

Anima Turbo is a newer anime model that also reads plain sentences and turns photos into anime.

• Prefect Pony XL LoRA APIPony XL anime art with up to three of your LoRAsFrom 4 credits per image
• Prefect Pony XL APIAnime and illustration art from tag-style promptsFrom 3 credits per image

Other image APIs

• Nano Banana 2.1 APIGoogle's newest Nano Banana, sharp text and 4K outputFrom 8 credits per image
• Nano Banana Pro APIPlans the layout first: dense text, diagrams and 4K editsFrom 17 credits per image
• GPT Image 2.5 Sunburst APIOpenAI's quality-first model, up to 4K with clean textFrom 1 credit per image
• Seedream 5.0 Pro APIHigh-detail images and edits from up to ten referencesFrom 6 credits per image
• FLUX.2 Max APITop-tier FLUX: photoreal light and exact brand colorsFrom 11 credits per image
• Qwen Image 2.1 Pro APIUp to six detailed 2K images from one promptFrom 6 credits per image

More about Prefect Pony XL

Try it

Prefect Pony XL AI Image Generator onlineCreate images with Prefect Pony XL in PopNow

Docs

Prefect Pony XL model ID and input schema in the API docsPopNow API quickstart: your first request in five minutesImage generation guide for the PopNow APIWebhooks: get Prefect Pony XL results without polling