j1b/jib-mix-qwen-image-lora/text-to-imageFrom 5 credits per image

Jib Mix Qwen LoRA is J1B's photoreal merge of Alibaba's Qwen-Image with up to three LoRA files of your own per request. LoRAs trained for Qwen-Image or Qwen-Image-2512 load from a direct link; camera, portrait and realism LoRAs shift the look, while drawn-style LoRAs barely move this photographic model. Nine aspect ratios at up to 1536 pixels on the long side, one flat price per image, and nothing is filtered.

Call it with the model name j1b/jib-mix-qwen-image-lora/text-to-image on POST /jobs/createTask, from 5 credits per image ($0.05). New accounts get 30 free credits to try it in the Playground first.

  • Create Image
  • 9 aspect ratios
  • Loads your own LoRA

Introduction

Jib Mix Qwen LoRA Text to image makes one photoreal image from a written prompt with up to three of your own LoRA files loaded. Jib Mix Qwen is a community checkpoint by J1B, a merge built on Alibaba's 20-billion-parameter open Qwen-Image and aimed at natural, photographic people.

Choose a mode by what you need

What you needMode
your own LoRAs on topJib Mix Qwen LoRA Text to image
the model as it isJib Mix Qwen Text to image

Key features

Photographic LoRAs that show

On one prompt and seed, a phone-camera LoRA, a portrait-retouch LoRA and two realism LoRAs each changed the face and the light in a way you can see, and two of them stacked cleanly.

Two LoRA generations accepted

LoRAs for Qwen-Image and for Qwen-Image-2512 both load, because they share one architecture. A LoRA for a different base model is skipped without an error, so check the card before you send it.

Request parameters

ParameterRequiredDescription
aspect_ratioNoThe shape of the frame: wide, square or tall. 1:1 · 16:9 · 9:16 · 4:3 · 3:4 · 3:2 · 2:3 · 21:9 · 9:21 · Default: 1:1
lorasNoLoad your own LoRA files to lock in a style or character. Default: []
output_formatNoFile type of the result. jpeg · png · webp · Default: jpeg
promptYesDescribe the person, place and light. If a LoRA has a trigger phrase, put it first.
seedNoReuse the same number to get a repeatable result. ≥ 0 · ≤ 2147483647

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.

OptionCredits per image≈ USD
Standard4.5$0.045

Each task is rounded up to whole credits, so one run at the lowest tier costs 5 credits per image ($0.05).

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

Use cases

A series with one camera look

Pin a camera or film LoRA at a fixed scale and keep the seed to give a whole set of portraits the same lens and light.

Studio portraits

A portrait LoRA adds an even, retouched studio finish while the base model keeps skin texture.

Prompt guide & pro tips

Match the prompt to the LoRA

If a LoRA imitates a phone camera, say "phone photo with flash" in the prompt too. Prompt and weights pulling the same way give the clearest result.

Do not expect drawn styles

Anime and pixel-art LoRAs load but the image stays a photograph, even at scale 2.

Keep scales between 0.5 and 1.5

0.5 is a light touch and 1 is the intended strength. At 4 our test image fell apart.

Link the file

Copy the direct download URL of the .safetensors file.

API quick start

Call the Jib Mix Qwen 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 j1b/jib-mix-qwen-image-lora/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": "j1b/jib-mix-qwen-image-lora/text-to-image",
  "input": {
    "prompt": "A ceramic teapot on a linen cloth, soft window light, muted palette",
    "aspect_ratio": "1:1",
    "output_format": "jpeg"
  }
}'

# 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.

Jib Mix Qwen LoRA API questions

How much does the Jib Mix Qwen LoRA API cost?

Jib Mix Qwen LoRA costs 5 credits ($0.05) per image. Credits are the same as on the website (1 credit = $0.01), new accounts get 30 free credits, and failed tasks are refunded.

What is the model name for Jib Mix Qwen LoRA in the API?

Put j1b/jib-mix-qwen-image-lora/text-to-image for Create Image in the model field of POST /jobs/createTask.

Which LoRAs work best?

Photographic ones: camera looks, portrait retouching and realism LoRAs changed the face and the light visibly in our tests. Drawn-style LoRAs such as anime or pixel art load but leave a photograph, because the base model is strongly photographic.

Do Qwen-Image-2512 LoRAs work?

They load, because 2512 shares the Qwen-Image architecture, and they change the image. A 2512 pixel-art LoRA did not turn our test photo into pixel art, so treat 2512 style LoRAs as hit-and-miss here.

What happens with a LoRA for a different model?

Nothing. A FLUX LoRA loaded without an error and the image was identical to one without it. Check the base named on the LoRA card before you spend a request.

Can I use Civitai LoRAs?

Yes, with a direct download link that works without logging in. A Civitai download link we tried loaded and changed the image.

What are the limits of the Jib Mix Qwen LoRA API?

Aspect ratios: 1:1 · 16:9 · 9:16 · 4:3 · 3:4 · 3:2 +3; Prompt length (characters): 5,000. Requests outside these limits are rejected before anything is charged.

Can I try Jib Mix Qwen LoRA without writing code?

Yes. The Playground runs Jib Mix Qwen LoRA on your PopNow credits, needs no API key, and shows the matching code for every run.

All Jib Mix Qwen models

Plain Jib Mix Qwen is the same model without LoRA slots.

More about Jib Mix Qwen LoRA