Prediction

Official model

qwen/qwen-image-edit-plus-lora

rjwkg3p6tnrme0ctg1mv6drkeg

Status

Succeeded

Source

Web

Total duration

11.2s

Created

about 10 hours ago by zsxkib

Webhook

–

Input

prompt: Replace the current plain wall background with a sophisticated, softly lit indoor event space, featuring warm golden ambient lighting, elegant architectural details such as decorative panels or subtle artwork, and a slightly blurred depth of field to keep the focus on the subjects while ensuring the new background's rich, muted tones complement their attire.
image: https://replicate.delivery/pbxt/O3gN6S2UvFOLILskrSOVghxUt6IOjAW21KYjcsPcI4woJKIm/Screenshot%202025-11-13%20at%2022.29.13.png
aspect_ratio: match_input_image
lora_weights: eigen-ai-labs/eigen-banana-qwen-image-edit
lora_scale: 1.25
go_fast: true
output_format: webp
output_quality: 95

{
  "aspect_ratio": "match_input_image",
  "go_fast": true,
  "image": [
    "https://replicate.delivery/pbxt/O3gN6S2UvFOLILskrSOVghxUt6IOjAW21KYjcsPcI4woJKIm/Screenshot%202025-11-13%20at%2022.29.13.png"
  ],
  "lora_scale": 1.25,
  "lora_weights": "eigen-ai-labs/eigen-banana-qwen-image-edit",
  "output_format": "webp",
  "output_quality": 95,
  "prompt": "Replace the current plain wall background with a sophisticated, softly lit indoor event space, featuring warm golden ambient lighting, elegant architectural details such as decorative panels or subtle artwork, and a slightly blurred depth of field to keep the focus on the subjects while ensuring the new background's rich,\nmuted tones complement their attire."
}

Install Replicate’s Node.js client library:

npm install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=r8_VSj**********************************

This is your API token. Keep it to yourself.

Import and set up the client:

import Replicate from "replicate";
import fs from "node:fs";

const replicate = new Replicate({
  auth: process.env.REPLICATE_API_TOKEN,
});

Run qwen/qwen-image-edit-plus-lora using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const input = {
  aspect_ratio: "match_input_image",
  go_fast: true,
  image: ["https://replicate.delivery/pbxt/O3gN6S2UvFOLILskrSOVghxUt6IOjAW21KYjcsPcI4woJKIm/Screenshot%202025-11-13%20at%2022.29.13.png"],
  lora_scale: 1.25,
  lora_weights: "eigen-ai-labs/eigen-banana-qwen-image-edit",
  output_format: "webp",
  output_quality: 95,
  prompt: "Replace the current plain wall background with a sophisticated, softly lit indoor event space, featuring warm golden ambient lighting, elegant architectural details such as decorative panels or subtle artwork, and a slightly blurred depth of field to keep the focus on the subjects while ensuring the new background's rich,\nmuted tones complement their attire."
};

const output = await replicate.run("qwen/qwen-image-edit-plus-lora", { input });

// To access the file URL:
console.log(output[0].url()); //=> "http://example.com"

// To write the file to disk:
fs.writeFile("my-image.png", output[0]);

To learn more, take a look at the guide on getting started with Node.js.

Install Replicate’s Python client library:

pip install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=r8_VSj**********************************

This is your API token. Keep it to yourself.

Import the client:

import replicate

Run qwen/qwen-image-edit-plus-lora using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "qwen/qwen-image-edit-plus-lora",
    input={
        "aspect_ratio": "match_input_image",
        "go_fast": True,
        "image": ["https://replicate.delivery/pbxt/O3gN6S2UvFOLILskrSOVghxUt6IOjAW21KYjcsPcI4woJKIm/Screenshot%202025-11-13%20at%2022.29.13.png"],
        "lora_scale": 1.25,
        "lora_weights": "eigen-ai-labs/eigen-banana-qwen-image-edit",
        "output_format": "webp",
        "output_quality": 95,
        "prompt": "Replace the current plain wall background with a sophisticated, softly lit indoor event space, featuring warm golden ambient lighting, elegant architectural details such as decorative panels or subtle artwork, and a slightly blurred depth of field to keep the focus on the subjects while ensuring the new background's rich,\nmuted tones complement their attire."
    }
)

# To access the file URL:
print(output[0].url())
#=> "http://example.com"

# To write the file to disk:
with open("my-image.png", "wb") as file:
    file.write(output[0].read())

To learn more, take a look at the guide on getting started with Python.

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=r8_VSj**********************************

This is your API token. Keep it to yourself.

Run qwen/qwen-image-edit-plus-lora using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

curl -s -X POST \
  -H "Authorization: Bearer $REPLICATE_API_TOKEN" \
  -H "Content-Type: application/json" \
  -H "Prefer: wait" \
  -d $'{
    "input": {
      "aspect_ratio": "match_input_image",
      "go_fast": true,
      "image": ["https://replicate.delivery/pbxt/O3gN6S2UvFOLILskrSOVghxUt6IOjAW21KYjcsPcI4woJKIm/Screenshot%202025-11-13%20at%2022.29.13.png"],
      "lora_scale": 1.25,
      "lora_weights": "eigen-ai-labs/eigen-banana-qwen-image-edit",
      "output_format": "webp",
      "output_quality": 95,
      "prompt": "Replace the current plain wall background with a sophisticated, softly lit indoor event space, featuring warm golden ambient lighting, elegant architectural details such as decorative panels or subtle artwork, and a slightly blurred depth of field to keep the focus on the subjects while ensuring the new background\'s rich,\\nmuted tones complement their attire."
    }
  }' \
  https://api.replicate.com/v1/models/qwen/qwen-image-edit-plus-lora/predictions

To learn more, take a look at Replicate’s HTTP API reference docs.

Output

{
  "id": "rjwkg3p6tnrme0ctg1mv6drkeg",
  "model": "qwen/qwen-image-edit-plus-lora",
  "version": "hidden",
  "input": {
    "aspect_ratio": "match_input_image",
    "go_fast": true,
    "image": [
      "https://replicate.delivery/pbxt/O3gN6S2UvFOLILskrSOVghxUt6IOjAW21KYjcsPcI4woJKIm/Screenshot%202025-11-13%20at%2022.29.13.png"
    ],
    "lora_scale": 1.25,
    "lora_weights": "eigen-ai-labs/eigen-banana-qwen-image-edit",
    "output_format": "webp",
    "output_quality": 95,
    "prompt": "Replace the current plain wall background with a sophisticated, softly lit indoor event space, featuring warm golden ambient lighting, elegant architectural details such as decorative panels or subtle artwork, and a slightly blurred depth of field to keep the focus on the subjects while ensuring the new background's rich,\nmuted tones complement their attire."
  },
  "logs": "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\n📁 [LoRA] eigen-ai-labs/eigen-banana-qwen-image-edit weights you can copy/paste:\n✅ lora_weights=\"eigen-ai-labs/eigen-banana-qwen-image-edit/eigen-banana-qwen-image-edit-fp16-lora.safetensors\"\n━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\nCached raw LoRA to: /tmp/lora_cache/fed65a1eeb23c37667ca55c2a71bd099_raw.safetensors\nAttempting to load LoRA in raw form...\nNo LoRA keys associated to QwenImageTransformer2DModel found with the prefix='transformer'. This is safe to ignore if LoRA state dict didn't originally have any QwenImageTransformer2DModel related params. You can also try specifying `prefix=None` to resolve the warning. Otherwise, open an issue if you think it's unexpected: https://github.com/huggingface/diffusers/issues/new\nRaw LoRA loading failed: Adapter not registered after raw load\nConverting LoRA for compatibility...\nLoading safetensors file...\nTransforming keys...\nSaving transformed LoRA to /tmp/lora_cache/fed65a1eeb23c37667ca55c2a71bd099_transformed.safetensors...\nSuccessfully transformed 1440 keys and saved to /tmp/lora_cache/fed65a1eeb23c37667ca55c2a71bd099_transformed.safetensors!\nCached transformed LoRA to: /tmp/lora_cache/fed65a1eeb23c37667ca55c2a71bd099_transformed.safetensors\nSuccessfully loaded transformed LoRA from: eigen-ai-labs/eigen-banana-qwen-image-edit\nUsing seed: 837177\nGeneration took 6.13 seconds\nTotal safe images: 1 out of 1",
  "output": [
    "https://replicate.delivery/xezq/e6mpkTDL6y0TPKY1jlY8iiJPcF3SHea3fONlcV9sI45UiKSrA/out-0.webp"
  ],
  "data_removed": false,
  "error": null,
  "source": "web",
  "status": "succeeded",
  "created_at": "2025-11-14T03:30:07.189Z",
  "started_at": "2025-11-14T03:30:07.198749Z",
  "completed_at": "2025-11-14T03:30:18.388045Z",
  "urls": {
    "cancel": "https://api.replicate.com/v1/predictions/rjwkg3p6tnrme0ctg1mv6drkeg/cancel",
    "get": "https://api.replicate.com/v1/predictions/rjwkg3p6tnrme0ctg1mv6drkeg",
    "stream": "https://stream.replicate.com/v1/files/bcwr-crndxklcqi25ci6jfjwfhb5ppl6qnge6sahkxb7xgw4a53gamsqq",
    "web": "https://replicate.com/p/rjwkg3p6tnrme0ctg1mv6drkeg"
  },
  "metrics": {
    "predict_time": 11.189295188,
    "total_time": 11.199045121
  }
}

Generated in

11.2 seconds

Tweak it Iterate in playground Report