Skip to content
Qwen Image 3
Explore/Qwen Image 3
image
from0.04 / img

Qwen Image 3

Edit images from an instruction and one to three ordered references with Qwen Image 3.

import { config, higgsfield } from "@higgsfield/client/v2"; config({  credentials: process.env.HF_CREDENTIALS,}); const result = await higgsfield.subscribe(  "alibaba/qwen-image-3/edit",  {    input: {      "prompt": "A cinematic scene at sunset",      "image_urls": [        "https://example.com/input.jpg"      ],      "resolution": "1k",      "aspect_ratio": "1:1",      "prompt_extend": true,      "enable_thinking": true,      "prompt_extend_mode": "direct"    },    withPolling: true,  },); console.log(result);

Calling the API

Use alibaba/qwen-image-3/edit with the Higgsfield API. Keep credentials on your server.

import { config, higgsfield } from "@higgsfield/client/v2"; config({  credentials: process.env.HF_CREDENTIALS,}); const result = await higgsfield.subscribe(  "alibaba/qwen-image-3/edit",  {    input: {      "prompt": "A cinematic scene at sunset",      "image_urls": [        "https://example.com/input.jpg"      ],      "resolution": "1k",      "aspect_ratio": "1:1",      "prompt_extend": true,      "enable_thinking": true,      "prompt_extend_mode": "direct"    },    withPolling: true,  },); console.log(result);

Request parameters

promptstring · required

Positive prompt or editing instruction in Chinese or English. Alibaba recommends at most 4,500 tokens.

{
  "type": "string",
  "minLength": 1,
  "description": "Positive prompt or editing instruction in Chinese or English. Alibaba recommends at most 4,500 tokens."
}
image_urlsarray · required

One to three ordered public image URLs used as editing references.

{
  "type": "array",
  "items": {
    "type": "string",
    "format": "uri"
  },
  "maxItems": 3,
  "minItems": 1,
  "description": "One to three ordered public image URLs used as editing references."
}
aspect_ratiostring · optional

Output aspect ratio. Exact provider-recommended dimensions are selected automatically.

Options: 1:1, 2:3, 3:2, 3:4, 4:3, 7:9, 9:7, 9:16, 16:9, 21:9

Default: "1:1"

{
  "enum": [
    "1:1",
    "2:3",
    "3:2",
    "3:4",
    "4:3",
    "7:9",
    "9:7",
    "9:16",
    "16:9",
    "21:9"
  ],
  "type": "string",
  "default": "1:1",
  "description": "Output aspect ratio. Exact provider-recommended dimensions are selected automatically."
}
resolutionstring · optional

Output resolution tier. Both tiers produce PNG images.

Options: 1k, 2k

Default: "1k"

{
  "enum": [
    "1k",
    "2k"
  ],
  "type": "string",
  "default": "1k",
  "description": "Output resolution tier. Both tiers produce PNG images."
}
negative_promptstring · optional

Content, styles, or artifacts to avoid in the output.

{
  "type": "string",
  "description": "Content, styles, or artifacts to avoid in the output."
}
prompt_extendboolean · optional

Improve the prompt before generation. Required when thinking mode is enabled.

Default: true

{
  "type": "boolean",
  "default": true,
  "description": "Improve the prompt before generation. Required when thinking mode is enabled."
}
prompt_extend_modestring · optional

Direct enhancement is available for every request; agent enhancement is text-to-image only.

Options: direct

Default: "direct"

{
  "enum": [
    "direct"
  ],
  "type": "string",
  "default": "direct",
  "description": "Direct enhancement is available for every request; agent enhancement is text-to-image only."
}
enable_thinkingboolean · optional

Use model reasoning to improve image quality. Requires prompt enhancement.

Default: true

{
  "type": "boolean",
  "default": true,
  "description": "Use model reasoning to improve image quality. Requires prompt enhancement."
}
seedinteger · optional

Optional random seed for similar, reproducible results.

{
  "type": "integer",
  "maximum": 2147483647,
  "minimum": 0,
  "description": "Optional random seed for similar, reproducible results."
}

Price

From $0.0400 per image.

View all pricing
Seedance 2.5▶VideoGenerates videos up to 30 seconds from text, image, video, or audio.$0.118/ sKling 4.0▶VideoCreate videos with Kling 4.0 from text, images, and video references. Generate up to 30-second clips in 1080p, guide keyframes, and edit existing videos.$0.126/ sKling 4.0 Flash▶VideoGenerate 720p videos from text prompts with Kling 4.0 Flash. Choose a duration from 3 to 20 seconds and an aspect ratio of 21:9, 16:9, 9:16, or 1:1.$0.094/ sMiniMax H3 Highspeed▶VideoGenerate 4–15 second videos from text with MiniMax H3 Highspeed. Choose 480P or 768P and control the scene, motion and aspect ratio for quick creative iteration.$0.040/ sWan 3.0 Prime▶VideoGenerates videos from text or media references with fast processing and clips up to 30 seconds.$0.051/ sGrok Imagine 2.0▧ImageGenerates images and makes precise edits while preserving image details and visual consistency.$0.040/ imageSeedance 2.0▶VideoCreates 4K video from text or media references. Supports up to 15 seconds with optional sound.$0.080/ sKling Image 4.0▧ImageGenerate detailed images from text with Kling Image 4.0. Create realistic scenes, product visuals and text-rich designs at 2K, 4K or native 8K.$0.063/ imageSeedream 5.0 Pro▧ImageCreate images from detailed prompts with Seedream 5.0 Pro. Generate product visuals, posters and illustrations at 1K, 1.5K or 2K, with control over the aspect ratio.$0.054/ imageMiniMax H3 Lite▶VideoGenerate 4–15 second videos from text with MiniMax H3 Lite. Choose 480P or 768P and control the scene, motion and aspect ratio for affordable creative exploration.$0.025/ sWan 3.0▶VideoGenerates videos from text or images with native audio and adjustable duration up to 30 seconds.$0.037/ sLTX 2.5 Fast▶VideoGenerates videos from text or images with native audio, camera motion controls and 4K resolution.$0.090/ sLTX 2.5 Pro▶VideoGenerates videos from text or images with native audio, camera motion controls and 1080p output.$0.120/ sGrok Imagine Video 1.5▶VideoCreates videos from text prompts or still images, with 1080p resolution and clips up to 15 seconds.$0.080/ sWan 2.7▶VideoGenerates videos from text or images with native audio and consistent characters across scenes.$0.075/ sHappy Horse 1.1▶VideoGenerates videos from text or image references with output at 1080p and clips up to 15 seconds.$0.140/ sIdeogram 4.0▧ImageGenerates and edits images with multilingual text for posters, packaging and other graphic layouts.$0.030/ imageKling 3.0▶VideoGenerates multi-shot videos from text or images, with native audio and durations up to 15 seconds.$0.071/ sRecraft 4.1▧ImageGenerates images and illustrations using custom palettes and background colors to fit your brand.$0.035/ imageHappy Horse 1.0▶VideoGenerates videos from text or image references with clips up to 15 seconds and 1080p resolution.$0.140/ sPixVerse 6▶VideoGenerates videos from text or images with native sound and control over the first and last frames.$0.098/ sKling O3▶VideoGenerates and edits videos using image or video references, multi-shot scenes and native sound.$0.068/ sKling 2.6▶VideoGenerates videos and sound from text or images, including dialogue, sound effects and ambience.$0.067/ sKling O1 (Omni)▶VideoGenerates and edits videos using image or video references and controls for start and end frames.$0.063/ sWan 2.6▶VideoGenerates multi-shot videos from text or images with native sound and optional video references.$0.075/ sMiniMax Hailuo 2.3▶VideoGenerates short videos from text or images with fluid body motion and natural facial expressions.$0.047/ sKling 2.5▶VideoGenerates videos from text prompts and images, with fast generation and precise prompt control.$0.032/ sQwen Image 3▧ImageGenerates images from English or Chinese text, with enhanced prompts and resolution up to 2K.$0.040/ imageZ-Image Turbo▧ImageGenerates images quickly with clear Chinese and English text rendering and PNG output up to 2K.$0.015/ image