Try MiniMax FastH3 V2 from Fastvideo →
Models
Agents
Workflows
Studio
PricingBlogDocs
ExploreDiscover models by categoryBrowse All ModelsBrowse the complete catalogSee FavoritesSign in to view saved models
Generative Media AgentCreate and edit media by chattingWorkflow AgentBuild visual workflows with Agent
OverviewThe platform at a glanceLearnSkills, knowledge, guardrailsAnatomyWhat makes agents reasonBuild Your AgentPick skills, set tier, deploy
Pre-built AgentsBrowse the catalog
Agent Usecases
Ad Campaign ManagerApp Event ManagerApp Review RepliesBarber BookingCustomer Win-BackEcommerce ListingsRestaurant Reviews
Sign InStart Building

Task History

Click to see output list

No tasks yet

Go to Models
Explore models/
Image GenerationActive

Qwen Image Edit Uncensored (Wiro Partners)

bywiro-partners

Edit a photo with one instruction and up to 3 input images. This uncensored Qwen-based editor keeps identity and framing while changing objects or text.

Image to Image
Model ID
qwen image edit uncensored
Provider
wiro-partners
Updated
1790175841
qwen image edit uncensored
14
Comments
Average rating : 2.36 (35 users)
Providerwiro-partners
Modelqwen image edit uncensored
Image to Image
wiro playground—wiro-partners/qwen image edit uncensored
Reset to defaults
0 / 3
Maximum 3 image allowed
Delete All

Required. Up to 3 images, max 10MB each, between 384x384 and 3072x3072. The first one is the image being edited, the rest are references. The output keeps the size of the first image.

Required. Describe the edit you want. You can point to the inputs by index, like "Image 1" or "Image 2".

Sample outputs
Sample 1
Sample 2
Sample 3
Sample 4
Updated 1790175841

Overview

Qwen Image Edit Uncensored is an instruction-based image editor by Wiro Partners. You give it 1–3 images and one edit instruction. It rewrites pixels to match your request while trying to preserve the original scene structure. It can also edit on-image text with strong font and style matching. The output is a single PNG you can reuse in design or marketing workflows.

What you can build

  • Product photo edits like color swaps, label changes, and prop insertion
  • Portrait restyles that keep the same face while changing clothing and setting
  • Poster and thumbnail updates by replacing or translating visible text
  • Background replacement while keeping subject scale and composition
  • Multi-image fusion like “use the person from Image 1 and the outfit from Image 2”
  • Viewpoint tweaks like “front view” or “face left” for simple object rotations
  • Cleanup edits like removing small objects and blemishes

Inputs

  • One to three input images. Upload them as JPG, JPEG, PNG, BMP, TIFF, WEBP, GIF, or HEIC/HEIF when supported by the platform.
  • The first image is the base image to edit. Any extra images act as references for identity, style, pose, or objects.
  • Each image must be 10 MB or smaller.
  • Each image should be between 384×384 and 3072×3072 pixels for best results.
  • If you upload an animated GIF, the model only uses the first frame.
  • One required edit instruction written in plain language. You can refer to inputs as “Image 1”, “Image 2”, and “Image 3”.
  • An optional numeric random seed (0 to 2,147,483,647) to reproduce the same result.

Outputs

  • One edited image returned as a PNG.
  • The output keeps the width and height of the first input image.
  • The PNG contains the full edited scene, not a layer or mask.

Limitations

  • It may change more than you asked when the instruction is too broad.
  • Many unrelated edits in one instruction can cause drift and unwanted redraws.
  • Small, dense text can still warp or misspell, even when it looks close.
  • Multi-image fusion can blend features if references conflict.
  • Low-quality inputs reduce consistency. Blurry photos, heavy compression, scanned images, and UI screenshots can create artifacts.
  • Very small subjects in a wide shot are harder to preserve during edits.

Safety & compliance

Uncensored variants typically use weaker filtering than standard endpoints. You’re responsible for lawful use and for following the Wiro platform rules.

  • Don’t upload images you don’t have rights to edit.
  • Get consent before editing real people, especially for sensitive or sexual content.
  • Never create sexual content involving minors.
  • Don’t generate non-consensual intimate imagery or harassment.
  • Don’t use it for deceptive impersonation or fraud.
  • Treat reference images as sensitive data. Avoid private or identifying details.

Example prompts

Great starting points for qwen image edit uncensored.

change her outfit to a champagne silk lingerie set and place her reclining on a bed in a softly lit bedroom, warm lamp light, rumpled white sheets, keep her face and hair the same, photorealistic editorial photographyImage Generation
change her clothes to a navy bikini and place her standing at the shoreline of a sunny beach, turquoise water and small waves behind her, keep her face and hair the same, high detail swimwear photographyImage Generation
change her outfit to a black satin lingerie set and place her in a dim luxury hotel suite at night, city lights through floor to ceiling windows, keep her face and hair the same, moody cinematic photographyImage Generation
change her clothes to a white bikini and place her sitting on the edge of a sunlit pool, clear water and palm trees behind her, keep her face the same, travel editorial photographyImage Generation

API quick start

Run qwen image edit uncensored with a single API call.

POST https://api.wiro.ai/v1/Run/wiro-partners/qwen-image-edit-uncensored
{
  "prompt": "change her outfit to a champagne silk lin…",
  "inputImage": "https://your-cdn.com/input.png",
  "seed": 0
}
curl
curl -X POST "https://api.wiro.ai/v1/Run/wiro-partners/qwen-image-edit-uncensored" \
  -H "Content-Type: application/json" \
  -H "x-api-key: YOUR_WIRO_API_KEY" \
  --data-binary @- <<'JSON'
{
  "prompt": "change her outfit to a champagne silk lin…",
  "inputImage": "https://your-cdn.com/input.png",
  "seed": 0
}
JSON
View full API docs

Discover, test, and run AI models, build workflows and agents with one unified API.

All systems operational
WiroAboutBlogCareersContact
ProductModelsAgentsPricingPartnerChangelogStatusFAQ
ModelsNano Banana 2GPT Image 2.5Seedream V5 ProSeedance 2.5Veo 3.1Kling V3FLUX 3FLUX.2 ProWan 3.0 PrimeGrok Imagine 1.5
PartnersGoogleOpenAIByteDanceBlack Forest LabsKling AIQwenAlibabaxAIMiniMaxElevenLabs
Getting StartedIntroductionAuthenticationProjectsCode ExamplesWiro MCP ServerSelf-Hosted MCPn8n IntegrationLLMs.txt
API ReferenceModelsRun a ModelModel ParametersTasksLLM & Chat StreamingWebSocketRealtime VoiceFiles
© 2026 Wiro AI. All rights reserved.
PrivacyTermsData Deletion