Try MiniMax FastH3 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/
Video GenerationActive

Wan 3.0 Prime Pro R2V Uncensored

bywiro-partners

Create 2–30s reference-guided videos from a prompt plus up to 10 images, 5 clips, and 5 audio tracks. Export 1080p, 2K, or 4K MP4.

Image to VideoVideo to Video
Model ID
wan 3.0 prime pro r2v uncensored
Provider
wiro-partners
Updated
1789748012
14
Comments
Average rating : 3.325 (20 users)
Providerwiro-partners
Modelwan 3.0 prime pro r2v uncensored
Image to VideoVideo to Video
wiro playground—wiro-partners/wan 3.0 prime pro r2v uncensored
Reset to defaults
0 / 10
Maximum 10 image allowed
Delete All

Optional. Up to 10 subject or style references.

Required. The prompt to generate the video. You can point to the inputs by index, like "Image 1" or "Video 1".

Required. Total duration of the generated video (in seconds)

Required. Quality tier for the generated video

Optional. Aspect ratio of the output. Adaptive derives it from the prompt and the input media.

Sample outputs
Updated 1789748012

Overview

Wan 3.0 Prime Pro R2V Uncensored by Wiro-Partners generates a short video from your written direction and references. You give it a set of images, video clips, and optional audio, then describe what should happen. The model uses your references to keep identity, wardrobe, props, and style more consistent across frames. It outputs a ready-to-use MP4 clip, which solves the “same character, new scene” problem.

What you can build

  • Character-consistent clips across many prompts using the same reference set
  • Product videos that keep logos, shapes, and materials stable while adding motion
  • UGC-style creator shots driven by a reference face, outfit, and setting
  • Style-locked brand content using a mood board plus a subject reference
  • Motion studies that borrow pacing from a reference clip while changing the scene
  • Music-led clips where a short audio reference guides timing and mood

Inputs

  • A written video brief in plain text. You can point to your uploads by index, like “Image 1” or “Video 2”.
  • Optional reference images for subject identity or style guidance. You can provide up to 10 images (JPG, JPEG, PNG, GIF, WEBP, HEIC).
  • Optional reference video clips for motion, pacing, or shot feel. You can provide up to 5 clips (MP4, WEBM, MOV). Total reference video time must stay within 15 seconds. Each clip must be 100 MB or smaller.
  • Optional reference audio clips for voice, ambience, or music cues. You can provide up to 5 clips (WAV, MP3). Total reference audio time must stay within 15 seconds.
  • A target output duration in whole seconds. It must be between 2 and 30 seconds.
  • An output quality tier. Choose 1080p, 2K, or 4K.
  • An optional aspect ratio choice. You can let it adapt, or force 16:9, 4:3, 1:1, 3:4, or 9:16.
  • An optional switch to include an audio track in the exported video.
  • An optional switch that rewrites and expands your prompt for more detail.
  • An optional numeric seed for repeatable results.

Outputs

The model returns a single MP4 video file. The clip length matches your selected duration. Frame size matches your selected quality tier and aspect ratio. If you enable audio, the MP4 includes an audio track.

Limitations

  • The generated video length is capped at 30 seconds per run.
  • Reference limits are strict: up to 10 images, 5 videos, and 5 audio clips.
  • Reference clips have a combined limit of 15 seconds for video and 15 seconds for audio.
  • Input reference video duration counts toward the total time budget. Input plus output must stay within 30 seconds.
  • Prompting is sensitive to how you assign roles to each reference. Conflicting references can cause identity drift.
  • Low-quality inputs can degrade results. Heavy compression, noisy images, scanned screenshots, and text overlays can trigger motion glitches.

Safety & compliance

This model is labeled uncensored, so it may follow adult-themed prompts more readily than moderated models. You still must follow platform rules and all applicable laws.

  • Only upload images, video, and audio you have rights to use.
  • Don’t upload real-person likeness or voice without consent.
  • Don’t create deceptive impersonations, fraud, or misleading deepfakes.
  • Never generate sexual content involving minors or non-consensual content.
  • If you ship this in a user-facing product, add your own moderation and abuse controls.

Example prompts

Great starting points for wan 3.0 prime pro r2v uncensored.

Image 1 is now in a photo studio wearing an opaque black lingerie set with a full coverage bra and matching briefs, she turns toward the camera and takes one slow step forward with a small smileVideo Generation
Image 1 is now walking a fashion show runway in a modest white two-piece bikini with full coverage, she walks toward the camera with a slow model stride, then looks back over her shoulderVideo Generation
Image 1 is now in a living room wearing an opaque burgundy lingerie set with a full coverage bra and matching briefs, she stands up from the sofa and walks toward the camera, then tucks her hair behind one earVideo Generation
Image 1 is now on an empty soccer field wearing a modest sport bikini with full coverage, she jogs a few steps toward the camera, then slows down, puts her hands on her hips, and smilesVideo Generation

API quick start

Run wan 3.0 prime pro r2v uncensored with a single API call.

POST https://api.wiro.ai/v1/Run/wiro-partners/wan-3-0-prime-pro-r2v-uncensored
{
  "prompt": "Image 1 is now on an empty soccer field w…",
  "duration": 5,
  "resolution": "1080p",
  "inputImage": "https://your-cdn.com/input.png"
}
curl
curl -X POST "https://api.wiro.ai/v1/Run/wiro-partners/wan-3-0-prime-pro-r2v-uncensored" \
  -H "Content-Type: application/json" \
  -H "x-api-key: YOUR_WIRO_API_KEY" \
  --data-binary @- <<'JSON'
{
  "prompt": "Image 1 is now on an empty soccer field w…",
  "duration": 5,
  "resolution": "1080p",
  "inputImage": "https://your-cdn.com/input.png"
}
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