Try Seedance 2.5 Uncensored Video from ByteDance →
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/
LLM & ChatActive

ByteDance / seed-v2-pro-uncensored

seed-v2-pro-uncensored

bybytedance

ByteDance Seed V2 Pro Uncensored is a long-context multimodal chat model for complex reasoning and image Q&A. It generates detailed text answers from prompts and images.

Partner LLM
Model ID
seed-v2-pro-uncensored
Provider
bytedance
Updated
1786973929
seed-v2-pro-uncensored
11
Comments
Average rating : 3 (20 users)
Providerbytedance
Modelseed-v2-pro-uncensored
Partner LLM
wiro playground—bytedance/seed-v2-pro-uncensored
Reset to defaults
Delete All
0 / 20
Maximum 20 image allowed
Drop image to upload

OR

Click to browse your device

Supports: JPG, JPEG, PNG, GIF, WEBP, HEIC

Optional. Multiple image files separated by semicolon for visual understanding.

Required.

Required for chat history. Numeric or string ID.

Required for chat history. Numeric or string ID.

Sample outputs

No samples yet

Run this model to create outputs and build up samples.

Updated 1786973929

Overview

Seed V2 Pro Uncensored is a text model from ByteDance’s Seed family. It’s designed for complex, long-horizon tasks and agent-style workflows. (seed.bytedance.com)

It accepts text and can also read images for visual reasoning. It produces text responses that can include step-by-step plans, structured extractions, and detailed explanations. This helps when you need one model for both analysis and visual Q&A. (seed.bytedance.com)

What you can build

  • Screenshot Q&A for apps, dashboards, and product UIs (seed.bytedance.com)
  • Chart and table interpretation with plain-language summaries (seed.bytedance.com)
  • Document-style extraction from images into clean bullet points (seed.bytedance.com)
  • Multi-step troubleshooting plans and decision trees (github.com)
  • Coding support for long tasks, like repo-level change planning (github.com)
  • “Plan → act → reflect” style task decomposition for research and synthesis (github.com)

Inputs

  • A required user request in plain text. Put the full task, constraints, and desired format in one message.
  • Optional reference images for visual understanding. You can attach multiple images, separated with semicolons, up to 20 images.
  • Optional user identifier as a number or string. Use it to keep chat history tied to one user.
  • Optional session identifier as a number or string. Use it to group a single multi-turn session.
  • Optional system-level instructions in plain text. Use this to set role, tone, and hard rules.
  • Optional creativity control. Lower values make outputs steadier. Higher values add variety.
  • Optional nucleus sampling control. Lower values narrow word choice. Higher values broaden it.
  • Optional repetition controls. You can penalize repeated wording and push topic novelty.
  • Optional maximum response length in tokens. Very large outputs can hit platform or provider limits.
  • Optional reasoning depth selection. Choose from minimal, low, medium, or high.
  • Optional deep thinking mode. Choose enabled, disabled, or auto.

Outputs

The model returns a text response.

The response is typically a single assistant message. It can include: - A direct answer

  • Lists and checklists
  • Structured text meant to be parsed as JSON if you request it
  • Explanations tied to details it finds in attached images (seed.bytedance.com)

Limitations

  • This is a text model. It does not generate images, audio, or video.
  • The Seed 2.0 Pro-class deployment is documented with a 256K context window. Requests that exceed limits can truncate or fail. (docs.byteplus.com)
  • Documented maximum output (including reasoning content) can be up to 128K tokens in some providers. Your Wiro settings may cap outputs lower. (docs.byteplus.com)
  • Visual understanding depends on image quality. Blurry screenshots, heavy compression, or skewed scans can cause missed details.
  • Multi-image prompts can reduce accuracy when images conflict or lack clear ordering.
  • Like other LLMs, it can hallucinate. Verify factual claims, math, and citations.

Safety & compliance

Even if this listing is labeled “uncensored,” you must follow the BytePlus GenAI Acceptable Use Policy when the underlying service is BytePlus-hosted.

Key restrictions called out by BytePlus include: - Don’t use it to support illegal activity or regulated wrongdoing.

  • Don’t create or enable sexual content involving minors.
  • Don’t violate privacy or process personal data without a legal basis.
  • Don’t identify people or verify identity from biometric or personal data.
  • Don’t generate impersonation or likeness content without consent.
  • Don’t run scams, phishing, or deceptive misinformation.
  • Don’t remove or hide model watermarks or provenance signals.
  • Don’t bypass or try to defeat safety mechanisms. (docs.byteplus.com)

BytePlus also expects responsible deployment. Test your workflows, keep human review, and disclose AI-generated content where required. (docs.byteplus.com)

API quick start

Run seed-v2-pro-uncensored with a single API call.

POST https://api.wiro.ai/v1/Run/ByteDance/seed-v2-pro-uncensored
{
  "prompt": "Tell me about Türkiye",
  "inputImage": "https://your-cdn.com/input.png",
  "userId": "...",
  "sessionId": "..."
}
View full API docs

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

All systems operational
WiroAboutBlogCareersContact
ProductModelsAgentsPricingPartnerChangelogStatusFAQ
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