LLM & ChatActive
bytedance / seed-v2-lite
seed-v2-lite
A lightweight text-to-image generation model optimized for visual content creation using prompts and optional images.
LLMPartner LLM
Model ID
seed-v2-lite
Provider
bytedance
Updated
1777044326
wiro playground—bytedance/seed-v2-lite
Updated 1777044326
# Seed-V2-Lite Text-to-Image Generator
## Overview
Seed-V2-Lite is a lightweight text-to-image generation model developed by ByteDance. It enables users to create visual content from textual descriptions, with optional support for input images to guide the generation process.
## What you can build
- Creative AI art generators
- Visual content tools for designers
- Custom image synthesis platforms
## Inputs
- **Prompt**: Required. A textual description of the desired image.
- **Input Image** (Optional): Multiple image files separated by semicolon for visual understanding.
- **User ID & Session ID** (Optional): For maintaining chat history.
## Outputs
- Generated image(s) based on the provided prompt and optional input image.
## Recommended settings
- Temperature: 1.0 (balanced creativity)
- Top P: 0.7 (nucleus sampling for diversity)
- Reasoning Effort: Medium (for balanced output quality)
## Limitations
- Performance may vary depending on input complexity.
- Output quality depends on prompt clarity and model training data.
## Safety & compliance
- Designed for general-purpose image generation.
- Users must comply with applicable laws and platform policies when generating content.
API quick start
Run seed-v2-lite with a single API call.
POST https://api.wiro.ai/v1/Run/bytedance/seed-v2-lite
{
"prompt": "Tell me about Türkiye",
"inputImage": "https://your-cdn.com/input.png",
"user_id": "...",
"session_id": "..."
}