Translate manga online from images while preserving speech bubbles, artwork, and page layout
Open-source SDXL-based AI model for native high-resolution anime art generation
Stage
Not given
Not given
Founded
Not given
Not given
Based in
Not given
Not given
Pricing model
Freemium
Open source
Pricing
Free plan: 20 free translations. Lite: $4/month (billed annually) with 500 credits. Standard: $7/month (billed annually) with 3,000 credits. Pro: $14/month (billed annually) with 12,000 credits. Save up to 30% with annual billing.
Free for personal and research use; prohibits closed-source proprietary monetization
Key features
Batch processing: translate multiple pages together in one queue
Accurate text recognition in manga panels and speech bubbles
Fast translation of manga dialogue
Text color recognition carries original colors into translation
Adaptive text sizing adjusts font and line breaks for translated dialogue
Automatic text removal with background repair
Support for JPG, PNG, and WEBP image formats
Translation to multiple languages including English, Chinese, Korean, and more
Manga Editor included with paid plans
Advanced translation model and custom fonts on paid plans
Native 1536x1536 high-resolution generation without upscaling
Hybrid Prompting System combining natural English and Danbooru tags
Stable text encoder fine-tuning for superior concept understanding
Trained on comprehensive Danbooru2023 dataset
Full compatibility with ComfyUI, Automatic1111, Forge, and Draw Things
Superior anatomy rendering with flawless hands and character details
V-Prediction architecture for enhanced dynamic range and contrast
Highly flexible base canvas for LoRA training and custom checkpoints
What makes it different
Translate directly from images without copying text to another tool
Automatic text removal saves time compared to manual erasing
Process multiple pages in one batch instead of uploading one by one
Free tier available with 20 free translations and no signup required
Only open-source SDXL model natively trained at 1536x1536 resolution
Stylistically neutral untuned base canvas unlike Pony Diffusion
Continuous rapid iterations from v0.1 to v3.5 with aggressive optimization
Thousands of compatible community-trained LoRAs and derivatives
TranslateManga
Illustrious XL