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
CN
Not given
Pricing model
Paid
Open source
Pricing
Starter: $9.90 for 300 credits (1 standard 480p video + 100 credits or 1 HD 720p video). Creator: $24.90 for 900 credits (4 standard videos + 100 credits or 3 HD videos). Studio: $59.90 for 3,000 credits (15 standard videos or 10 HD videos). Videos cost 200 credits for 480p or 300 credits for 720p H
Free for personal and research use; prohibits closed-source proprietary monetization
Key features
Two-photo input for human and zombie or pet and owner stories
Online generation with 10-15 minute processing time
Portrait 9:16 and landscape 16:9 format options
480p and 720p HD quality options
Video download and watch from My creations
No editing or prompt writing required
15-second videos with sound
Four-scene story structure with confrontation, embrace and memory
Support for JPG, PNG and WebP formats up to 8 MB
Clapping cat generator alternative
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
No subscription required, only one-time credit purchases
Automated generation without manual editing or prompt engineering
Emotional AI-generated video stories from personal photos
Support for both people and pets in the same format
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