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
Paid
Open source
Pricing
Single $9.90 for 1 video (100 credits), Trio $22.90 for 3 videos (300 credits), Party $49.90 for 8 videos (800 credits). All one-time purchases, no subscription or automatic renewal.
Free for personal and research use; prohibits closed-source proprietary monetization
Key features
One-time credit packs with no subscription
Support for one or two people in each video
Fixed 12-second 2K video output
Automatic credit refund on confirmed failed generation
Guest sessions without email or password registration
Private storage with one-hour expiring links for AI processing
Credits that never expire
Download videos as MP4 files
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
Purpose-built for the specific Rumpelstiltskin meme with a fixed preset rather than a general video editor
Uses MiniMax H3 for consistent AI video generation
Quick render times with guidance on what to expect
Independent tool not affiliated with major brands
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