Analyze Instagram Reels and TikTok videos with AI, then turn what you learn into original scripts for your own audience and voice.
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
Starter: $19/month with 100 credits per month, about 9 complete video analyses with scripts. Pro: $39/month with 300 credits per month, about 27 complete video analyses with scripts. A complete video package uses 11 credits; each later revision uses 1 credit.
Free for personal and research use; prohibits closed-source proprietary monetization
Key features
Video analysis with hook and beat breakdown
Original script and shot list generation
Instagram Reels and TikTok video transcription
Content profile to store audience and voice context
One-credit chat revisions for refinement
Integration with ChatGPT and Claude via MCP
Automatic credit refund for failed video processing
Source video automatic deletion after analysis
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
Studies visual structure and timing, not just transcripts
Applies your stored voice, niche and audience to every script
Creates original content, not copies of the source video
Includes ready-to-shoot package with script, shot list and captions
Works as an MCP tool within existing ChatGPT and Claude workflows
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
Karmo
Illustrious XL