AI gaming clip maker for Twitch VODs and gameplay uploads
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
US
Not given
Pricing model
Paid
Open source
Pricing
Creator plan: $19.99/month (30 clips per month). Pro plan: $49.99/month (unlimited clips). Both include AI highlight detection, vertical format conversion, auto-generated subtitles, fine-tune editor, and montage maker. 14-day money-back guarantee. Cancel anytime.
Free for personal and research use; prohibits closed-source proprietary monetization
Key features
AI highlight detection analyzes gameplay to find kills, aces, clutches, and funny moments
9:16 vertical format conversion for TikTok, Reels, and Shorts
Automatic speech-to-text subtitles burned into clips
Fine-tune editor with frame-level precision for start and end times
Montage maker to stitch multiple clips together
Get 5-8 ready-to-post clips from a single video
Supports video uploads up to 4 hours and Twitch URL imports
Browser-based, no software installation required
High-quality MP4 export at 1080x1920 resolution, 30fps H.264 codec
Optimized for FPS and MOBA games with distinctive audio cues
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
Processing in 15-30 minutes from raw footage to ready-to-post vertical clips
AI automatically generates 5-8 clips per video without manual editing
Built-in AI subtitles and montage maker included in all plans
Works with any game, optimized for popular FPS and MOBA titles
100% content ownership retained by users with AES-256 encryption security
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
FragCut
Illustrious XL