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
Not given
Open source
Pricing
Free: unlimited ad copy, scripts, and image ads. Starter: $29/mo includes monthly video and image credits, watermark removed. Pro: $69/mo includes more monthly credits and Brand Guide applied across every ad. Credit packs also available: 79 credits for $9.90 and 119 credits for $14.90.
Free for personal and research use; prohibits closed-source proprietary monetization
Key features
AI Video Ad Generator: turn product photos or URLs into 9:16 vertical video ads
UGC Ad Maker: generate real-person-style UGC ads that feel like authentic testimonials
Image & Banner Ads: create image ads in 10 aspect ratios from product photos
Product Photoshoot: convert product photos into store-ready shots and lifestyle scenes
Brand Guide: apply logo, colors, and voice automatically across every ad
One credit wallet: all studios draw from a single pool of credits
Regenerate feature: create fresh ad variations from the same input to test against ad fatigue
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
Minutes not weeks: create ready-to-run ads in minutes without shoots, editors, or designers
Honest by design: every showcase ad is real output from the same pipeline, never fabricated or stock mockups
Ads built for Ads Manager: vertical formats with hooks in the opening second, native pacing for platform feeds
No per-asset licensing fees: full commercial rights on every export with no restrictions on usage
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
Punchylime
Illustrious XL