🚀 Project AniMax Engine V1.1 – Redefining Creative Imaging

We are thrilled to introduce Project AniMax Engine V1.1, a next-generation SDXL-based AI model built to push the boundaries of creativity. Whether you're an artist, designer, or AI enthusiast, this model brings your vision to life with incredible detail, enhanced realism, and Full HD resolution support.

🧠 Key Features

• Max Native Resolution: 1440x1920 (Tested in Forge / A1111)

• Full XL LoRA Compatibility: Works seamlessly with all XL LoRA models (e.g., Pony, Anime styles, etc.)

• Special Scoring System:

  • score_SFW / halfSFW / NSFW: 0–2.0

  • score_feeling_somefeeling: 1–2.0 (Face detail & emotion quality)

  • score_details: 0–2.0 (Overall image detailing)

  • score_fullhdanatomyfix: 0 or 1 (Fixes anatomical issues in HD)

• Built-in Detail Enhancement Engine

• Fixed Clip Integration – Special internal tweaks for better prompt coherence

• Next-Gen Sampler Support – Compatible with the newest sampling methods

• Custom Trained VAE – Specifically trained to match the model’s aesthetic

⚙️ Industrial-Grade Training Pipeline

• Training Resolution: 1568x1568

• Image Dataset: Over 5 million high-quality images

• Hardware: Trained using 1TB+ VRAM across 6× AMD Instinct™ MI300X GPUs

• Resulting in a robust, versatile, and highly adaptive AI model for serious creators.

🐞 Known Issues (Transparency First!)

• Score Tags: May appear on some images during generation.

• Background Artefacts: Occasionally, background characters may appear incorrectly as pasted images or ghosted figures.

• Hires.fix Scaling Bug: Scaling from native 1080p to 4K may break image structure. This issue stems from mismatches between specified and actual generation dimensions — fix in progress!