Rae Diffusion XL V2

🚀 Rae Diffusion XL V2

Rae Diffusion XL V2 is an enhanced iteration based on the Animagine XL 3.1 model. It is specifically fine - tuned for generating stunning anime - style artwork, excelling in depicting anime characters and pushing the boundaries of creativity.

🚀 Quick Start

Overview

Introducing Rae Diffusion XL V2, an enhanced iteration based on the Animagine XL 3.1 model, specifically fine - tuned for generating stunning anime - style artwork. Rae Diffusion XL V2 is meticulously optimized to excel in depicting anime characters, pushing the boundaries of creativity.

✨ Features

Model Details

📚 Documentation

Usage Guidelines

Tag Ordering

For optimal results, it's recommended to follow the structured prompt template because we train the model like this:

1girl/1boy, character name, from which series, everything else in any order.

Special Tag

Rae Diffusion XL inherits special tags from Animagine XL 3.1 to enhance image generation by steering results toward quality, rating, creation date, and aesthetic. While the model can generate images without these tags, using them helps achieve better results.

• Quality tags: masterpiece, best quality, great quality, good quality, normal quality, low quality, worst quality
• Rating tags: safe, sensitive, nsfw, explicit
• Year tags: newest, recent, mid, early, oldest
• Aesthetic tags: very aesthetic, aesthetic, displeasing, very displeasing

Recommended settings

• Positive prompts:

masterpiece, best quality, very aesthetic, absurdres,

• Negative prompts:

(low quality, worst quality:1.2), very displeasing, ugly, poorly drawn, signature, watermark,

• CFG: 7
• Sampling steps: 25 to 35
• Sampler: Euler a
• Supported Resolution:

1024 x 1024, 1152 x 896, 896 x 1152, 1216 x 832, 832 x 1216, 1344 x 768, 768 x 1344, 1536 x 640, 640 x 1536

Hires.fix Setting

• Upscaler: 4x_NMKD - YandereNeoXL
• Hires step: 10 - 15
• Denoising: 0.1 - 0.3 or 0.55 for latent upscaler

Training config

• Hardware: 1x A100 80GB
• Batch size: 48
• Gradient Accumulation: 1
• Epochs: 10
• Learning Rate: 3e - 6
• Optimizer: Adafactor
• Optimizer Args: (Scale Parameter: False, Relative Step: False, Warmup Init: False)
• Scheduler: Constant with warmup
• Warmup steps: 0.05
• Noise offset: 0.0357

📄 License

Rae Diffusion XL V2 now uses the Fair AI Public License 1.0 - SD inherited from Animagine XL 3.1, compatible with Stable Diffusion models. Key points:

1. Modification Sharing: If you modify Rae Diffusion XL, you must share both your changes and the original license.
2. Source Code Accessibility: If your modified version is network - accessible, provide a way (like a download link) for others to get the source code. This applies to derived models too.
3. Distribution Terms: Any distribution must be under this license or another with similar rules.
4. Compliance: Non - compliance must be fixed within 30 days to avoid license termination, emphasizing transparency and adherence to open - source values.