Overview
Introducing Rae Diffusion XL , an enhanced iteration based on the Animagine XL 3.1 model, specifically fine-tuned for generating stunning anime-style artwork. Building on the robust foundation of the SDXL model, Rae Diffusion XL is meticulously optimized to excel in depicting anime characters, pushing the boundaries of creativity.
Model Details
- Developed by: Raelina
- Model type: Diffusion-based text-to-image generative model
- Model Description: Rae Diffusion XL is an enhanced iteration built on the Animagine XL 3.1 model. It is fine-tuned for high-quality anime-style character art generation.
- License: Fair AI Public License 1.0-SD
- Finetuned from: Animagine XL 3.1
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, ultra detailed, very aesthetic,
- Negative prompts:
(low quality, worst quality:1.2), very displeasing, ugly, interlocked fingers, badly drawn, anatomically incorrect hands, signature, watermark,
- CFG: 7
- Sampling steps: 25 to 30
- 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 RTX 3090 24gb
- Batch size: 12
- Gradient Accumulation: 1
- Epochs: 15
- Learning Rate: 5e-5
- 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
- Algorithm: Locon
License
Rae Diffusion XL now uses the Fair AI Public License 1.0-SD inherited from Animagine XL 3.1, compatible with Stable Diffusion models. Key points:
- Modification Sharing: If you modify Rae Diffusion XL, you must share both your changes and the original license.
- 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.
- Distribution Terms: Any distribution must be under this license or another with similar rules.
- Compliance: Non-compliance must be fixed within 30 days to avoid license termination, emphasizing transparency and adherence to open-source values.