Type | |
Stats | 689 |
Reviews | (116) |
Published | Jun 24, 2024 |
Base Model | |
Hash | AutoV2 9895131306 |
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. Rae Diffusion XL is meticulously optimized to excel in depicting anime characters, pushing the boundaries of creativity.
Also available at Shakker AI. check it out here
Love my work? Support me with a coffee on Ko-fi
Anime Series
New additional anime series that have been trained:
V1
Fairy Tail
Gabriel Dropout
Blend S
Nisekoi
Youkoso Jitsuryoku Shijou no Kyoushitsu e
Kanojo Okarishimasu
Saenai Heroine no Sodatekata
Mirai Nikki
Guilty Crown
Wildcard character available to download here
V2
Zombie land saga
Yuru yuri
To love-ru
Amagi brilliant park
Avatar legends
Highschool of the dead
Infinite stratos
Inuyasha
Kara no kyoukai
Monster musume no iru nichijou
Seishun buta yarou
Snk
Tekken
Wuthering waves
Wildcard character for V2 is available to download here
*Note: Wildcards are automatically generated from metadata JSON. Some characters might not have been properly generated due to the limited dataset available. You may need more specific prompts, such as hair color, eye color, accessories, costume, etc.
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.
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 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.