AsahinaMix
AsahinaMix is a merge model, and has two branches of merge models, AsaMix which focuses on Anime style while HinaMix focuses on 2.5D anime style.
Model Details AsaMix (Still WIP Comming soon ^^)
- Developed by: Asahina2k
- Model type: Diffusion-based text-to-image generative model
- Model Description: Generate high-quality anime images from textual prompts
- License: Fair AI Public License 1.0-SD
- Merged from model: Animagine XL 3.0
Model Details HinaMix
- Developed by: Asahina2k
- Model type: Diffusion-based text-to-image generative model
- Model Description: Generate high-quality anime images from textual prompts
- License: Fair AI Public License 1.0-SD
- Merged from model: Animagine XL 3.0, RealCartoon-XL, bluePencilXL, Lah | Mysterious SDXL, SwampMachine
Recommended settings
AsaMix and HinaMix have same recommended settings
To guide the model towards generating high-aesthetic images, use negative prompts like:
(worst quality, low quality, lowres), (interlocked fingers, badly drawn hands and fingers, anatomically incorrect hands), blurry, watermark,
For higher quality outcomes, prepend prompts with:
(very aethetic, best quality, ultra detailed), intricate details,
Multi Aspect Resolution
This model supports generating images at the following dimensions:
Dimensions | Aspect Ratio |
---|---|
1024 x 1024 |
1:1 Square |
1152 x 896 |
9:7 |
896 x 1152 |
7:9 |
1216 x 832 |
19:13 |
832 x 1216 |
13:19 |
1344 x 768 |
7:4 Horizontal |
768 x 1344 |
4:7 Vertical |
1536 x 640 |
12:5 Horizontal |
640 x 1536 |
5:12 Vertical |
Hires.fix Setting
- Upscaler : 4x-YandereNeoXL
- Hires step : 10-20
- Denoising : 0.2-0.4 or 0.55 for latent upscaler
Merge parameters for HinaMix
- Animagine XL 3.0 merged to RealCartoonXL V6 to get 2.5D body using MBW (0,1,0.8,0.5,0.25,0,0,0,0,0,0,0.3,0.5,0.71,1,0.56,0.71,1,0.83,0.1)
- (1) merged with Blue Pencil XL v4.0.1 to get anime touch using MBW (0,0.11,0.22,0.33,0.44,0.55,0.44,0.33,0.22,0.11,0,0.11,0.22,0.33,0.44,0.55,0.44,0.33,0.22,0.11)
- (2) merge with Lah | Mysterious SDXL to get manhua fantasy style using MBW (0,1,0.8,0.5,0.25,0,0,0,0,0,0,0.3,0.5,0.71,1,0.56,0.71,1,0.83,0.1)
- (3) merge with SwampMachine for final anime touch using MBW (0,0.11,0.22,0.33,0.44,0.55,0.44,0.33,0.22,0.11,0,0.11,0.22,0.33,0.44,0.55,0.44,0.33,0.22,0.11)
- HinaMix
License
AsahinaMix now uses the Fair AI Public License 1.0-SD inherited from Animagine XL 3.0, compatible with Stable Diffusion models. Key points:
- Modification Sharing: If you modify AsahinaMix, 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.
The choice of this license aims to keep AsahinaMix open and modifiable, aligning with open source community spirit. It protects contributors and users, encouraging a collaborative, ethical open-source community. This ensures the model not only benefits from communal input but also respects open-source development freedoms.
Model tree for Asahina2K/AsahinaMix
Base model
stabilityai/stable-diffusion-xl-base-1.0