v4
Base model changed to Anima.
Recommended Prompt: None
Negative Prompt: None
CFG: 3–6
License Information
This model is an unofficial derivative of Anima by CircleStone Labs LLC, modified by merging my own iLECO LoRAs.
This model remains subject to the CircleStone Labs Non-Commercial License. Rights to use the model are granted directly by CircleStone Labs LLC under that license. Commercial use of generated images is permitted under the original license.
This model is not affiliated with, endorsed by, or officially approved by CircleStone Labs LLC.
Built on NVIDIA Cosmos.
Original Model:
https://huggingface.co/circlestone-labs/Anima
CircleStone Labs Non-Commercial License (including the required Attribution Notice in Section 3(b)):
https://huggingface.co/circlestone-labs/Anima/blob/main/LICENSE.md
NVIDIA Open Model License Agreement:
https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/
v3
Changed the base model to “Seele-NoobAI-SDXL v2.1”.
https://civarchive.com/models/1445275?modelVersionId=2281915
Generation at 2048x2048 resolution is now possible.
Recommended prompt
My Settings(anime): masterpiece, best quality, newest, very aesthetic, absurdres, highres, high resolution, (megami:1.4) (magazine:0), (flat color:0.7), (anime screenshot:1.4)
Seele-NoobAI-SDXL: masterpiece, best quality, newest, absurdres, highres, high resolution
My Settings(old): very aesthetic, masterpiece, best quality, newest, vector trace, absurdres, highres, anime coloring
Negative Prompt
My Settings(anime): text, word, text watermark, (overexposure:1.4), (megami:0) magazine, realistic, worst quality, low quality
Seele-NoobAI-SDXL: worst quality, normal quality, old, early, low quality, lowres, text, word, text watermark, Color cast, Blurred background, Halo, Colorful spots
My Settings(old): worst quality, normal quality, low quality
CFG: 3-6
noob-vpred1
This is an anime model merged based on noobAI XL.
V-Pred v1.0 was used.
Recommended prompt: very aesthetic, masterpiece, best quality, newest, vector trace, absurdres, highres, anime screenshot
Negative Prompt: worst quality
CFG: 5
Sampling method: Euler_Smea
advance_eular_sampler_extension: https://github.com/licyk/advanced_euler_sampler_extension.git
Please comply with NoobAI XL for licensing.
I am using A1111 WebUI and WebUI Forge. Please note that I am not familiar with ComfyUI.
Description
This model was provisionally merged in response to an inquiry from another user asking whether an illustrious version was planned.
At present, it’s only capable of producing reasonably clean linework. With sufficient prompt enhancement and the use of tools like prompt completion, it may be possible to generate somewhat acceptable outputs.
Test settings:
CFG: 7
Resolution: 2048x2048
I’m personally not very fond of this model, but I’m publishing it in the hope that it might serve as a base for someone else's merging experiments.
I just wish illustrious V3.5 v-pred would be released soon.