Type | |
Stats | 1,272 |
Reviews | (415) |
Published | May 13, 2023 |
Base Model | |
Hash | AutoV2 69AEBD6FA8 |
Follow me on Twitter for latest Art Generation: https://twitter.com/Vajrabond
This model can be thought of as a model for Beginners, which will give consistent and quick results if using all the same settings as I have shown in samples, for image to image purpose.
This model has been tested to be effective in producing AI Cosplay Characters with Control Net. Particularly female human cosplayers can be more easily generated. Ionising strength optimal between 0.22 to 0.44. 0.22 for small details to be captured then inpaint the rest of the image with 0.33 for closer to original art lines or 0.44 for more realism.
Works well with realistic prompts.
I have attached core positive and negative prompts used in all samples generated.
Those set of prompts will work well with this model.
I have done up 2 videos to share my work flow:
Part 1: Setup:
Part 2: Image Generation
Samples I shared are mostly Image to Image results.
Use Control Net models to get closer results.
Specifically I use Canny Model more often than others.
Please do not use this model for illegal means, for unauthorized use of IP for profits, super impose real human faces onto nude bodies etc.
Art used as base to develop Fan Art are from world renowned Artists:
1) ZIPCY: https://twitter.com/zipcy88
2) KyuYongEom(KYE): https://twitter.com/KyuYongEom
Art referenced are NFTs from the SuperNormal NFT Ecosystem:
1) opensea.io/collection/supernormalbyzipcy
2) opensea.io/collection/dg-origins
I own the exact NFT or versions of the Art used as reference.
Thanks and hope you find it useful!
Follow me on Twitter for latest Art Generation: https://twitter.com/Vajrabond