Type | |
Stats | 612 |
Reviews | (109) |
Published | Jan 20, 2023 |
Base Model | |
Training | Steps: 800 |
Hash | AutoV2 8C04DFFE67 |
This hypernetwork was trained on AnythingV3, so it should work pretty well with any or almost any other anime-based model.
Showcase images was generated with AnythingV3 and AbyssOrangeMix2_hard.
My prompts for experemintation was pretty simple, so i recommend to begin with this parameters:
Prompt:
masterpiece, character_name standing menacingly on a dark background with lightnings behind him, thick black outline
Negative:
(bad_prompt_version2:0.7), low quality, close up, old, lowres, text, error, (cropped:1.2), worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, black and white, monochrome, censored, (out of frame:1.3)
Euler A, 512x512, CFG 7-8
As soon as you understand for yourself how to get generations with consistent quality you will able to experiment wIth it properly.
...or you just can stop reading this lame stuff and go for punching this "generate" button.
Anyway, feel free and enjoy!