Type | |
Stats | 94 1,636 |
Reviews | (10) |
Published | Mar 15, 2024 |
Base Model | |
Training | Steps: 3,200 Epochs: 20 |
Usage Tips | Clip Skip: 1 Strength: 0.7 |
Trigger Words | ferdinand-clooney, ferdinand-researcher, ferdinand-fugitive, 1boy, solo, male focus, mature male, short hair, brown hair, multicolored hair, brown eyes, facial hair, stubble, animal ears, cat ears, cat boy, cat tail, spotted tail, long sleeves, jacket, white shirt, open clothes, necktie, spotted necktie, collared shirt, belt, pants, formal, suit, muscular male, coat, sideburns,brown pants, brown vest, brown necktie, necktie, spotted necktie, collared shirt, belt, pants, uniform, vest, military, military uniform, facepaint, sleeves rolled up, headset, watch, wristwatch, brown pants,id card, harness, earpiece, tactical clothes, bulletproof vest, walkie-talkie |
Hash | AutoV2 90131CB956 |
Ferdinand Clooney from Arknights
LoRAs are trained on all the images that I could find on the internet, official art and fan art
Preview generated without using ADetailer & Hires. fix
Recommended LoRA Strength (Weight): 0.7-0.8
v1.3 - The dataset has been slightly changed, new images and sprites with other emotions have been added. Trigger Words have been changed and Captions have been edited, this version should be better than other versions as much as possible (I will not claim that this version will be the last!)
v1.2 - slightly better looking hair and face than in v1.1 & v1.0 And added multicolored hair, spotted necktie tokens, but not sure if that helps (Most likely this will be the latest version).
v1.1 - is pretty much the same as v1.0 only softer not as sharp as v1.0 and trained a little differently
v1.0 - the first release, in comparison with other versions, looks worse