Type | |
Stats | 217 |
Reviews | (25) |
Published | Apr 22, 2023 |
Base Model | |
Training | Steps: 1,596 Epochs: 38 |
Trigger Words | Fortnite_Dolph |
Hash | AutoV2 0BD1243284 |
If you make some cool images, please consider sharing them. That is why I make these. :)
I am the Reindeer Czar, so I created my first LORA, of Dolph from Fortnite. This depicts him really well I think.
Latest Description:
Version 2 improves the model very much. No more issue with background, overall more expressive and high quality. 0.5 - 0.7 weight for LORA is good. Euler a and DPM++ seem to be best sampling. Sample around 50 seems good too, more can be better too.
You can add tags like skydiving, sitting, open mouth, smiling, holding weapon, lightsaber to use for some dynamic situations. You can also add Widow's Promise, Sword to get that back bling on him.
If you like my models, please consider a tip, to help me train more models!
https://ko-fi.com/reindeerczar
Deprecated Version 1 Description:
Strength for LORA is say, 0.4 to 0.65 to get the good result, if you want a b1ackground.
It was trained on 5600 iterations, so quite much. Add the tags blue gradient background and simple background in the negative tag to get rid of the background better.