I made v2.0 with better training parameters and bigger data set




















Hello,
You can use this Lora to create any type of fantasy hero, especially with any type of armors.
Use trigger word “f4nt4nsy style” to activate full potential of this lora.
I made v2.0 with better training parameters and bigger data set
Lora weight: 0.6-0.8
Sampler: DPM++ 2M Karras or DPM++ 2M SDE Karras
Steps: 20-30
Highres. Fix is recommended to get best result
Denoising strength: 0.3-0.5
CFG scale: 5-7
Recommended model: ReV Animated
Lora weight: 0.6-0.8
Sampler: DPM++ 2M Karras or DPM++ 2M SDE Karras
Steps: 35
Highres. Fix is recommended to get best result
Denoising strength: 0.6-0.7
CFG scale: 7
Recommended model: ReV Animated
I appreciate any feedback so I can deliver better version in the future.
I made v2.0 with better training parameters and bigger data set
1. The rights to reposted models belong to original creators.
2. Original creators should contact SeaArt.AI staff through official channels to claim their models. We are committed to protecting every creator's rights. Click to Claim
