LORA
SDXL 1.0
Trained Words
my-nut-scene
About this model
Recommended weight: 1
Sampler：DPM++ 2M SDE
Schedule type：Karras
Steps：20
Hires. fix：R-ESRGAN 4x+ Anime6B
Magnification：2~2.2（It's safe between these two levels, but it's bad if it's beyond this level）
Width and Height：1280×720、736×1308
CFG Scale：7.5
Judging from the loss curve of this training, the convergence is pretty good. But I don't know why an error occurs when the batch size is greater than 1. It should be because of insufficient video memory, but I can't solve it by adjusting other parameters. Does anyone know what the reason is? Please tell me, thank you
Tags
Related Models
Similar AI models you may like
Checkpoint
SDXL 1.0
Juggernaut XL
⭐ 0.0
⬇ 1,514,146
LORA
Pony
Not Artists Styles for Pony Diffusion V6 XL
⭐ 0.0
⬇ 648,297
Checkpoint
SDXL 1.0
epiCRealism XL
⭐ 0.0
⬇ 529,243
Checkpoint
SDXL 1.0
ControlNetXL (CNXL)
⭐ 0.0
⬇ 308,850
Checkpoint
SDXL 1.0
iNiverse Mix(SFW & NSFW)
⭐ 0.0
⬇ 303,491
LORA
ZImageTurbo
Hands XL + SD 1.5 + F1D + Pony + Illustrious + zit
⭐ 0.0
⬇ 287,528
Checkpoint
SDXL 1.0
CyberRealistic XL
⭐ 0.0
⬇ 219,660
LORA
Anima
Velvet's Mythic Fantasy Styles | Flux + Pony + illustrious
⭐ 0.0
⬇ 206,685