Download
1 variant available
fp16 SafeTensor
raw-xs-v1.inpainting.safetensors
Half precision, best balance β’ 3.97 GB
Verified: 3 years ago
.jpeg){kind=tracking}
without hires to gen highly detailed photo
without default asian face
without need too much tag weight, better text understanding
works fine with almost all LORA and TI
[update:0230825]
version 2 (close to sdxl1.0)
Advices
Not require strong prompt weight adjustments. Try removing all prompt weights.
Not require Hi-RES. Try big steps (>50steps) and use a DPM++ series sampler.
Asian-style version π LOFI-v4
Fantasy-style version π EPIC-v1
[update: v1]
What raw-xs ?
raw: Realistic Artistic Wizardry
xs: Extra Small
(chatgpt generated)
a little better than sdxl-0.9 οΌXD
based on LOFI_V3 (with sdxl0.9) fine-tuning
Tips
this model may be include wrong sdxl partten π
(for example, in some color modes, human skin will be very oily, You can try different samplers, there will be different effects)