Applicable to: picture books, banner illustrations and other artistic creations
Please send us more pictures, thanks!
wechat: V1olife
Reference template
Positive prompt words: Example: 1girl, black eyes, long hair, super precise depiction, flowers, multiple colors, high definition, Rich in intricate details, profile picture,
Negative prompt words: (worst quality: 2), (low quality: 2), Flat, dim, bad-artist, nsfw, badhandv4, EasyNegative, (worst quality, low quality), (fused fingers, bad structure), ((Blurred face, fused face)), lowres, bad anatomy, bad hands, ((monochrome)), ((grayscale)) watermark,
Model: SDXL official version_sdxl_1.0 |
VAE: automatic
LoRa weight: 0.9~1
Size: 1024x1024 Or other ratios (9:16, 4:3)
Sampling method: Euler a, DPM, etc.
Sampling steps: 30
CLIP: 2
CFG: 7
Image raw image recommended weight 1~1.3
Description
FAQ
Comments (4)
Awesome stuff, well done! Thanks!
再来支持一波，少有的图生图用了instantid后还能继承笔触的插画lora，有什么诀窍吗？为啥大部分插画lora图生图用instantid后笔触效果都消失了（同参数下），就你的还有那种笔触颗粒感
可能是我的训练集这种笔触比较突出
Hello, I see that in your parameters, there is also a lora: ABS_flat_Illustration, but now this model seems to be invalid, is there any other way to share it
Details
Files
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.