模型/aesthetical anime style - V1

aesthetical anime style - V1

|
7/26/2025
|
11:43:16 AM
| Discussion

推薦提示詞

b74_aes

推薦參數

samplers

Euler, DPM2 Karras, DPM++ 2M

steps

20 - 28

cfg

1 - 3.5

resolution

1024x1024, 1216x1600, 880x1104, 832x1176, 1120x848

other models

aesthetical_epoch_3 (6cfbc527c811), AnimeLight-v2-000103 (52ddb365e265), flux1-dev-fp8 (275ef623d3), AnimeLight-v2-000091 (5cb1ac1928f2), glowing_flux (08f9542d54b7), Bright_aesthetical_r1-000002 (0b9f3da140c0)

推薦高解析度參數

upscaler

SwinIR_4x, SwinIR 4x

upscale

1.3 - 1.6

steps

20

denoising strength

0.4 - 0.5

提示

Use with strength 1.4+ when using this LoRA alone, reduce strength to 1 when used with other LoRAs.

Currently tested only on flux dev fp8 model, results on other models unknown.

Recommend pairing with AnimeLight-v2 LoRA for improved lighting effects.

Dataset of 450 aesthetical anime images is available upon request.

創作者贊助

YOU HAVE TO USE IT WITH "b74_aes"

Use with strength of 1.4+ when only using this one lora, reduce to 1 when use with other lora

This lora emphasized on lighting and shadow(anime stlye).

I only tried this on flux dev fp8, not sure how it works on other model.

recommend also using with this lora AnimeLight-v2 - AnimeLightv2 | Stable Diffusion LoRA | Civitai

Will try train again with 1024*1024 and more steps if I could get more buzz.

I picked 450 my most favourite aesthetical anime imgs, feel free to ask me for the dataset and train it yourselves.

my discord: b74

here is the other epoch if you want: aesthetical_epoch_1.safetensors · b74444/style1 at main (huggingface.co)

aesthetical_epoch_2.safetensors · b74444/style1 at main (huggingface.co)

aesthetical_epoch_4.safetensors · b74444/style1 at main (huggingface.co)

貢獻者

上一個
SocaRealism XL - 1.3
下一個
80s Fantasy Movie - Flux V3

模型詳情

模型類型

LORA

基礎模型

Flux.1 D

模型版本

V1

模型雜湊值

554d6e1fcc

訓練詞彙

b74_aes

創作者

討論

log in以發表評論。