emoji-xl

🐣 새 업데이트를 받으려면 저를 팔로우하세요 https://twitter.com/camenduru
🔥
우리 디스코드 서버에 참여하세요 https://discord.gg/k5BwmmvJJU
🥳
제 패트리온 커뮤니티에 참여하세요 https://patreon.com/camenduru

모델 Colab: https://github.com/camenduru/ios-emoji-xl-model-colab
모델 미러: https://huggingface.co/camenduru/ios-emoji-xl/blob/main/ios_emoji_xl_v2_lora_webui.safetensors
모델 데이터셋: https://huggingface.co/camenduru/ios-emoji-xl/blob/main/dataset_160x160_images.zip
160x160 픽셀 이모지 제공에 감사합니다: https://github.com/samuelngs/apple-emoji-linux ❤
감사합니다: https://replicate.com ❤

학습 로그:

Trained with 160x160 pixel ios v16.4 emojis 😋

GPU = Nvidia A40 (Large) at https://replicate.com
Num examples = 4129
Num batches each epoch = 1033
Num Epochs = 1
Instantaneous batch size per device = 4
Total train batch size (w. parallel, distributed & accumulation) = 4
Gradient Accumulation steps = 1
Total optimization steps = 1000
Total Run time: 45.46 minutes
Total Cost: $1.98

Replicate LoRA를 WebUI LoRA로 변환기

• 감사합니다:

• https://github.com/ignacfetser ❤

• huggingface/diffusers#2326 ❤

• https://github.com/harrywang/finetune-sd/blob/main/convert-to-safetensors.py ❤

pip install safetensors==0.3.3

import re
from safetensors.torch import load_file, save_file
checkpoint = load_file('/content/ui/models/Lora/ios_emoji_xl_v2_lora.safetensors')
new_dict = dict()
for idx, key in enumerate(checkpoint):
    new_key = re.sub('\.processor\.', '_', key)
    new_key = re.sub('mid_block\.', 'mid_block_', new_key)
    new_key = re.sub('_lora.up.', '.lora_up.', new_key)
    new_key = re.sub('_lora.down.', '.lora_down.', new_key)
    new_key = re.sub('\.(\d+)\.', '_\\1_', new_key)
    new_key = re.sub('to_out', 'to_out_0', new_key)
    new_key = 'lora_unet_' + new_key
    new_dict[new_key] = checkpoint[key]
save_file(new_dict, 'ios_emoji_xl_v2_lora_webui.safetensors')

아이디어 제공에 감사합니다: fofr ❤
fofr의 모델: https://twitter.com/fofrAI/status/1698741974835065171