datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
tmpmjnj384384imagenet1kk1921kk imagenet with auradiffusion vae 192x192
see https://huggingface.co/datasets/AiArtLab/imagenet1kk192/blob/main/imagenet-1kk/sdxs1b-imagenet.ipynb
7681152576640384dataset640imagenet-1kkUsage: https://huggingface.co/AiArtLab/sdxs/blob/main/imagenet.ipynb
640_mjnj640dspai_art_np
Dataset Card for "ai_art_np"
More Information needed
aiart_channel_nai3_geachuaesthetic_6k1024
MidJourney
NijiJourney
E-Shushu
Compressed by a factor of 64 pixels in JPEG, 97 quality, maximum side length of 1024.
Mixed labeling using different models:
Human prompts in MJ/NJ
Long captions (LLaVA)
Short captions (LLaVA + LLaMA)
Medium captions (Moondream)
dtasettardataset7681024vaelora-Asbestos_Ceiling
Lora - Asbestos_Ceiling
석면 천장 로라 파일
!!사용법!!
그냥 T2I에서 로라 넣고 돌리면 벽까지 침범을 당해서 타율이 매우 떨어짐
천장 쪽만 인페인트해서 돌려야 타율이 좋음
디노이즈 강도 : 0.5
<lora:Asbestos Ceiling:2.0>
다운로드
AI-ArtTools-Pack
AI ArtTools Pack v1.0 — 372 Styles / 23 Categories
Developer and artist utility pack for Stable Diffusion XL.
Not for generating pretty pictures — for generating usable production assets.
Compatible with Style Grid Organizer extension.
Contents
372 prompt styles across 23 categories
CSV format (Forge/A1111 compatible)
Covers the full production pipeline from rough concept to final asset
Categories
Category
Count
Purpose
ASSET
41
Weapons, props, UI… See the full description on the dataset page: https://huggingface.co/datasets/Kazzze/AI-ArtTools-Pack.576dataset576_10ksampleSample: https://huggingface.co/datasets/AiArtLab/dataset576_10ksample/blob/main/Untitled.ipynb
wan21dtasettar23tstdatasetlora-Hanbok_LoRA_V2
Lora - Hanbok_LoRA_V2
한복 로라 파일
예시 프롬프트
(masterpiece, best quality:1.2), 1girl, solo, <lora:Hanbok_LoRA_V2:0.8>, hanbok, korean_clothes, smile, best ratio four finger and one thumb, looking_at_viewer, cowboy_shot, (white background), (simple background)
Negative prompt: EasyNegative, extra fingers,fewer fingers, watermark, text, animal_ears, japanese_clothes, kimono, chinese_clothes
Steps: 20, Sampler: DPM++ 2M Karras, CFG scale: 10, Size: 640x960, Model: Counterfeit-V2.5… See the full description on the dataset page: https://huggingface.co/datasets/AIARTCHAN/lora-Hanbok_LoRA_V2.