Downloads · 30 days
0
leoftm/shimabara_yuuhi_lora-weights
shimabara_yuuhi_lora-weights is a machine learning model from leoftm. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as creativeml-openrail-m.
Downloads · 30 days
0
Access
Public
Updated Sep 3, 2024
Repo size
1.8 GB
Likes
1
Public
Click a slice to open those files.
.safetensors915 MB · 75%
From the Hugging Face model README
update logs<br />
shimabara_yuuhi_neo_ranga_Pony_lora<br /> v2024/09/01 v000.004.043<br /> Lora hashes: "shimabara_yuuhi_neo_ranga_Pony_lora_v20240901-weights_epoch_28+43: 24f2776042b8", <br /> changed v000.003.037→v000.004.043<br /> Formally support tag “Joel (neo ranga)”.<br /> ADD study images to support “Joel (neo ranga)”.<br /> MORE Manual correction of some of the TAGs.<br /> epoch 31→epoch mixed 28+43.<br /> ADetailer is no longer necessary due to the model update.<br /> In the Hires. fix, use "DPM++ 2M" for "Hires sampling method" and specify "Denoising strength" around "0.4".<br />
shimabara_yuuhi_spmrgr01_lora-weights<br /> 2023/06/23 This version uses SuperMarger to correct the magnification and limb collapse.<br /> <br /> shimabara_yuuhi_lora-weights<br /> 2023/06/23 Incorrect metadata has been corrected.<br /> 2023/06/09 Metadata added, no change to study content.<br />
Shimabara_Yuuhi (Neo_ranga) <br /> "sshs_model_hash": "cc03d2aea32e247548eec4ff2e5fdb73c6f62f01d9e4aecdaf1edc4b90efdba5", <br /> "sshs_legacy_hash": "9db54dc5", <br />
option <br /> <lyco:shimabara_yuuhi_spmrgr01_lora-weights:0.8> or<br /> <lyco:shimabara_yuuhi_lora-weights:0.25:1.5><br />
OR <br /> Separate UNet/Text Encoder weights (sd-webui-additional-networks) <br /> UNet Weight 1.5 <br /> TEnc Weight 0.25-1.5<br />
OR<br /> <lora:shimabara_yuuhi_spmrgr01_lora-weights:0.8> or<br /> <lora:shimabara_yuuhi_lora-weights:1.5><br />
sd-webui-additional-networks<br /> https://github.com/kohya-ss/sd-webui-additional-networks.git<br />
extract_lora_from_models.py <br /> https://github.com/kohya-ss/sd-scripts/blob/main/train_network_README-ja.md <br /> Lora saved differences from files studied by DreamBooth using extract_lora_from_models.py. <br />
Used embeddings: NG_DeepNegative_V1_75T [1a3e] <br /> https://civitai.com/models/4629/deep-negative-v1x <br />
Used embeddings: bad_prompt_version2 {"embed:bad_prompt_version2": "6f35e7dd81"} <br /> https://civitai.com/models/55700/badprompt-negative-embedding <br />
sample prompts <br /> <lyco:shimabara_yuuhi_spmrgr01_lora-weights:0.8><br /> shimabara yuuhi, blue black hair,short disheveled bangs,jagged cowlick,long locks,medium hair,thick eyebrows,raised eyebrow,squinting,half opened one eye,sharp yellow eyes,small breasts,parted lips, <br /> wet clothes white loincloth,white sarong,between legs white apron,white ribbon forehead hachimaki,wet clothes white criss-cross halter neck, <br /> 12yo girl tribal red tattoo swirls spin pattern all over body,red body markings,bodypaint,tattoo,full-body tattoo,body writing,chest tattoo,red facepaint,red facial tattoo,arm tattoo,leg tattoo,shoulder tattoo,tribal, <br /> golden anklet,golden armlet,golden bangle,golden bracelet,golden choker, <br />
sample Negative prompts <br /> (worst quality:1.4),(low quality:1.4),(bad_prompt_version2:0.8), <br /> ,short legs,short thighs,parted bangs,blunt bangs,bobbed bangs,extra eyebrows,pointy ears, <br />