--- license: creativeml-openrail-m language: - ja - en library_name: diffusers tags: - art - artwork - girl - stable-diffusion --- # ▼ モデルの詳細 (Model Details)

LastpieceCore_A0621

# ▼ 本モデルの概要 (Overview of this model) 本モデルはCreativeML OpenRAIL-Mライセンスの訓練モデル、SD1.5追加学習モデルのみを使用したマージモデルになります。
柔らかいタッチと強い色彩に重点を置き、前作のlastpieceMix及びpiecepixelMixのタッチに寄せた調整を行っております。
クオリティ系のLoRAやLyCORISを使用せずとも、ある程度精細な表現ができるよう調整しています。

This model will be a merged model, using only the training model and SDXL1.0 additional learning model from the CreativeML OpenRAIL++-M license.
Based on the illustration style, the touch is soft and the colors are strong, and the adjustment is closer to the illustration touch of the lastpieceMix and piecepixelMix.
This model will be a merged model, using only the training model and SD1.5 additional learning model from the CreativeML OpenRAIL-M license.
Adjustments are made to achieve a certain degree of detailed expression without the use of quality systems LoRA or LyCORIS.
# ▼ 推奨設定 (Recommended settings) - Sampler: DPM++ 2M Karras - Step: 35 - 40 - CFG scale: 10 - 11 - Denoising strength: 0.55 - 0.6 - Clip skip: 2 - Hires upscale: 2 - Hires steps: 15 - 20 - Hires upscaler: Latent (nearest) - VAE: lastpiece.vae.brightness or lastpiece.vae.contrast # ▼ 出力サンプル (Sample) ![](images/A0621/logo.png) [Prompt]
``` best quality,masterpiece,highres,beautiful eyes,detailed background, BREAK (1 girl, solo:1.5),bobcut,silver hair,((forest green eyes)),[smile],(off-shoulder frill blouse and tight jeans), BREAK close-up face,portrait,from above, BREAK summer,shiny,daytime in the city ``` [Negative prompt]
``` EasyNegativeV2,[:(negative_hand-neg:1.2):15],(worst quality:1.5),(low quality:1.5),(normal quality:1.5),(monochrome),(grayscale),(watermark),(white letters),signature,username,text,error,(manicure),(nsfw),(earing) ```

[Prompt]
``` best quality,masterpiece,highres,beautiful eyes,detailed background, BREAK (1 girl, solo:1.5),bobcut,silver hair,((wisteria eyes)),[smile],(off-shoulder frill blouse and tight jeans), BREAK portrait,close-up upbody,from above, BREAK summer,shiny,daytime in the city ``` [Negative prompt]
``` EasyNegativeV2,[:(negative_hand-neg:1.2):15],(worst quality:1.5),(low quality:1.5),(normal quality:1.5),(monochrome),(grayscale),(watermark),(white letters),signature,username,text,error,(manicure),(nsfw),(earing) ```

### VAEサンプル (VAE Sample)

---- # ▼ マージ使用モデル (Base model) dreamshaper_6NoVae (Lykon) - https://civitai.com/models/4384
Evt_V4_e10_ema (haor) - https://huggingface.co/haor/Evt_V4-preview
trinart_characters_it4_v1 (Sta, AI Novelist Dev, Bit192, Inc.) - https://huggingface.co/naclbit/trinart_characters_19.2m_stable_diffusion_v1
sdhk_V30 (hakoniwa) - https://civitai.com/models/82813
iroiro-lora (2vXpSwA7) - https://huggingface.co/2vXpSwA7/iroiro-lora
# ▼ VAE使用モデル (VAE base model) vae-ft-mse-840000-ema-pruned (StabilityAI) - https://huggingface.co/stabilityai/sd-vae-ft-mse-original
kl-f8-anime2 (hakurei) - https://huggingface.co/hakurei/waifu-diffusion-v1-4
----

LastpieceCore_A0692

![](images/A0692/logo.png) # ▼ 本モデルの概要 (Overview of this model) 本モデルはCreativeML OpenRAIL-Mライセンスの訓練モデル、SD1.5追加学習モデルのみを使用したマージモデルになります。
柔らかいタッチと強い色彩に重点を置き、前作のlastpieceMix及びpiecepixelMixのタッチに寄せた調整を行っております。
クオリティ系のLoRAやLyCORISを使用せずとも、ある程度精細な表現ができるよう調整しています。

This model will be a merged model, using only the training model and SDXL1.0 additional learning model from the CreativeML OpenRAIL++-M license.
Based on the illustration style, the touch is soft and the colors are strong, and the adjustment is closer to the illustration touch of the lastpieceMix and piecepixelMix.
This model will be a merged model, using only the training model and SD1.5 additional learning model from the CreativeML OpenRAIL-M license.
Adjustments are made to achieve a certain degree of detailed expression without the use of quality systems LoRA or LyCORIS.
# ▼ 推奨設定 (Recommended settings) - Sampler: DPM++ 2M Karras - Step: 35 - 40 - CFG scale: 10 - 11 - Denoising strength: 0.55 - 0.6 - Clip skip: 2 - Hires upscale: 2 - Hires steps: 15 - 20 - Hires upscaler: Latent (nearest) - VAE: lastpiece.vae.brightness or lastpiece.vae.contrast # ▼ 出力サンプル (Sample) [Prompt]
``` absurdres,highres,beautiful eyes,detailed background,best quality, BREAK (1 girl, solo:1.5),bobcut,[smile],(off-shoulder frill blouse and tight jeans), BREAK summer,shiny,daytimne in the city ``` [Negative prompt]
``` EasyNegativeV2,[:(negative_hand-neg:1.2):15],(worst quality:1.5),(low quality:1.5),(normal quality:1.5), (monochrome),(grayscale),(watermark),(white letters),signature,username,text,error,(manicure),(nsfw) ```

---- ### マージ使用モデル (Base model) LastpieceCore_A0621 (konapieces)
epicrealism_pureEvolutionV3 (epinikion) - https://civitai.com/models/25694
LittleStepMix_A (sazyou-roukaku) - https://huggingface.co/sazyou-roukaku/LittleStepMix
----

LastpieceCore_S0680

# ▼ 本モデルの概要 (Overview of this model) 本モデルはCreativeML OpenRAIL-Mライセンスの訓練モデル、SD1.5追加学習モデルのみを使用したマージモデルになります。
柔らかいタッチと強い色彩に重点を置き、前作のlastpieceMix及びpiecepixelMixのタッチに寄せた調整を行っております。
クオリティ系のLoRAやLyCORISを使用せずとも、ある程度精細な表現ができるよう調整しています。

Based on the illustration style, the touch is soft and the colors are strong, and the adjustment is closer to the illustration touch of the lastpieceMix and piecepixelMix.
This model will be a merged model, using only the training model and SD1.5 additional learning model from the CreativeML OpenRAIL-M license.
Adjustments are made to achieve a certain degree of detailed expression without the use of quality systems LoRA or LyCORIS.
# ▼ 推奨設定 (Recommended settings) - Sampler: DPM++ 2M Karras - Step: 35 - 40 - CFG scale: 10 - 11 - Denoising strength: 0.55 - 0.6 - Clip skip: 2 - Hires upscale: 2 - Hires steps: 15 - 20 - Hires upscaler: Latent (nearest) - VAE: lastpiece.vae.brightness or lastpiece.vae.contrast # ▼ 出力サンプル (Sample) [Prompt]
``` absurdres,highres,beautiful eyes,detailed background,best quality, BREAK (1 girl, solo:1.5),bobcut,[smile],(off-shoulder frill blouse and tight jeans), BREAK summer,shiny,daytimne in the city ``` [Negative prompt]
``` EasyNegativeV2,[:(negative_hand-neg:1.2):15],(worst quality:1.5),(low quality:1.5),(normal quality:1.5), (monochrome),(grayscale),(watermark),(white letters),signature,username,text,error,(manicure),(nsfw) ```

LastpieceCore_A0751

![](images/A0751/logo.png) # ▼ 本モデルの概要 (Overview of this model) 本モデルはCreativeML OpenRAIL-Mライセンスの訓練モデル、SD1.5追加学習モデルのみを使用したマージモデルになります。
柔らかいタッチと強い色彩に重点を置き、前作のlastpieceMix及びpiecepixelMixのタッチに寄せた調整を行っております。
クオリティ系のLoRAやLyCORISを使用せずとも、ある程度精細な表現ができるよう調整しています。

This model will be a merged model, using only the training model and SDXL1.0 additional learning model from the CreativeML OpenRAIL++-M license.
Based on the illustration style, the touch is soft and the colors are strong, and the adjustment is closer to the illustration touch of the lastpieceMix and piecepixelMix.
This model will be a merged model, using only the training model and SD1.5 additional learning model from the CreativeML OpenRAIL-M license.
Adjustments are made to achieve a certain degree of detailed expression without the use of quality systems LoRA or LyCORIS.
# ▼ 推奨設定 (Recommended settings) - Sampler: DPM++ 2M Karras - Step: 35 - 40 - CFG scale: 10 - 11 - Denoising strength: 0.55 - 0.6 - Clip skip: 2 - Hires upscale: 2 - Hires steps: 15 - 20 - Hires upscaler: Latent (nearest) - VAE: lastpiece.vae.brightness or lastpiece.vae.contrast # ▼ 出力サンプル (Sample) [Prompt]
``` best quality,masterpiece,absurdres,highres,dynamic lighting,intricate detailed,beautiful eyes, BREAK (1 girl, solo:1.5), slicked back,(grape hair:1.3),khaki eyes,(arms behind back),close-up upper body, (bare-shoulder blouse and white tight pants), BREAK [backlighting],(looking of viewer),sunshine,blue sky,cloud, (outdoor, daytime, beach),(wet hair:1.2),(splashing water:1.2),(droplets of water:1.1),looking at viewer, summer,chromatic aberration ``` [Negative prompt]
``` EasyNegativeV2,[:(negative_hand-neg:1.2):15],(worst quality:1.5),(low quality:1.5),(normal quality:1.5), (monochrome),(grayscale),(watermark),(white letters),signature,username,text,error,(manicure),(nsfw) ```

[Prompt]
``` best quality,masterpiece,absurdres,highres,dynamic lighting,intricate detailed,beautiful eyes, BREAK (1 girl, solo:1.5), slicked back,(violet hair:1.3),smoke eyes,(arms behind back),close-up upper body, (bare-shoulder blouse and white tight pants), BREAK [backlighting],(looking of viewer),starry sky,(outdoor, night, river),(wet hair:1.2), (splashing water:1.2),(droplets of water:1.1),looking at viewer,summer,chromatic aberration ``` [Negative prompt]
``` EasyNegativeV2,[:(negative_hand-neg:1.2):15],(worst quality:1.5),(low quality:1.5),(normal quality:1.5), (monochrome),(grayscale),(watermark),(white letters),signature,username,text,error,(manicure),(nsfw) ```

---- ### マージ使用モデル (Base model) LastpieceCore_A0692 (konapieces)
FlexWaifuRainbow (Ai-tensa) - https://huggingface.co/Ai-tensa/FlexWaifu
BrainDance_BD051 (sazyou-roukaku) - https://civitai.com/models/102753/braindance
----

LastpieceCore_S1018

![](images/S1018/logo.png) # ▼ 本モデルの概要 (Overview of this model) 本モデルはCreativeML OpenRAIL-Mライセンスの訓練モデル、SD1.5追加学習モデルのみを使用したマージモデルになります。
柔らかいタッチと強い色彩に重点を置き、前作のlastpieceMix及びpiecepixelMixのタッチに寄せた調整を行っております。
クオリティ系のLoRAやLyCORISを使用せずとも、ある程度精細な表現ができるよう調整しています。

This model will be a merged model, using only the training model and SDXL1.0 additional learning model from the CreativeML OpenRAIL++-M license.
Based on the illustration style, the touch is soft and the colors are strong, and the adjustment is closer to the illustration touch of the lastpieceMix and piecepixelMix.
This model will be a merged model, using only the training model and SD1.5 additional learning model from the CreativeML OpenRAIL-M license.
Adjustments are made to achieve a certain degree of detailed expression without the use of quality systems LoRA or LyCORIS.
# ▼ 推奨設定 (Recommended settings) - Sampler: DPM++ 2M Karras - Step: 35 - 40 - CFG scale: 10 - 11 - Denoising strength: 0.55 - 0.6 - Clip skip: 2 - Hires upscale: 2 - Hires steps: 15 - 20 - Hires upscaler: Latent (nearest) - VAE: lastpiece.vae.brightness or lastpiece.vae.contrast # ▼ 出力サンプル (Sample) [Prompt]
``` kawaii, cute,(1 girl,solo:1.3),moss green eyes:1.5,[wrathful],parchment hair, long hair, bangs, hair_ornament, snapback hat,large breasts, BREAK best quality,8k,raw photo,realistic,absurdres,highres,ultra detailed,beautiful eyes, BREAK kneel,bakery,theater,hen house ``` [Negative prompt]
``` EasyNegativeV2,[:(negative_hand-neg:1.2):15],(worst quality:1.5),(low quality:1.5),(normal quality:1.5), (monochrome),(grayscale),(watermark),(white letters),signature,username,text,error,(manicure),(nsfw) ```

[Prompt]
``` kawaii, cute,(1 girl,solo:1.3),orange_eyes:1.5,[surprised],silver hair, long hair, bangs, scoop neck top,large breasts, BREAK best quality,8k,raw photo,realistic,absurdres,highres,ultra detailed,beautiful eyes, BREAK blow a kiss,museum,shop,runway ``` [Negative prompt]
``` EasyNegativeV2,[:(negative_hand-neg:1.2):15],(worst quality:1.5),(low quality:1.5),(normal quality:1.5), (monochrome),(grayscale),(watermark),(white letters),signature,username,text,error,(manicure),(nsfw) ```

---- ### マージ使用モデル (Base model) LastpieceCore_A0692 (konapieces)
VoidnoiseCore_R0829 (konapieces)
----

LastpieceCore_S1624

![](images/S1624/logo.png) # ▼ 本モデルの概要 (Overview of this model) 本モデルはCreativeML OpenRAIL-Mライセンスの訓練モデル、SD1.5追加学習モデルのみを使用したマージモデルになります。
LastpieceCore S1018を微調整し、更に立体感や光の描写、人物の精細さを向上させたモデルになります。
更に、S1018の強みであった、指の崩壊の大幅な低減も継承しており、非常に安定性の高いモデルとなっております。
本モデルで使用しているベースモデルは、私が公開しているモデルのみで構成しております。

This model will be a merged model, using only the training model and SDXL1.0 additional learning model from the CreativeML OpenRAIL++-M license.
LastpieceCore S1624 is a refined version of LastpieceCore S1018, enhancing three-dimensionality, light rendition, and detailing of individuals.
Moreover, it maintains S1018's capability of significantly minimizing finger collapse, rendering it an exceptionally stable model.
The base model used in this version comprises only models that I have publicly shared.
# ▼ 推奨設定 (Recommended settings) - Sampler: DPM++ 2M Karras - Step: 35 - 40 - CFG scale: 10 - 11 - Denoising strength: 0.55 - 0.6 - Clip skip: 2 - Hires upscale: 2 - Hires steps: 15 - 20 - Hires upscaler: Latent (nearest) - VAE: lastpiece.vae.brightness or lastpiece.vae.contrast # ▼ 出力サンプル (Sample) [Prompt]
``` 4k wallpaper,highres,kawaii,cute,1 girl, solo,ecru hair, french braid, bangs,black eyes,dutch angle, vexed,High-neck blouse with a pleated front and ruffled collar,large breasts, BREAK simple background,bokeh ``` [Negative prompt]
``` EasyNegativeV2,negative_hand-neg,(worst quality:1.5),(low quality:1.5),(normal quality:1.5),(monochrome),(grayscale), (watermark),(white letters),signature,username,text,error,(manicure),(nsfw) ```

[Prompt]
``` 4k wallpaper,highres,kawaii,cute,1 girl, solo,azure hair, lob, bangs,brown eyes,from front,impatient, Oversized cardigan with patchwork details,large breasts, BREAK simple background,bokeh ``` [Negative prompt]
``` EasyNegativeV2,negative_hand-neg,(worst quality:1.5),(low quality:1.5),(normal quality:1.5),(monochrome),(grayscale), (watermark),(white letters),signature,username,text,error,(manicure),(nsfw) ```

# 免責事項 (Disclaimer) - 本モデルを使用して作成された画像に関しては、個々の利用者に委ねておりますので、生成された画像に関する如何なる問題や係争について、モデル製作者は一切の責任を負いません。 - The model creator assumes no liability for any problems or disputes related to the images created using this model. - 本モデルはアダルトコンテンツを目的とした用途を想定しておりません。成人向けコンテンツを生成し、発生した問題についてはモデル製作者は一切の責任を負いません。 - This model is not intended for use with adult content. The model creator assumes no liability for any problems that may occur as a result of generating adult-oriented content. - ライセンスに関して問題が発生した場合は、本モデルを予告なく削除させて頂く可能性があります。ご了承ください。 - In the event of any licensing issues, this model may be removed without notice. We appreciate your understanding. - 犯罪への利用や医療用などの専門的な用途への使用は禁止されております。ライセンス不履行による過失については、モデル製作者は一切の責任を負いません。 - Use for criminal offenses or for professional purposes such as medical use is prohibited. The model maker is not liable for any negligence due to non-fulfillment of the license. - CreativeML OpenRAIL ライセンスの特性上、モデル及び派生モデルにおける販売を許可しておりますが、現状オープンアクセスライセンスである為、モデルの販売は推奨致しません。著作者に無断でモデル販売を行った際に生じたいかなる問題もモデル製作者は一切責任を負いません。 - The CreativeML OpenRAIL license permits the sale of models and derivatives, but does not recommend the sale of models because it is currently an open access license. The creator of the model will not be held responsible for any problems that may arise from the sale of the model without the author's permission. --- # モデルライセンス (Model License) このモデルはオープンアクセスであり、すべての人が利用できます。CreativeML OpenRAIL-M ライセンスにより、権利と使用方法がさらに規定されています。
CreativeML OpenRAIL ライセンスでは、次のことが規定されています。
1. モデルを使用して、違法または有害な出力またはコンテンツを意図的に作成または共有することはできません。
2. 作成者は、あなたが生成した出力に対していかなる権利も主張しません。あなたはそれらを自由に使用でき、ライセンスに設定された規定に違反してはならない使用について説明責任を負います。
3. 重みを再配布し、モデルを商用および/またはサービスとして使用することができます。
その場合、ライセンスに記載されているのと同じ使用制限を含め、
CreativeML OpenRAIL-M のコピーをすべてのユーザーと共有する必要があることに注意してください。 (ライセンスを完全にかつ慎重にお読みください。)
[こちら](https://huggingface.co/spaces/CompVis/stable-diffusion-license)からライセンス全文をお読みください。
This model is open access and available to all, with a CreativeML OpenRAIL-M license further specifying rights and usage. The CreativeML OpenRAIL License specifies:
1. You can't use the model to deliberately produce nor share illegal or harmful outputs or content
2. The authors claims no rights on the outputs you generate, you are free to use them and are accountable for their use which must not go against the provisions set in the license
3. You may re-distribute the weights and use the model commercially and/or as a service.
If you do, please be aware you have to include the same use restrictions as the ones in the license and share a copy of the CreativeML OpenRAIL-M to all your users (please read the license entirely and carefully)
Please read the full license [here](https://huggingface.co/spaces/CompVis/stable-diffusion-license)
# VAEライセンス(VAE License) また、同梱しているVAEは、vae-ft-mse-840000-ema-prunedをベースに作成されております。
その為、kl-f8-anime2のCreativeML OpenRAIL-M以外に、継承元である vae-ft-mse-840000-ema-prunedのMIT Licenseも適用となる為、適用ライセンスが異なる点を留意してください。
それに伴い、とーふのかけらが追加著作者として追記しています。
適用ライセンスは以下になります。
The included VAE is based on vae-ft-mse-840000-ema-pruned.
Please note that in addition to CreativeML OpenRAIL-M, the inherited MIT License is also applicable.
With this, konapieces has been added as an additional author.
The applicable licenses are as follows:
Copyright 2022 StabilityAI, Additional Copyright 2023 konapieces
Release under the MIT and CreativeML OpenRAIL-M licenses.
MIT License
CreativeML OpenRAIL-M --- # 製作者 (The creator of this model) とーふのかけら(konapieces)
twitter: @konapieces
Website: https://lit.link/konapieces ---