一位棕色頭髮、穿棕色高領毛衣的日式少女肖像,站在窗前,具有逼真的光線和柔和的陰影。
一張逼真寫實的照片,描繪一位18歲微笑的日本少女,穿著帶藍色領子和蝴蝶結的白色水手風校服,戴著白色貝雷帽和百褶裙。她有長直的深色頭髮和齊瀏海。
一位日本女性肖像,長長的深色頭髮和閃亮的藍色眼睛,穿著帶有精緻刺繡的優雅深藍色旗袍,站在窗邊,窗外綠意模糊。

推薦提示詞

1 woman, (RAW photo, best quality), close mouth, (realistic, photo-realistic:1.5), an extremely delicate and beautiful, extremely detailed, smile, drooping eyes, 8k, amazing, brown straight hair, japanese idol, ultra-detailed, swept bangs, highres, brown eyes, BREAK 1 beautiful woman, kawaii, looking at viewer, (ultra low-rise jeans:1.2), (swetter blouse:1.4), lipgloss, simple background, cute, (large breasts:1.5), (thigh:1.5), petite, (drooping eyes:1.5), longeyelashes, thin eyebrow, (off-shoulder blouse and skinny jeans:1.4), extremely detailed eyes and face, BREAK (checkerboard floor:1.2), bookcase, indoor, chandelier, window shade, armchair, cloudy, suck thumb

推薦反向提示詞

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)

推薦參數

samplers

DPM++ SDE Karras

steps

35

cfg

11

clip skip

2

resolution

512x768

vae

vae-ft-mse-840000-ema-pruned - original

推薦高解析度參數

upscaler

Latent (nearest), Latent

upscale

2

steps

15

denoising strength

0.62

版本亮點

  • 取樣器: DPM++ SDE Karras

  • 步數: 30 - 35

  • CFG 比例: 11.0 - 11.5

  • 去噪強度: 0.6 - 0.65

  • Clip skip: 2

  • 高解析度升級倍數: 2

  • 高解析度步數: 15 - 18

  • 高解析度升頻器: 潛空間 (最近鄰法)

  • ENSD (Eta noise seed delta): 31337

  • VAE: voidnoise.vae.tuned

  • Embeddings: negative_hand

創作者贊助

如果您喜歡我的作品,請考慮支持我!

欲知更多資訊,請造訪Patreon

如果您喜歡我的作品,請考慮支持我!

欲知更多資訊,請造訪Patreon

本模型的概要 (Overview of this model)

本模型是使用CreativeML OpenRAIL-M授權的訓練模型、SD1.5附加訓練模型,及僅使用這些模型合併製作的模型。
The model will be produced using only the CreativeML OpenRAIL-M licensed training model, the SD1.5 additional training model, and a merged model using only those models.

以寫實風格(F系列)和照片風格(R系列)為基礎,針對人物表現做出專注於寫實的調整,並參考原本預定公開的 voidnoiseMix 系列來製作。
Based on the realism style (F series) and photo style (R series), the figures are adjusted to be drawn specifically for realism, and the work is produced with the voidnoiseMix series.

即使不使用品質系統的 LoRA 或 LyCORIS,也調整至可達到一定程度的細膩表現。
Adjustments are made to achieve a certain degree of detailed expression without the use of quality systems LoRA or LyCORIS.

其他使用的模型等詳細資訊,請參考 Hugging Face 的模型說明頁。
For other detailed information, including models used, please refer to the Hugging Face model card.

https://huggingface.co/konapieces/VoidnoiseCore

推薦設置 (Recommended settings)

詳細內容請查看本模型的版本紀錄(About this version)。

Please check the "About this version" of this model for details.

免責聲明 (Disclaimer)

  • 使用本模型生成的圖片由使用者自行負責,對於由此產生的任何問題或爭議,模型製作者概不負責。

  • The model creator assumes no liability for any problems or disputes related to the images created using this model.

  • 本模型非為成人內容用途設計。生成成人向內容所造成的任何問題,模型製作者均不承擔任何責任。

  • 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.

  • 若發生授權相關問題,本模型可能會在未預告下被刪除,敬請諒解。

  • In the event of any licensing issues, this model may be removed without notice. We appreciate your understanding.

  • 禁止用於犯罪或醫療等專業用途。對於未履行授權的過失,模型製作者不承擔任何責任。

  • 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.

  • 基於 CreativeML OpenRAIL 授權,允許進行模型及衍生模型的銷售,但由於目前為開放存取授權,並不推薦銷售模型。未經作者同意銷售模型所引發的任何問題,模型製作者概不負責。

  • 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.

授權 (License)

本模型為開放存取,所有人皆可使用。CreativeML OpenRAIL-M 授權規範了權利與使用方式。
CreativeML OpenRAIL 授權規定如下:

  1. 禁止使用本模型故意製作或分享非法或有害的輸出或內容。

  2. 作者不主張對你生成的內容擁有任何權利。你可自由使用,且對其使用負責,不得違反授權規定。

  3. 允許重新分發權重,並將模型用於商業或服務。
    但需包含授權中相同的使用限制,並向所有使用者提供 CreativeML OpenRAIL-M 授權副本(請完整且仔細閱讀授權條款)。
    請於此處查看完整授權

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

VAE授權 (VAE License)

隨模型附帶的 VAE 是基於 vae-ft-mse-840000-ema-pruned 製作。
因此,除 kl-f8-anime2CreativeML OpenRAIL-M 授權外,還適用繼承來源 vae-ft-mse-840000-ema-pruned 的 MIT License,請留意適用授權差異。
因此,增加了とーふのかけら作為附加著作權人。
適用授權如下:

版權所有 2022 StabilityAI,附加版權 2023 konapieces
以 MIT 與 CreativeML OpenRAIL-M 授權釋出。
MIT License
CreativeML OpenRAIL-M

製作者 (The creator of this model)

とーふのかけら(konapieces)
twitter: @konapieces
網站: https://lit.link/konapieces

上一個
表現性推理 - v1.0
下一個
Epic Style - 動態姿勢 XL(動畫動作增強 / 細節特效 / 速度線)- v1.0

模型詳情

模型類型

Checkpoint

基礎模型

SD 1.5

模型版本

R1311

模型雜湊值

cfe3cb7308

討論

log in以發表評論。

VoidnoiseCore - R1311 的圖片

基礎模型 圖片

女孩 圖片

寫實主義 圖片

stable diffusion 圖片