CivArchive
    PornMaster Krea2 AnimeToReal - V1
    NSFW
    Preview 145246582
    Preview 145246591
    Preview 145246586
    Preview 145246585
    Preview 145246793
    Preview 145246794
    Preview 145246796
    Preview 145246797
    Preview 145246800
    Preview 145246801

    模型介紹為中英雙語,中文使用者可以關閉翻譯。

    PornMaster 色情大師-Krea2

    PornMaster Krea2 AnimeToReal Workflows

    可使用@AIGC_Singularity 所製作的工作流,然後將他的lora替換成我的lora: Krea2_Anything2RealCharacters-V3-Workflows

    (工作流中的插件可能有bug,當多次切換不同lora使用時,工作流會卡住無法運行,必須重啟comfyui。)

     

    也可使用其他的動漫到寫實工作流。

     

    Lora權重1,無須觸發詞即可轉換圖片。

    簡單的描述人種、年齡、髮色、眼睛視角、表情、拍攝視角、姿勢,效果會更好。

    無法在100%保持一致性的情況下,將動漫轉換成真實,轉換時可能產生一些偏移。

    如果使用巨大頭部的卡通人物進行轉換,生成的真實圖片就會是大頭人物。

    已經在我自己訓練的真人人物lora測試過,可以使用真人人物lora來替換角色的臉。

    可透過攝影風格的lora來改變風格。

    圖片轉換後如果還不夠真實感,可以進行第二次轉換。

     

    Krea2解除審查時容易產生液體,可使用以下lora消除液體:

    Wetness Slider 、Cum Slider

     

    以下是觸發詞,但是不一定需要使用:

    transform the image to realistic photograph.

    transform the image to Semi-realistic photograph.

     


    You can use the workflow created by @AIGC_Singularity and replace their LoRA with mine: Krea2_Anything2RealCharacters-V3-Workflows

    (The plugin in the workflow may have a bug. When switching between different LoRAs multiple times, the workflow may freeze and become unresponsive. You will need to restart ComfyUI to get it working again.)

    You can also use other anime-to-realism workflows.

    Set the LoRA weight to 1. No trigger words are required to convert images.

    For better results, provide simple descriptions of the character's ethnicity, age, hair color, eye direction, expression, camera angle, and pose.

    It is not possible to convert anime characters into realistic images while maintaining 100% consistency. Some deviations may occur during the conversion process.

    If you convert cartoon characters with oversized heads, the resulting realistic images will also feature oversized heads.

    I have tested this with my own trained LoRAs of real people. You can use a LoRA of a real person to replace a character's face.

    You can also change the style by using photography-style LoRAs.

    If the converted image still doesn't look realistic enough, you can run it through the conversion process a second time.

    Krea2 tends to generate unwanted fluids when its content restrictions are removed. You can use the following LoRA to eliminate them:

    Wetness Slider 、Cum Slider

     

     

    The following are trigger words, but they are not necessarily required:

    transform the image to realistic photograph.

    transform the image to Semi-realistic photograph.

    我的其他檢查站和Lora。

    My other checkpoints and Lora.

    --

    我的tensorhub。

    我的My seaart。

    My tensorhub.

    My My seaart.

    我已將模型上傳至runninghub。

    I have uploaded the model to runninghub.

    PornMaster_Krea2_AnimeToReal_V1:

    https://www.runninghub.ai/zh-cn/model/public/2108896794175447041/?inviteCode=rh-v1304

     

    不要問我如何安裝的問題與comfyui如何使用。

    客製化lora:我的Telegram ID:@iamddtla0620

    我的微信ID:iamddtla

    我的line ID:iamddtla

    時間寶貴,請直接說明來意,例如:訂製lora.

    Do not ask me questions about how to install it or how to use ComfyUI.

    Customized lora: My Telegram ID: @iamddtla0620

    My WeChat ID: iamddtla

    My Line ID: iamddtla

    Time is precious, please state your intention directly, for example: customized LORA.

    Description

    PornMaster Krea2 AnimeToReal Workflows

    可使用@AIGC_Singularity 所製作的工作流,然後將他的lora替換成我的lora: Krea2_Anything2RealCharacters-V3-Workflows

    (工作流中的插件可能有bug,當多次切換不同lora使用時,工作流會卡住無法運行,必須重啟comfyui。)

    也可使用其他的動漫到寫實工作流。

    Lora權重1,無須觸發詞即可轉換圖片。

    簡單的描述人種、年齡、髮色、眼睛視角、表情、拍攝視角、姿勢,效果會更好。

    無法在100%保持一致性的情況下,將動漫轉換成真實,轉換時可能產生一些偏移。

    如果使用巨大頭部的卡通人物進行轉換,生成的真實圖片就會是大頭人物。

    已經在我自己訓練的真人人物lora測試過,可以使用真人人物lora來替換角色的臉。

    可透過攝影風格的lora來改變風格。

    圖片轉換後如果還不夠真實感,可以進行第二次轉換。

    Krea2解除審查時容易產生液體,可使用以下lora消除液體:

    Wetness Slider 、Cum Slider

    以下是觸發詞,但是不一定需要使用:

    transform the image to realistic photograph.

    transform the image to Semi-realistic photograph.

    You can use the workflow created by @AIGC_Singularity and replace their LoRA with mine: Krea2_Anything2RealCharacters-V3-Workflows

    (The plugin in the workflow may have a bug. When switching between different LoRAs multiple times, the workflow may freeze and become unresponsive. You will need to restart ComfyUI to get it working again.)

    You can also use other anime-to-realism workflows.

    Set the LoRA weight to 1. No trigger words are required to convert images.

    For better results, provide simple descriptions of the character's ethnicity, age, hair color, eye direction, expression, camera angle, and pose.

    It is not possible to convert anime characters into realistic images while maintaining 100% consistency. Some deviations may occur during the conversion process.

    If you convert cartoon characters with oversized heads, the resulting realistic images will also feature oversized heads.

    I have tested this with my own trained LoRAs of real people. You can use a LoRA of a real person to replace a character's face.

    You can also change the style by using photography-style LoRAs.

    If the converted image still doesn't look realistic enough, you can run it through the conversion process a second time.

    Krea2 tends to generate unwanted fluids when its content restrictions are removed. You can use the following LoRA to eliminate them:

    Wetness Slider 、Cum Slider

    The following are trigger words, but they are not necessarily required:

    transform the image to realistic photograph.

    transform the image to Semi-realistic photograph.

    FAQ

    LORA
    Krea 2

    Details

    Downloads
    594
    Platform
    CivitAI
    Platform Status
    Available
    Created
    10/10/2026
    Updated
    10/11/2026
    Deleted
    -
    Trigger Words:
    transform the image to realistic photograph.
    transform the image to Semi-realistic photograph.

    Files

    Workflow.zip

    Mirrors

    CivitAI (1 mirrors)

    PornMaster_Krea2_AnimeToReal_V1.safetensors