CivArchive
    Keanu_V1 | Keanu Charles Reeves | 基努李维斯 | - KEANU_v1.0
    Preview 47956934
    Preview 47957817
    Preview 47958137
    Preview 47958250
    Preview 47958331

    基础模型 majicMIX realistic V7

    使用 HIDIFFUSION

    使用 UPSCALER

    使用 DETAILER


    BASE MODEL majicMIX realistic V7

    USE HIDIFFUSION

    USE UPSCALER

    USE DETAILER


    根据出图类型(肖像、半身、全身)推荐出图类型提示词
    肖像:portrait
    半身:upper body
    全身:full body | standing | walking |

    显卡性能限制无法直出大图,可以用小尺寸出全身图配合upscale+detailer 以防止脸部崩坏


    参数建议:

    推荐固定前三个提示词:keanu,1boy,portrait(根据自己要出的类型更换)

    推荐使用负面提示词
    推荐开启 Hidiffusion

    采样算法:Euler a 或尝试其它
    CLIP SKIP:2
    LoRA强度:0.70.8


    备选提示词:
    male focus | realistic | solo| shirt | jacket | facial hair | looking at viewer | photorealistic | outdoors | sitting | smile | stubble |


    法律免责声明:
    本模型仅限于技术交流与学习用途,不得用于任何商业用途或其他侵犯第三方合法权益的行为。使用本模型生成的内容所导致的任何侵权或法律后果,由使用者自行承担,本人不承担任何责任。


    ======================================================================================================================================================

    • portrait

    • upper body

    • full body | standing | walking

    If your GPU performance is not enough to generate high resolution images, consider generating smaller full-body images and using upscale+detailer to prevent facial distortions.


    Parameter Suggestions:

    • Recommended fixed initial prompts:
      keanu,1boy,portrait (replace "portrait" with the type of image you want: portrait, upper body, or full body).

    • Recommended negative prompts:
      Use detailed negative prompts as needed.

    • Recommended additional settings:

      • Enable Hidiffusion

      • Sampling method: Euler a (or experiment with others).

      • CLIP SKIP: Set to 2

      • LoRA strength: Use 0.7 or 0.8


    Optional Prompts:

    You can use these additional prompts based on your preferences:
    male focus | realistic | solo | shirt | jacket | facial hair | looking at viewer | photorealistic | outdoors | sitting | smile | stubble |


    Legal Disclaimer:
    This model is strictly intended for purposes of technical exchange and learning. It is prohibited to use this model for any commercial purposes or activities that infringe upon the legal rights of third parties. The user assumes full responsibility for any infringement or legal consequences arising from the use of this model. The creator assumes no liability for such actions.

    Description

    LORA
    SD 1.5

    Looks like we don't have an active mirror for this file right now.

    CivArchive is a community-maintained index — we catalog mirrors that volunteers upload to HuggingFace, torrents, and other public hosts. Looks like no one has uploaded a copy of this file yet.

    Some files do get recovered over time through contributions. If you're looking for this one, feel free to ask in Discord, or help preserve it if you have a copy.

    Details

    Downloads
    25
    Platform
    CivitAI
    Platform Status
    Deleted
    Created
    4/24/2025
    Updated
    5/4/2026
    Deleted
    4/24/2025
    Trigger Words:
    keanu

    Files

    KEANU_V1.safetensors

    Mirrors

    HuggingFace (1 mirrors)
    CivitAI (1 mirrors)

    Available On (1 platform)

    Same model published on other platforms. May have additional downloads or version variants.