CivArchive
    ip-adapter-plus_sd15 - ip-adapter-plus_sdxl_vit
    Preview 6517989

    Credit to https://huggingface.co/h94/IP-Adapter/tree/main/models

    Description

    we present IP-Adapter, an effective and lightweight adapter to achieve image prompt capability for the pre-trained text-to-image diffusion models. An IP-Adapter with only 22M parameters can achieve comparable or even better performance to a fine-tuned image prompt model. IP-Adapter can be generalized not only to other custom models fine-tuned from the same base model, but also to controllable generation using existing controllable tools. Moreover, the image prompt can also work well with the text prompt to accomplish multimodal image generation.

    FAQ

    Comments (3)

    codegixJun 23, 2024· 3 reactions
    CivitAI

    Describe please

    PinkywDreamsJul 30, 2024

    have you figured it out lol

    xia1740Nov 23, 2025

    It helps you keep the character, face, and style consistent across images.
    There are different versions of IP-Adapter depending on what you want to control.
    and... they all needs an image encoder to work, which simply reads your reference image so IP-Adapter can use it.

    Controlnet
    SDXL 1.0
    by Gametesterbuz
    Download (Beta) View on CivitAI

    Details

    Downloads
    8,942
    Platform
    CivitAI
    Platform Status
    Available
    Created
    2/11/2024
    Updated
    7/11/2026
    Deleted
    -

    Files

    ipAdapterPlusSd15_ipAdapterPlusSdxlVit.safetensors

    Size:
    808.26 MB
    SHA256:
    677ad8860204f7d0bfba12d29e6c31ded9beefdf3e4bbd102518357d31a292c1

    Mirrors

    HuggingFace (75 mirrors)
    CivitAI (2 mirrors)

    Available On (1 platform)

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

    SeaArt
    ip-adapter-plus_sd15 - ip-adapter-plus_sdxl_vit