VIP Transformation (Wan2.1 I2V LoRA)

    vip_50_epochs.safetensors LORA / Wan Video

    Model Information
    Model Name
    VIP Transformation (Wan2.1 I2V LoRA)
    Version
    v1.0
    Creator
    Remade
    Size
    342.61 MB
    Downloads
    555
    Trigger
    v1p red carpet transformation
    Torrent Details
    BTIH
    5881A64EF653A3B542CCD63CDC228938994B310E
    BTMH
    149007522DC4C2D0D81396DBCA55DD3DBB4B0F306E1B2A3422F25865AAC42B9A
    SHA256
    6A802FC04D8325BBDDC31FBB329B15115DE1980DCF6E0AB281E9BDEF712C9280
    Upload Date
    about a year ago
    Uploader
    CivitasBay.org
    Status
    Not currently seeded — request it
    0 Seeders
    1 Peers
    Info

    Request a Wan2.1 LoRA on our Discord and we will train and open-source it for free.

    Join our Discord to generate videos of the VIP Transformation LoRA for free.

    Wan2.1 14B I2V 480p v1.0:

    Trained on 35 seconds of video comprised of 7 short clips (each clip captioned separately) of people undergoing a VIP transformation. This was trained on the Wan.21 14B I2V 480p model.

    The trigger word is: 'v1p red carpet transformation'

    See below for some prompt examples that worked well for me. You can also check the videos I've posted here for the captions that were used to generate them. For each video the input image is just the first frame.

    Recommended Settings:

    LoRA strength = 1.0

    Embedded guidance scale = 6.0

    Flow shift = 5.0

    Here's a link to the Wan2.1 I2V LoRA inference workflow I used to generate these videos: https://huggingface.co/Remade/Squish/blob/main/workflow/wan_img2video_lora_workflow.json

    This is a slight modification to Kijai's version, with the main difference being the addition of the WanVideo Lora Select node, connected to the 'lora' field of the WanVideo Lora Select node. Find Kijai's original workflow here:
    https://github.com/kijai/ComfyUI-WanVideoWrapper/blob/main/example_workflows/wanvideo_480p_I2V_example_02.json

    Check out all our LoRAs on our page: https://app.remade.ai/

    Prompt Examples:

    The video begins with an image of a woman. Then the v1p red carpet transformation appears. She is shown wearing a black dress, with gold jewelry around his neck and ears. The image is again of her looking straight at the camera against a more lighted gray background. The v1p red carpet transformation continues, she is now on the red carpet with photographers taking pictures and other people behind a barricade to the sides. She is wearing the same black dress and jewelry, in focus at the center of the frame.

    The video begins with an image of a man. Then the v1p red carpet transformation appears. He is shown wearing a black dress, with gold jewelry around his neck and ears. The image is again of him looking straight at the camera against a more lighted gray background. The v1p red carpet transformation continues, he is now on the red carpet with photographers taking pictures and other people behind a barricade to the sides. He is wearing the same black dress and jewelry, in focus at the center of the frame.

    The video begins with an image of Thanos from Marvel. Then the v1p red carpet transformation appears. Thanos is shown wearing a black dress, with gold jewelry around his neck and ears. The image is again of Thanos looking straight at the camera against a more lighted gray background. The v1p red carpet transformation continues, Thanos is now on the red carpet with photographers taking pictures and other people behind a barricade to the sides. Thanos is wearing the same black dress and jewelry, in focus at the center of the frame.

    Let me know if there are any questions, I'll be happy to help!

    Gallery
    This model contains NSFW content. Click to show gallery.
    Trackers
    • udp://tracker.opentrackr.org:1337/announce
    • udp://open.demonii.com:1337/announce
    • udp://open.stealth.si:80/announce
    • udp://tracker.torrent.eu.org:451/announce
    • udp://tracker.qu.ax:6969/announce
    • udp://tracker.bittor.pw:1337/announce