GodPussy XL

    SDXL_GodPussy_v1.safetensors LORA / SDXL 1.0

    Model Information
    Model Name
    GodPussy XL
    Version
    v1.0
    Size
    649.70 MB
    Downloads
    4,656
    Trigger
    godpussy
    Torrent Details
    BTIH
    31FC804E4CCB6F0D924767EDE8C65D799C6B1F63
    BTMH
    0C195EE8A848AE82105ABC5C7226277C7A42C3ADA153587B9D77A3747CC40F51
    SHA256
    80F7EC7D9BBE6967F02FD767D18741452311550885501332989C9E8F51B3B2A8
    Upload Date
    11 months ago
    Uploader
    CivitasBay.org
    Status
    8 Seeders
    0 Peers
    Info

    This LoRA works best when inpainting to improve vaginas. It only works on realistic or semi-realistic images and not on Anime.

    Recommended workflow:

    1. Generate NSFW image without this LoRA (using a NSFW checkpoint or LoRA).

    2. Optional: upscaling (for example with Tiled Diffusion, explained below)

    3. Inpaint with GodPussy XL LoRA (for example using automatic ADetailer pussy detection, explained below)

    The automatic ADetailer pussy detection is using pussyV2.pt from here:
    https://civarchive.com/models/132388/penis-pussy-adetailer-model
    I'm using the following parameters:

    Img2Img
    Enable ADetailer:
    Skip img2img:
    ADetailer model: pussyV2.pt
    ADetailer positive prompt: godpussy, <lora:SDXL_GodPussy_v1:1> (optional: highres, masterpiece, best quality, ultra-detailed 8k wallpaper, extremely clear)
    ADetailer negative prompt:

    Detection model confidence threshold: 0.3
    Mask only the top k largest: 1
    Mask erosion (-) / dilation (+): 8
    Inpaint mask blur: 8
    Inpaint denoising strength: 0.45 (0.2-0.45, depending on the quality of the original pussy)
    Inpaint only masked:
    Inpaint only masked padding, pixels: 128 (32-256, depending on your image size. Choose it to be just large enough that the algorithm sees the general hip orientation.)
    Use separate width/height:
    Inpaint width: 1024
    Inpaint hight: 1024
    Use separate CFG scale: 4 (2-7, depending on how pronounced the result should be)

    All other ADetailer settings are left at default.

    For upscaling vial Tiled Diffusion I'm using the "multidiffusion upscaler for automatic1111":

    https://github.com/pkuliyi2015/multidiffusion-upscaler-for-automatic1111

    This extension can be installed to Automatic1111 using "Install from URL". Usually I generate images in 768x1024 pixels and upscale them to 1536x2048 using the following parameters:
    Sampling steps: 100
    CFG Scale: 7
    Denoising strength: 0.35
    Enable Tiled Diffusion: ✓
    Keep input image size: ✓
    Method: Mixture of Diffusers
    Latent tile width: 128
    Latent tile height: 128
    Latent tile overlap: 48
    Latent tile batch size: 2
    Upscaler: 4x-UltraSharp for Anime or 4x_NMKD-Superscale-SP_178000_G for photorealism
    Scale Factor: 2
    Enable Noise Inversion: ✓
    Inversion steps: 10
    Retouch: 1
    Renoise strength: 1
    Renoise kernel size: 2

    "Region Prompt Control" currently does not work with SDXL. If you want to use this as well, there are other options that work with SDXL like "Regional Prompter".

    Tiled VAE might be necessary depending on the VRAM of your GPU and image size. If you need to use it, you can use the Fast Encoder without problems but don't use the Fast Decoder. Fast Decoder always gave me noisy images.

    This upscaling first simply upscales the image with the chosen "Upscaler" by your "Scale Factor" (2) and then splits the image into overlapping 1024x1024 pieces ("Latent tile width/height" multiplied by 8). The amount of overlapping is defined by "Latent tile overlap". The amount of "Denoising strength" changes how close the result should be to the original. Lower values are closer to the original, but also quality wise and therefore will result in a blurry image. Higher values give the algorithm too much space for changes when only seeing a piece of the image which can result in awful results with multiple faces etc. Therefore try to use the highest Denoising strength without image artefacts. Most of the time 0.35 is the perfect value for me.

    Keep in mind that since the algorithm only sees parts of the image, it is extremely important to use the right prompts/LoRAs for this. If for example your prompt describes a face and your Denoising strength is high enough, you might get multiple faces in your image since the algorithm tries to fulfil the prompt in every piece of the image. Most of the LoRAs also create problems during upscaling, so you might want to reduce their strength or exclude them from your prompt entirely. Most of the time only using general prompts like "highres, masterpiece, best quality" etc. is your best choice.

    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