CivArchive
    ProFantasy - v2.1
    NSFW
    Preview 699650
    Preview 699652
    Preview 736029
    Preview 699651

    " ProFantasy was tested with a huge of scenarios, and fine-tuning several times to ensure that you will be able to create a FANTASY image in your own way "

    This model merges with my own 3 models called R-base (Realistic), F-base (Fantasy), and V-base (Vibrant)

    *** This Model needs VAE !!! ***

    Overview:

    • The purpose of this model is to generate epic fantasy images that are not only realistic but Animation also.

    • These models require a VAE. You can try mse-840000-ema or anything. I have a photo of the comparison in the Comparison section (below)

      • If you got bugs, adding '--no-half-vae' to the argument will solve it.

    Recommends:

    • You use it with any steps, prompt, sampler, ... (anything you want)

    • Prompt: If you don't know what to prompt, Fantasy Prompts by TxcTrtl is a great choice.

    • Steps: I recommend 30-45 (You can use higher, but many times do not have a big difference)

    • Sampling Methods: You can see the comparison in the Comparison section (below).

    • Sizes: 512x512, 512x768, 512x904 (Can be used both vertically and horizontally). Use more than 768x768 when you generate a long shot or extreme long shot photo.

    • Hires. fix: Use Denoising strength less than 0.6 (but you can try >= 0.7, sometimes you will get problems with the hands)

    Versioning:

    • v1: Pilot version. Aim to be realistic (Cinematic style, Realistic photo, less fantasy)

    • v2: All tunned. It's stable since version 2.1

    Comparison:

    # VAE

    full-size image

    # Versions

    full-size image

    # Steps

    full-size image

    # Sampling Methods (with steps 45)

    full-size image

    Disclaimers:

    • Do not sell: on any website.

    • Credit: If you use my model in your own merges

    • Not authorized: to be used on generative services (without my permission)

    Description

    • Training a new VFX Lora and embedding to it

    • Fix results at low-steps use

    • This model is bf16 (Mixed Precision)

    FAQ

    Comments (7)

    genZ_ArtMay 6, 2023
    CivitAI
    DimensionsAI
    Author
    May 6, 2023· 1 reaction

    Look like that model was made for the same purpose. You can use XYZ grid to compare, and pick the best one that suits for your work.

    genZ_ArtMay 6, 2023· 1 reaction

    Try using the same prompt, but it appears that it requires some tweaking. will post here too if I get some good result!

    haoxiangsong390May 6, 2023
    CivitAI

    I don't know why I got this error: AssertionError: could not find upscaler named TGHQFace8x_500k.

    Could you please help me?

    DimensionsAI
    Author
    May 6, 2023

    How you got that error, Which process are you doing?

    TGHQFace8x_500k is my favorite upScaler model, I use on every picture for Hires Fix. You can download from here (Ctrl + F for search)

    https://upscale.wiki/wiki/Model_Database

    ADMNtekMay 29, 2023· 1 reaction

    @DimensionsAI got that error because they loaded your image with png info and it auto-selected the TGHQFace8x_500k upscaler but since it doesn't come with stable diffusion by default it got angry and gave an error. Downloading the file and dropping it into stable-diffusion-webui\models\ESRGAN should fix it. Leaving this here because I had a relatively hard time where and how to install custom upscalers.

    xianflux799May 8, 2023
    CivitAI

    Anyone had any luck getting auras or a glow to work with this model? Trying to get some ice stuff worked up, but having little in the way of luck

    Checkpoint
    SD 1.5

    Details

    Downloads
    3,407
    Platform
    CivitAI
    Platform Status
    Available
    Created
    5/5/2023
    Updated
    4/30/2026
    Deleted
    -

    Files

    profantasy_v21.safetensors

    Mirrors

    CivitAI (1 mirrors)

    profantasy_v21.safetensors

    Mirrors

    Huggingface (1 mirrors)
    CivitAI (1 mirrors)