CivArchive
    3DMDT1 - Generalist Model - High skill in 3D. 2.1 768X - V1
    NSFW
    Preview 128233
    Preview 127838
    Preview 127837
    Preview 127836
    Preview 127835
    Preview 127881
    Preview 127880
    Preview 127879
    Preview 127886
    Preview 127885
    Preview 127884
    Preview 127883
    Preview 127897
    Preview 131312
    Preview 131313
    Preview 131334
    Preview 131342
    Preview 131341

    If this model is useful to you, your support helps me keep publishing free models and open-source AI tools.

    Discover more of my models, projects, and practical AI resources:

    • Portfolio: artificialguy.com — models, projects, and experiments.

    • Prompt library: FindGoodPrompt — curated prompts for image and language models.

    • AI tools directory: JustGoodAI — a curated directory of useful AI tools.

    • Twitter/X: @artificialguybr — new models announced here first.

    Hi guys. This is a work that I have been developing for weeks uninterruptedly. It all started with a desire to create a more 3D-oriented model, generating images as if they were generated in Blender/Unreal and other 3D editing tools. I got good results in 3D.

    After that together with my friend Shadow, from the PRMJ model, I was able to improve both models by making modifications and creating a generalist model that delivers good results in a high range of prompts. Although it is focused more on 3D, I got good results in landscapes, portrait, photorealism, illustrations, among others.

    The most important part of the models to understand a prompt well. If you want something more photorealistic, put in keywords for photos such as raw photo, etc. Now if you want a 3d render, put 3d render word on it.

    Because the model is more focused on 3d rendering, if you don't insert anything it will create something more 3d related than photorealistic.

    All images in the gallery were made using DPM 2M++ Karras 30 Steps. No embeddings. Negative prompts standard. No face restore.

    I really hope you like the model and use it.

    All money received is reverted to make GPU TIME rent since I don't have a local machine with GPU.

    I would like to thank the help and support of;

    • Shadow_Shinigami

    • Mousewrites

    • PePPa

    • Queria Star Morta

    • PublicPrompts

    Description

    FAQ

    Comments (9)

    AgimaFRFeb 21, 2023
    CivitAI

    I will try this generic model which looks very interesting, thanks.

    Can you please give examples of prompts like all the others do?

    artificialguybr
    Author
    Feb 21, 2023· 1 reaction

    Here some: https://imgur.com/a/tKXZbZm

    9ballFeb 21, 2023
    CivitAI

    Keeping an eye on this one. Would love to see some sample prompts.

    artificialguybr
    Author
    Feb 21, 2023

    Here https://imgur.com/a/tKXZbZm

    ritcher1Feb 21, 2023
    CivitAI

    Really a great model, full of potential. Can you show some prompts of your sample renders ?

    artificialguybr
    Author
    Feb 21, 2023· 1 reaction

    I am trying to upload the examples on Civitai, but the site is very unstable. Here are some examples for now; I will add more when the CIVITAI site gets more stable and stops crashing; Imgur: The magic of the Internet

    ritcher1Feb 21, 2023

    Ok, thanks. Yes CAI seems overloaded these days.

    Seen the images on imgur, but they still haven't the metadata inside so no prompts, just images. Can you upload the images with the metadata/prompt inside the png, on imgur ?

    MattHVisualMar 18, 2023

    If you check "View More" images he has prompts for the last four uploaded images.

    GionTan333Mar 22, 2023· 2 reactions
    CivitAI

    Error:
    modules.devices.NansException: A tensor with all NaNs was produced in Unet. This could be either because there's not enough precision to represent the picture, or because your video card does not support half type. Try setting the "Upcast cross attention layer to float32" option in Settings > Stable Diffusion or using the --no-half commandline argument to fix this. Use --disable-nan-check commandline argument to disable this check.

    Checkpoint
    SD 2.1 768
    by artificialguybr
    Download (Beta) View on CivitAI
    illustration
    fantasy
    realistic
    photorealistic
    photography
    character
    3d render
    landscapes
    3d
    portraits

    Details

    Downloads
    2,603
    Platform
    CivitAI
    Platform Status
    Available
    Created
    2/20/2023
    Updated
    11/9/2026
    Deleted
    -
    Trigger Words:
    3dmdt1

    Files

    3DMDT1.ckpt

    Size:
    2.40 GB
    SHA256:
    ee8c6b7849c21a6c1553819988d499aa387f87ff7d1f7eceaed2053e27919de9

    Mirrors

    HuggingFace (1 mirrors)
    CivitAI (1 mirrors)

    3DMDT1.yaml

    Size:
    1.77 KB
    SHA256:
    72b092aadfe146f5d3f395a720c0aa3b2354b2095e3f10dc18f0e9716d286dcb

    Mirrors

    CivitAI (83 mirrors)
    TensorArt (1 mirrors)

    3DMDT1-FP32-NoPruned-Safe.safetensors

    Size:
    2.40 GB
    SHA256:
    cb89b1bb63b099bf94aafbd9bdfb879f32c7f9b3fbaed4a01df27dd21eabdcf4

    Mirrors

    HuggingFace (2 mirrors)
    CivitAI (1 mirrors)

    Available On (1 platform)

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

    SeaArt
    3DMDT1 - Generalist Model - High skill in 3D. 2.1 768X - V1