CivArchive
    Preview 66682531
    Preview 66682837
    Preview 66682865
    Preview 66682866
    Preview 66682855
    Preview 66682839
    Preview 66682842
    Preview 66682845
    Preview 66682849
    Preview 66682853
    Preview 66682864
    Preview 66682870
    Preview 66682840
    Preview 66682841
    Preview 66682836
    Preview 66682847
    Preview 66682830
    Preview 66682869
    Preview 66707810
    Preview 66707812

    PJ0_KREA

    REAL1SM_V3_FP8/FP16

    Most likely, this is the latest version of our joint model with my friend https://civarchive.com/user/Triple_Headed_Monkey . Styles and details have been improved in this version. As a result, we achieved what we had planned at the beginning of our work - realism and art in one model.

    For the style I'm using a node ComfyUI_MileHighStyler - Flux Mile High Beta | Flux Other | Civitai

    For realism and art styles use combination of samplers - Euler/Simpler, for anime and illustration use - Euler_ancestral/normal

    svdq-int4-project0_v40ArtReal1sm

    Special thanks @theunlikely for the work done on quantification!

    And thanks to JIB (J1B Creator Profile | Civitai) for his WF and clarifications on using this type of model:

    For using this model you need to install the nunchaku project following the instructions there. and the nunchaku ComfyUI custom nodes to get it to work. Download and unzip the archive from Civitai to: \comfyui.git\app\models\diffusion_models\int4-project0_v40ArtRealism-svdq\ This is the Nunchaku workflow I am using: https://civarchive.com/models/617562 Thanks a lot to theunlikely for running the Quantization which takes an H100 GPU 6 hours!

    Project0_REAL1SM_FP16 v2

    In this version, the details have been worked out, the background, the styles are more pronounced, the landscapes and nature have been trained.

    DO NOT POST NSFW CONTENT. If I see this, I will delete such content.

    Project0_REAL1SM_FP16

    In this version, more attention is paid to realism, and a small merge is made with a small part of the TruBass2 Tensor.Art model by Triple_Headed_Monkey.

    In order to keep up to date with the latest news in the AI world, I invite you to join our server AI Revolution https://discord.gg/hUKgjWwN

    DO NOT POST NSFW CONTENT. If I see this, I will delete such content.

    Ver4_Art_RealismDO NOT POST NSFW CONTENT. If I see this, I will delete such content.

    Improved background detail, realism, and some styles. This version of the model contains a small part of the TruBass ver 2 model published on TA

    It's not exactly a realistic model, but the realism is a little better than in version 3 and it's very good for an art model.

    v3 art

    This version is a transitional to the art version. Many art styles have been worked out, realism has been slightly reduced, and the model still does a good job with realism.

    v2

    Has more realism, emotion and quality.

    You can download the quantized versions of the model from the link ND911/Project0_GGUF at main

    Thanks kjs195 Creator Profile | Civitai for the quantized versions of the model Project0_v2

    V1

    This model is an experiment to improve the basic DEV model. I worked on the model together with my friend https://civarchive.com/user/Triple_Headed_Monkey The model is experimental and I hesitated to publish it for a long time, but since many people ask for it, I do it. The model gives decent results only in the bf16 format. When you try to use it in fp8 format, the result becomes much worse. This is the final version (the model is under development) and I will try to fix it.

    Thanks to OldCelticSoul for providing the opportunity to convert to GGUF format. https://huggingface.co/ND911https://huggingface.co/ND911

    Thanks kjs195 Creator Profile | Civitai for the quantized versions of the model Project0_v1. You can find the rest of the versions here ND911/Project0_GGUF at main

    Description

    REAL1SM_V2_FP8

    Improved details, background, additionally trained nature and landscapes

    FAQ

    Comments (23)

    jbrichezMar 29, 2025· 3 reactions
    CivitAI

    The model I was looking for.
    This is the best model so far ! 🔥

    Is there any way to send a prompt of more then 77 tokens ?

    speach1sdef178
    Author
    Mar 29, 2025

    Hi! Thank you for your words. i'm not sure what do you mean, please let me more info and i'll try help you. what are you using for generations? ComfyUI or something alse

    henlarsen1973Mar 30, 2025· 1 reaction

    From the internet, so use T5.
    T5-v1.1-XXL Encoder

    Purpose: T5 (Text-to-Text Transfer Transformer) is a general-purpose text processing model.

    Token Limit: Can handle up to 512 tokens (256 for the “schnell” version).
    CLIP L/14 Encoder

    Purpose: CLIP (Contrastive Language-Image Pre-training) is designed to understand the relationship between images and text.

    Token Limit: Fixed at 77 tokens.

    jbrichezMar 30, 2025

    @speach1sdef178 I'm using diffusers library for generations

    amazingbeautyJun 11, 2025

    @henlarsen1973 how properly manage to use same accurate way ? just using or sending text to t5 and make use of clip l empty ?

    viktoryaputevika727Mar 30, 2025
    CivitAI

    Привет! Эх, самовар не умеет рисовать. Не могли бы подсказать что из славянской темы она умеет? Спасибо!

    speach1sdef178
    Author
    Mar 30, 2025

    Hi! I didn't train the Slavic theme.

    viktoryaputevika727Mar 30, 2025· 1 reaction

    Oh, I'm sorry! I thought you were from Russia. Excellent model, I wish you creative success!

    speach1sdef178
    Author
    Mar 30, 2025· 1 reaction

    @viktoryaputevika727 Thank you so much! Even if I'm from Russia, my friend and I are making a universal model, not a highly specialized one. So I'm sorry.

    5423305Mar 31, 2025
    CivitAI

    Thank you for this work! Is this model unet or including t5xxl, clip and vae? https://civitai.com/models/1018060?modelVersionId=1591370

    speach1sdef178
    Author
    Mar 31, 2025

    @Bellissima3D Thank you! All version only UNET. That version also Unet FP16

    5423305Apr 1, 2025· 1 reaction

    @speach1sdef178 Thanks for the answer!

    Endorphin3Apr 2, 2025· 3 reactions
    CivitAI

    Thank you for your contribution!
    Can you update the discord invite link?

    speach1sdef178
    Author
    Apr 2, 2025· 1 reaction

    @Endorphin3 Thank you. I updated invite link :)

    jensnagel2012296Apr 9, 2025· 1 reaction
    CivitAI

    Flux has always been bad at creating animal fur. This checkpoint wipes said issue off the table. There are excellent SDXL checkpoints for creating photorealistic animal stuff which Flux finetunes never managed to get on par with - until now. This CP really gets the cake. And, if I may ask, a version needing a lower step count would be an excellent addition to this splendid checkpoint.

    speach1sdef178
    Author
    Apr 9, 2025

    I understand what you're talking about, but fewer steps means less quality

    Zakman99Apr 9, 2025· 1 reaction

    There are lores with which you can reduce the number of steps, but I would recommend nodes for acceleration, for example, wave speed comfy

    speach1sdef178
    Author
    Apr 10, 2025

    @Zakman99 thank you for the hint :)

    tigerartApr 15, 2025· 2 reactions

    I got a little hung up on the sentence “This CP really gets the cake” :)

    arkinsonApr 19, 2025· 3 reactions
    CivitAI

    Amazing checkpoint! One of the few flux models that really works. 🙂

    speach1sdef178
    Author
    Apr 19, 2025· 2 reactions

    Thank you so much :)

    JustXuX731Apr 27, 2025· 4 reactions
    CivitAI

    The best realistic model so far. And the prompt adherence is superb.

    speach1sdef178
    Author
    Apr 27, 2025· 2 reactions

    Thank you so much! It means a lot to us. And we are glad that you like it :)

    Checkpoint
    Flux.1 D

    Details

    Downloads
    1,104
    Platform
    CivitAI
    Platform Status
    Deleted
    Created
    3/29/2025
    Updated
    7/30/2026
    Deleted
    4/27/2026

    Available On (1 platform)

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