CivArchive
    Preview 123367723
    Preview 123367561
    Preview 123374958
    Preview 123368335
    Preview 123367564
    Preview 123367572
    Preview 123377481
    Preview 123367598
    Preview 123367636
    Preview 123367680
    Preview 123367747
    Preview 123369284
    Preview 123374953
    Preview 123374957
    Preview 123374989
    Preview 123376609

    I believe this model to be very good at photorealism although it does have some artistic capabilities as well. Here are a few tricks to using the SDXL versions of GonzaLomo to its fullest potential:

    • Clip Skip is your friend. I recommend trying a prompt with both 1 and 2 values. 1 can make images that are more creative, artistic, retro or grungy whereas 2 is better at photorealism and the, um, physical attractiveness of the subject(s).

    • Generate at 1024x1536 or higher using the PatchModelAddDownscale node in ComfyUI. This will create a much more detailed image that can then be upscaled further, resulting in incredible photorealistic detail. Using that node, I can do an initial generation as high as 1280x1920.

    • You can play around with different sampler settings but I find that the absolute best results are with LCM/Karras, 12 steps and CFG 1.0.

    • Selective usage of the Self Attention Guidance node can sometimes give amazing results. I always have it in the pipeline and usually bypassed but turn it on when I think an image has potential but just needs a little more oomph like color saturation or contrast.

    • I get really interesting/creative results by generating with the V1.1 Semi-Real model and then resampling that image with the V2.0 Unity model at around 0.60 denoise. You really need to play with the denoise to find the right value that tips the image from cartoonish to photorealism but you'll be amazed at what's possible when you do. Note that V1.1 Semi-Real requires Clip Skip 2+ and will not work with 1 at all.

    • And lastly, always be upscaling! More pixels equals more detail equals more photorealism.

    Note: I only use ComfyUI so I apologize in advance if you're having trouble with my model in some other tool and I can't help.

    Current Models

    V2.0 Unity

    Essentially, this is V1.1 Real with a bit of Siren Forge, Cyberrealistic and Lustify added to the mix. The base is still Gonzales and LomoXL.

    I called this version Unity because I originally wanted to have separate models for photorealism and artistic styles. However, I realized that I could get both in one model and created V1.1 Artsy for that purpose but it was a failure. This is my second attempt at that combination and I think/hope it's a success.

    At the very least, I don't want to degrade the photorealism capabilities and just want to add more surreal, artistic or fantastical styles as an option.

    The recommended settings haven't changed since V1.1 Real:

    Sampler: LCM (also dpmpp2a and ddim can provide interesting results)

    Scheduler: Karras, Exponential or Beta

    Steps: 8-12

    CFG: 1.0-1.3

    Clip Skip: 1-5

    I normally keep my settings at LCM/Karras with a CFG of 1.0 but I tend to vary the clip skip between 1 and 5 because those can change the image pretty drastically. Sometimes an image at clip skip 2 will be terrible but might become amazing with clip skip 1, and vice-versa.

    V1.1 Semi-Real

    I'm doing a little experimenting with non-photorealistic models. This is a merge of GonzaLomo v1.1 Real and ToonComix which is a toon model that does a really good job with detailed backgrounds. The whole Comix family of models is very good so check them out.

    Sampler: LCM

    Scheduler: Karras, Exponential or Beta

    Steps: 8-12

    CFG: 1.0-1.3

    Clip Skip: 2-5 (1 is not supported)

    Retired Models

    V1.1 Real

    This is a simple 60/40 merge between two of my favorite photorealistic models - Gonzales-NSFW-PonyV1/V2-DMD v2.0 and LomoXL (with a little bit of Lustify thrown in). Many, many thanks to the makers of those excellent models.

    Gonzales is a Pony model so GonzaLomo inherits all of those capabilties. LomoXL has a very strong analog feel to it which helps give an edge to Gonzales' "pony-ness".

    Sampler: LCM

    Scheduler: Karras, Exponential or Beta

    Steps: 8-12

    CFG: 1.0-1.3

    Clip Skip: 1 allows greater analog effect but lessens NSFW capabilities

    Clip Skip: 2-5 lessens/removes the analog effect but allows more NSFW

    Try this workflow to get started, if you need it.

    To be clear, I created this merge for my own use cases. It's certainly not better than Gonzales for most things. I'm just hoping to inject Gonzales with some of the gritty, analog feel that I was looking for in some cases. LomoXL also allows for a wider variation of faces, especially with clip skip 1.

    Enjoy!

    P.S. This is my first model upload so I would appreciate any constructive feedback or comments.

    V1.1 Artsy alpha (Not very good imo, use V2.0 Unity instead)

    This was an attempted merge between V1.1 Real and a few art-focused models. The main purpose of this model is to be able to produce artistic styles but it has the tendency to try to force photorealism when prompted clearly for an artistic style. This model has been abandoned in favor of V2.0 Unity which does a much better job of combining the photorealism of V1.1 Real with artistic styles.

    Description

    Just trying to make the images a little clearer. My primary purpose with this new version is to create better images that I can turn into videos but it's pretty good at creating static images as well, especially if you do a SDXL refinement at 0.20-0.30 denoise. It's not great for hard NSFW though.

    Steps: 6-10

    Flux Guidance: 3.5

    Sampler/Scheduler: euler/beta or dpmpp_2m/simple

    CFG: 1.0

    I strongly recommend using my Flux refining workflow with GonzaLomo v6.0 DMD as the refiner. This will make a huge difference in the skin texture and overall realism.

    This model can be used like a regular checkpoint as it contains both the UltraFlux VAE and CLIP (t5xxl_fp8_e4m3fn and ViT-L-14-TEXT-detail-improved-hiT-GmP-TE-only-HF).

    FAQ

    Comments (33)

    ShinobiSatMar 7, 2026· 4 reactions
    CivitAI

    Hello, today I downloaded the new version (V3.0 Flud D AIO), but when I start the generation and try to load the model, I get the following error: CheckpointLoaderSimple

    ERROR: Could not detect model type of

    Can you tell me why?

    GBRX
    Author
    Mar 7, 2026· 2 reactions

    hmm, I've seen that happen before and it's usually a corrupted download. can you try downloading it again?

    ShinobiSatMar 7, 2026· 1 reaction

    @GBRX Okay, I'll think about it, give it a try, and let you know. Thank you.

    GBRX
    Author
    Mar 7, 2026· 1 reaction

    @ShinobiSat I'll try downloading the civit version too just to make sure my upload didn't get corrupted.

    ShinobiSatMar 7, 2026· 1 reaction

    @GBRX Downloaded again, but same result.

    GBRX
    Author
    Mar 7, 2026· 1 reaction

    @ShinobiSat Ok, I'm downloading it now but the download is really slow. Which workflow are you using?

    ShinobiSatMar 7, 2026· 2 reactions

    @GBRX the first workflow I tried was yours, then I tried others to understand if the problem was on the flow, but it is not

    GBRX
    Author
    Mar 7, 2026· 1 reaction

    @ShinobiSat The download from civit is extremely slow for some reason. It's only 40% downloaded after two hours. Can you check the size of the file? My local file that I uploaded is 17,068,674,198 bytes.

    ShinobiSatMar 7, 2026· 1 reaction

    @GBRX it's often very slow... my download is 17,068,675,072 bytes

    GBRX
    Author
    Mar 7, 2026· 1 reaction

    @ShinobiSat I finally got the file after restarting the download and it works fine. Here is an image I just published using the civit version, https://civitai.com/images/123457017. I know civit was having a bunch of problems last night. It still could be that you got a corrupted download twice. I'm not sure what you can do other than to download it again. It does seem weird that your file size is different. The file size of the one that I just downloaded is exactly the same as the one I uploaded. Maybe I'll do a hash to make sure they're the same.

    ShinobiSatMar 7, 2026· 2 reactions

    @GBRX yes, in fact, that difference in size is strange, however between today and tomorrow I will try a new download

    ShinobiSatMar 7, 2026· 1 reaction

    @GBRX I re-downloaded (at least it's super fast for me :D) now the size is identical, but I get the same error. From the terminal, I saw that it also says this at startup:

    Warning, This is not a checkpoint file, trying to load it as a diffusion model only.

    !!! Exception during processing !!! ERROR: Could not detect model type of

    Then it stops saying:

    RuntimeError: ERROR: Could not detect model type of:

    I also tried loading it on a different workflow, loading it on a diffusion node instead of as a checkpoint, but with the same result.

    GBRX
    Author
    Mar 7, 2026· 1 reaction

    @ShinobiSat Sorry, I have no idea what the issue could be then. You might have said this already but have you tried updating and restarting comfy?

    ShinobiSatMar 8, 2026· 1 reaction

    @GBRX Yes, it remains a mystery!

    crustyloaf573Mar 8, 2026· 1 reaction

    Similar issue here (V3.0 Flux D AIO), SwarmUI gets stuck on 'waiting for model to load'. Have to force quit to get out of it. I've d/l this twice and getting the same result. There's something wrong with this version, previous ones work fine.

    GBRX
    Author
    Mar 9, 2026· 1 reaction

    @ShinobiSat Which ComfyUI version are you using. I've tested it successfully with v0.15 and v0.16.4.

    jrrytng467Mar 7, 2026· 3 reactions
    CivitAI

    I am so clueless to a lot of terms and such, and I am learning as I go, but I have a big question if someone could answer this, I'm sure it will help me going forward. The term SDXL, so I do everything using Standard Diffusion and if I'm set up to run SDXL models, why do all these models say you need to run this SDXL model using XYZ? I understand sampling and all that but I have hard times finding what I'm looking for, for what I want to do with it. Simple merging either Checkpoints or LoRAs?

    GBRX
    Author
    Mar 8, 2026· 1 reaction

    What is it you're trying to do?

    jrrytng467Mar 8, 2026· 2 reactions

    @GBRX Just the understanding of whats whats. I know that that covers a lot but if you can point me in a direction that explains it all. Ive noticed more and more people trying new tools and I dont understand the effect they have without diving into each and every one of them. I have ComfyUI and other tools but I enjoy just working out of stable diffusion, still learning about the extensions you can add to it. Ive though about sticking with older good models before all the new tools came out. I see everyone talking about thrying this or that, about clipping, high loads low loads ect ect and I just want to start at the beginning, where ever that is and work into it all. Kinda of feel like I'm chasing my tail

    GBRX
    Author
    Mar 8, 2026· 1 reaction

    @jrrytng467 I would say just watch youtube tutorials for beginners or ask grok or chatgpt to explain it all from a beginners perspective.

    jrrytng467Mar 8, 2026· 2 reactions

    @GBRX Thank you. I did merge your model in with mine and so far I'm pleased with the clear images I'm getting

    sriramakumar7799888Mar 8, 2026· 4 reactions
    CivitAI

    GonzaLomo Flux D V3 AIO, Good Model

    bees117Mar 9, 2026· 3 reactions
    CivitAI

    Hiya,
    I'm really looking forward to trying this model but I'm getting an error. ERROR: Could not detect model type of: J:gonzalomoXLFluxPony_v30FluxDAIO.safetensors. V2 works perfectly is there a new setting I need to use for this one?

    GBRX
    Author
    Mar 9, 2026· 1 reaction

    This has been reported by someone else too but I'm not sure what the issue is yet. What image generation tool are you trying to use it in?

    bees117Mar 9, 2026· 1 reaction

    @GBRX I'm using comfy with a custom workflow with dual clip loader. I also tried it with a single aio checkpoint loader.

    bees117Mar 9, 2026· 1 reaction

    @GBRX I see the other post. I'm going to try redownloading as well. Thanks for the great work!

    bees117Mar 9, 2026· 1 reaction

    @GBRX No luck. My downloaded file size matches your upload. I'm guessing I might need to update comfy, which I'm going to have to do now I guess. I'll report back if I get anything useful.

    GBRX
    Author
    Mar 9, 2026· 1 reaction

    @bees117 I've tested it successfully with ComfyUI v0.15 and v0.16.4, which is the latest.

    Lapalooza1Mar 9, 2026· 2 reactions

    This was happening to me as well. then I saw GRBX's comment about the it working on 0,.15 and 0.16.4.
    I checked my version turns out i'm still in 0.11. I updated and put the gonzalomo on checkpoint. works now.

    GBRX
    Author
    Mar 9, 2026· 1 reaction

    @Lapalooza1 Great!

    bees117Mar 9, 2026· 3 reactions
    CivitAI

    It was a problem on my end. Updated Comfy, re-wrote my broken nodes and BAM! I'm getting fantastically consistent results. I really like this checkpoint! Actually crazy consistent, what is this!?

    GBRX
    Author
    Mar 9, 2026· 1 reaction

    Awesome, glad it's working for you now. This v3 model now includes a lot of the same datasets that I've used in my SDXL, Chroma and Z-Image models.

    bees117Mar 10, 2026· 2 reactions

    Yeah buddy! I just got running my first batch. She's working great. Again thank you!