CivArchive
    Preview 108572935
    Preview 108572533
    Preview 108572520
    Preview 108572450

    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

    This is a return to the pure photorealism of the V4.0 style.

    The recommended settings are:

    Sampler: LCM

    Scheduler: karras, exponential or beta

    Steps: 7-14

    CFG: 1.0-1.3

    Clip Skip: 1-5

    My favorite setting is LCM\Karras, CFG 1.0, 10 steps.

    FAQ

    Comments (21)

    Los_WaifusNov 2, 2025· 2 reactions
    CivitAI

    Amazing... not sure how you did this, but wow... thank you for sharing.

    mphobbitNov 2, 2025· 1 reaction
    CivitAI

    Any chance to see this checkpoint on Chroma engine?

    GBRX
    Author
    Nov 2, 2025· 1 reaction

    Maybe? I honestly haven't spent much time with Chroma yet. The little bit of testing I did a few months ago wasn't very impressive but I know some people get great results.

    pavanijakati83575Nov 2, 2025· 3 reactions

    @GBRX  Please do with Chroma Engine

    mphobbitNov 2, 2025· 2 reactions

    @GBRX  Vanilla Chroma's realism looks like FLUX's one and I also wasn't impressed first time. Also it heavy finetuned towards anime (people said me that's reaction on booru tags). But now it very powerful thing and just needs heavy finetune to photorealism. Ppl make it by merging with regular FLUX models, (CenKreChro, Chroma Merge Experiments) . See also UnCanny (Photorealism Chroma) - that man did his own finetune.

    GBRX
    Author
    Nov 2, 2025· 1 reaction

    @mphobbit Thanks, I'll definitely check it out!

    NarzNov 19, 2025· 1 reaction

    @GBRX screw chroma.. Krea's where it's at 😉 (jk, i too see people make amazing chroma gens, i just don't have the ambition). also +1 for cenKreChro, if you haven't tried it you should. and it's great as a refiner for Flux models like yours, realDream and araminta (unlike models like Rayflux with its added skin textures; too much)
    but seriously, this is a request for your sauce but with Krea. for me, it's what i wanted out of Chroma's drawn out hype-release (minus the NSFW element, which is where Chroma merges come in). if you have the hardware for it, i think you'd excel in that 'new' world. something about your data set, bro!

    GBRX
    Author
    Nov 19, 2025· 1 reaction

    @Narz Thanks, I've got CenKreChro downloaded but haven't played with it yet. It sounds interesting so I'll check it out soon. I do like my Flux model but I'd also like to add more NSFW capabilities as well.

    mphobbitNov 19, 2025· 1 reaction

    @Narz Idk about "hype release". Let me describe my personal feelings. First time I didn't recognize Chroma as something new (just yet another custom FLUX mod). Now it's a powerful thing which has an artistic capability of Pony/Illustrious + prompt adherence of FLUX. I even call it as a "true Pony V7". Yeah, it's struggles about photorealism but good finetuning (something like "Real Pony/Illustrious on FLUX engine") can solve problem .

    TarendaxNov 2, 2025· 7 reactions
    CivitAI

    Using the PatchModelAddDownscale node in ComfyUI. I didn't know this gem existed, thanks for the golden tip you indirectly provided.

    GBRX
    Author
    Nov 2, 2025· 2 reactions

    No problem, I saw someone use it in a Youtube video a long time ago and I've been using it ever since. Much better quality when you can generate at a higher initial resolution, imo.

    lokalfokalNov 2, 2025· 3 reactions

    Indeed, also pair with this custom node call 'Normalized-Attention-Guidance' which supported most SD-platforms from https://github.com/pamparamm/sd-perturbed-attention
    90% goes well along(after) 'PatchModelAddDownscale' node. Plus 'NAG' got a Negative guidance -- explicitly suppressing unwanted attributes (negative prompts) even at 1 CFG set.

    pavanijakati83575Nov 2, 2025· 5 reactions
    CivitAI

    Another awesome release. Thanks Bro.

    SnapRYRY89Nov 3, 2025· 2 reactions
    CivitAI

    As others have said, this is a great checkpoint. it accepts most LORA I throw at it and the lightweight settings make this really optimized.

    Zakman99Nov 5, 2025· 2 reactions
    CivitAI

    Great model—fast, with DMD LoRA already built in, so there's no need to load it separately. Also, many thanks to the model's author for the workflow. I believe this model has plenty of room for further development. I'm glad SDXL is alive and well!

    LuckyJack1408Nov 7, 2025· 3 reactions
    CivitAI

    Holy Moly :-) A new favorite on my list, thanks for providing this great checkpoint!

    GenoMachinoNov 8, 2025· 4 reactions
    CivitAI

    I love your models!! I keep trying to merge them with other models of yours and others that I like, but I keep coming back to your base models!! HA! Well done! Also, I really dig the DMD versions... they're very clean and crisp... and FAST! Cool! Thanks!!

    jadicomanNov 10, 2025· 4 reactions
    CivitAI

    Hi GBRX, thank you for this awesome model. I use it with A1111. The best results are achieved with LCM Karras 12 steeps and CGF 0.8/0.5 (you can easily change the CGF slider precision in config.json). It also works well in Spanish prompts. Best regards

    lighthorsexajz830Nov 11, 2025· 4 reactions
    CivitAI

    GBRX ..very good model An incredible rendering thank you for your excellent work

    natasha_26Nov 15, 2025· 12 reactions
    CivitAI

    This model is one of the most realistic model you can find here on Civitai. Amazing job buddy. I used more than 15 LoRA without distortion the final work.

    GBRX
    Author
    Nov 15, 2025· 2 reactions

    Thanks, that's great to hear!

    Checkpoint
    SDXL 1.0
    by GBRX

    Details

    Downloads
    18,184
    Platform
    CivitAI
    Platform Status
    Available
    Created
    11/2/2025
    Updated
    5/16/2026
    Deleted
    -

    Files

    gonzalomoXLFluxPony_v60PhotoXLDMD.safetensors

    Mirrors