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 model may only work in ComfyUI as it requires the Perturbed Attention Guidance node.
This is an experimental merge between my GonzaLomo v4.0 non-DMD model and BigASP v2.5. I wouldn't say it's better than either of those two models. This is just an attempt to try to incorporate some of the great attributes of BigASP into my models.
BigASP provides superior color, composition and lighting - it's really like an SDXL version of Flux - but also not quite compatible with other SDXL models. That's why this is purely experimental.
This is not a DMD model. Here are the settings that seem to work best for me:
Steps: 20-30
CFG: 1.5-2.5
Sampler: Euler (Euler A also works well if you turn PAG down to 1.0)
Scheduler: Exponential
Perturbed Attention Guidance: 3.0
Model Sampling SD3: Does not work - unless you prefer your images to look like gray mushy oatmeal
Note that the images in the model showcase have been created using my refiner workflow for BigASP 2.5 so they've been upscaled and refined my GonzaLomo v4.0
FAQ
Comments (14)
I will nitpick a bit. Ive used your older model Gonzolomo v2 and that one is damn effin great.
But seeing examples of this creation makes me wonder if someone accidentaly dropped some Illustrious in it, cause those outlines and contrast looks very much like most not-so-great attempts of Illustrious realism (it usually is due CLIPs being trained for anime/line art so those lines and contrast simply bleeds out, if we dont mind base model that does same).
No clue how to fix it.
Unsure if you improved prompt follow in newer v4, but original was so-so. Maybe training with better CLIPs, or shipping with better CLIP?
I don't mind nitpicking at all. All feedback is welcome. Assuming by "this creation" you mean the v4.0 Unity model, I'm not sure what you're referring to about the "outlines". There's definitely no Illustrious merged in.
It's funny you mention v2 being much better because v5 is actually going to partially branch off of that - so maybe you'll like v5 better as well.
As far as the CLIP, I've been tinkering with using different CLIPs but haven't hit on something that results in objectively better images yet. If you have any suggestions for improving the CLIP I'm certainly open to hearing them.
GBRX No, I mean LittleASP. Trying BigASP v2.5 on its own.. that thing has some issues. :D
v4 looks great, no problem there.. very raw. Not my thing, but its nice.
CLIP L replacement is easy, CLIP G is hard.. trying to find one thats somewhat "all-around". SDXL mostly relies on G, I think author of BigASP v2.5 used just stock CLIP G (Ive tried it with different versions and Im pretty positive its just regular one). Which is one thing that makes it very non-cooperative.
Mescalamba Ahh, sorry for misunderstanding which model you were referring to. LittleASP is definitely a work in progress. BigASP provides lots of great possibilities but it's a bit of a wild stallion that I'm trying to tame. They'll be more versions that hopefully get incrementally better.
I have control over which CLIP gets used. I'm actually not using any of the CLIP from BigASP but I do have some learning to do regarding CLIPs.
I've tried the new model Little ASP for a whole hour but I couldn't find any settings in Forge WebUi that would give decent results. Maybe it only works well in Comfy. If not what would be the recommended settings in Forge, if anybody knows.
I'm sorry, I'm only able to test in ComfyUI. BigASP only really works in ComfyUI. It's is a tricky model to work with and consequently so is LittleASP. Most of the images it creates really require a refiner by a photorealistic SDXL model. If Forge lets you do that then you might get good results. Otherwise, you can also try turning down the CFG to 1.0 and using Euler A as the sampler. I've seen some good results that way sometimes.
hdmwot The color saturation is definitely a little higher than v4. I just added a post showing how to turn that down, https://civitai.com/posts/20150251. Just adding "desaturated" to the prompt should make it more similar in style to v4.
so CFG=1 means no negativ prompt ... right?
looking at all the image gallery users have posted, I wonder what magic have you concocted with this v4 unity xl dmd model. faces look so sultry sugary sweet. I'll have to incorporate this as a dedicated refiner checkpoint.
Hey, thanks! I do think the v4 model makes a great refiner for lots of other images. I've published a number of SDXL (https://civitai.com/models/1513601/gonzalomo-sdxl-workflows) and Flux (https://civitai.com/models/1651835?modelVersionId=1974042) workflows for just this purpose.
GBRX Thanks. I'm already using it as a refiner with Illustrious models focused on realism. Getting good results after tuning the parameters in facedetailer. Thanks for sharing your work!
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.




