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
A bit different merge from v0.3 which hopefully fixes some of the problems that version had. This version should not need the SDXL refiner - although I would still recommend using that refiner if photorealism is your primary goal.
Steps: 6-12
Flux Guidance: 4.0
Sampler: euler, dpmpp_2m
Scheduler: simple, beta
CFG: 1.0-1.3
I would also recommend prefacing your prompt with "(vivid vibrant colors, high contrast, sharp focus)". For whatever reason, this really does seem to result in better image quality with this model.
This model can be used like a regular checkpoint as it contains both the Flux VAE and CLIP (t5xxl_fp8_e4m3fn and ViT-L-14-TEXT-detail-improved-hiT-GmP-TE-only-HF).
FAQ
Comments (32)
I want to express my deep gratitude to you for your work, I love all your creativity!!! ❤️
Thanks so much for your support!
Is this trained on dicks ?
The SDXL models are but I'm sorry that the Flux model isn't. I can see about improving that in the next version.
@GBRX I'm not sure if Flux knows what a dick is anyway. Thanks !
@girlswithafros Yeah, it's pretty bad. There are some models that do a decent job. I'll try to incorporate them into the next version if they work out well.
Amazing model, i believe it's the best model for photorealism in this site, it has 2 problems though:
1-Doesn't have innie pussy, only ugly pussy
2-It struggles with anal, often just ignores the prompt and do vaginal instead
Thanks a lot for your hard work
Thanks very much and I appreciate the feedback. I'll see what I can do about those problems in the next version.
Model is just perfect but I think dmd lora merged with model, so it is very hard to train a lora for this model, is it possible to release a version without dmd?
No, I'm very sorry but I don't think I can un-DMD it. This is a checkpoint merge between several models, some of which were DMD-only so I don't have access to the non-DMD versions. Thanks for the kind comments and feedback though!
@GBRX did you ever train a lora with your checkpoint? I tried but loras dont like cfg 1 I guess, blurry results.
@diegomariopyande4640 you can't train loras on a dmd2 checkpoint.
@diegomariopyande4640 Sorry, I was not considering LoRA training when I created this model merge.
great model, but forces NSFW even when image is not supposed to be, no prompt variation can ensure no nsfw. any help?
oh yes, i've just noticed this. Very unfortunate. I hope its fixed in the next update. I like more neutral models specially when its this good in the iq department.
Thanks for the warranted feedback. It's a bit of a tricky balance because I don't want to degrade the NSFW abilities but I also would like it to not default to nudity unless prompted.
Great model. Color palette is amongst the best i've seen. There was effort made in that regard which I truly appreciate because normally it doesn't get the importance it should by finetuners.
The only serious con I see is that hands are a little more problematic than other SDXL checkpoints.
In any case, top tier checkpoint. Great work. Looking forward to the next update.
Thanks so much! Hands are definitely a problem. Usually if I just keep the same seed and give it another step or two then it fixes the bad hands. I will see if I can improve that in the next version.
just...... wooooow!
Does it work with flux loras?
I've used it with a couple of loras without issue but I don't know if it will work with all.
I tried a couple too - worked fine for those.
is the fluxity already include VAE/clip?
Yes it does. You can use it like a regular checkpoint.
for models where i need a workflow ... no good models ^^
cfg~1 so 1 is not negative prompt ...
cfg from 1-1.5 means heavy things go wrong
It's not a good model if you want to use cfg above 1.2 or really want to do much with the negative prompt.
Hi, thanks anagin for your amazing models. I wonder if you could post just a simple upscaling workflow that can retain the prompt and metadata. The one I have doesn't retain it and it's a pain for posting a valid picture on this site now.
Have you tried the latest version of my workflow for this model? It should retain all the metadata for civit to parse out. At least, it has been working for me so let me know if you see any issues.
@GBRX I will try, thanks.
Looks like negative prompts wont work very well and have minimal or no effect,but still my fav. Fooocus
Thanks so much for the feedback and support. Negative prompts get ignored when the cfg is 1.0 so you would need to increase that to about 1.3 for it to have any effect. Even then, you would probably need to generate a few times to see your negative prompt applied. Also, if you raise the strength of the negative prompt then that can help too - e.g. "(nipples:1.3)" instead of just "nipples".
@GBRX thank you for your response.Helpful







