HUGE UPDATE
* I've had a request or two asking about the Euler_Max sampler and where to find it. Here's the github:
https://github.com/licyk/advanced_euler_sampler_extension
You can download directly from github, or if you're using A1111 or Forge... you can install from url in the extensions panel with the above url.
--- SDXLv1 ---
This SDXL update is a full redraw of this model. It took months to get it where I wanted it, and I'm glad to have it move forward as a new solid asset. This model takes inspiration from artists like Norman Rockwell, Robert Maguire, Virgil Finlay, and other artists who contributed to Pulp magazine illustration. This isn't a model solely focused on pulp magazine covers, it is quite versatile and responsive. It is not trained on any hardcore images, so if that's your goal - use a LoRA, it will struggle with that on its own. It is trained in human anatomy, but that wasn't the focus. I like this model and I'm happy with how it came out. As always, please let me know if you find any issues and I'll take a look at updates. This model will updated in SDXL - I will no longer update the SD1.5 version.
I will also include more examples than typical, to show the variety of work its trained on.
--- v1 ---
This model has been a work in progress for a long time. I started with an earlier version of my Arrogant Bastard Photo model. I like this model a lot, and it does a really great job with lighting, so explore that a bit. It also does well with minimal prompting and darker scenes.
Happy to hear any thoughts you have and thanks for trying it out!
--Original Arrogant Bastard Notes--
My models always start as an update to an existing model until I do something weird.
This is definitely starting as a v1.0 - and I will be updating it, more quickly I think due to how everything came together.
Let me know what you think, and I'll incorporate your feedback into my future training.
Description
FAQ
Comments (11)
Where can I find the euler max sampler? A google search turns up nothing.
Hey there!
Here's the github for it:
https://github.com/licyk/advanced_euler_sampler_extension
If you're using A1111 or Forge, just go to extensions and install from url and it will do the rest.
Why you guys keep posting 3-4Gb SD1.5 models?
I prune all of yours "creations" and they became 2.1Gb without any difference in quality, - output is per pixel is exactly the same. Do you expect that the bigger the better or something?
Hey there, all of the SD1.5 models are legacy and aren't updated anymore. I totally get the frustration though, I opted to keep them available rather than remove them from Civitai, but I'm only maintaining SDXL/Pony and soon... SD3.5 models.
If the prune works for you, I'm glad. I had some problems with the pruned versions not working well for people using generators other than A1111/Forge - ComfyUI. So I opted to move to the full-size on the SD1.5 to solve that. I never really went back to find a different method of compatibility.
Your checkpoint, as always, is of excellent quality. However, I notice a certain fuzziness in all the images, which might be related to the VAE. Iโll try using a different XL VAE to see if it improves the image clarity.
I confirm ... I guet way better quality using "lunaXLVAE_luna". ๐. For info, i'm doing all that with Forge ui.
Try a different upscaler. I use the 4x_foolhardy_Remacri and get clear results, sometimes the upscaler can make things blurry.
@QuadPipeย Thanks, i'll give it a try.
@phillabaule359ย How'd the try go?
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.

















