Sampling Method Test, “ProtoGen_X5.8” – Part 1.

Home » Stable Diffusion » Sampling Method Test, “ProtoGen_X5.8” – Part 1.


Welcome to Part 02 of my Sampling Method Tester Series, with Checkpoint “ProtoGen_X5.8” and Prompt Style 01.

I’ll be using the X/Y/Z plot script to test different sampling methods. The purpose of this test is to gain an understanding of how these sampling methods behave with different Checkpoints and Clip Skips, and to visualize how differently they read the prompt.

To ensure a fair test, I’ll be using the same prompt text and parameters for each sampling method, except for the Sampling method and Clip Skip. I’ll be testing all the different sampling methods provided in Stable Diffusion with 2 different Clip Skips (1 and 2), including:

Euler a, Euler, LMS, Heun, DPM2, DPM2 a, DPM++ 2S a, DPM++ 2M, DPM++ SDE, DPM fast, DPM adaptive, LMS Karras, DPM2 Karras, DPM2 a Karras, DPM++ 2S a Karras, DPM++ 2M Karras, DPM++ SDE Karras, DDIM, PLMS, and UniPC.

To make this X/Y/Z plot test as fair as possible, I’ll use the same prompt settings for all other Checkpoints. If I come up with new prompt ideas, I’ll try to use the same prompt for other Checkpoints as well. And if you have any interesting suggestions, you’re welcome to share them too.

In certain cases, when the pictures have too many strange artifacts, I’ll try to adjust the prompt settings just for that sampling method. All the Checkpoints, Textual Inversion, VAE, and LoRA I use for the X/Y/Z plot test will be provided on the page, so you can follow along with my testing process.

If you found this post useful or interesting, please don’t hesitate to share it with your friends and followers! It would mean a lot to me and motivate me to create more valuable content about this topic. Your support is greatly appreciated, and I’m always open to feedback and suggestions for future posts. Let’s keep the conversation going and explore the fascinating world of sampling methods together!



Checkpoint (Model):

Textual Inversion: 
* They are slightly different, but you can use any what you like.



During my testing process, I noticed that this particular Checkpoint didn’t yield great results with low Sampling steps. I was seeing a lot of strange constructions in the generated images, which is definitely not ideal. So, I decided to increase the Sampling steps to 40, and that did help to remove most of the issues. However, there are still some images that have a few strange constructions, but I think it’s acceptable for testing purposes. It just goes to show how important it is to find the right balance between Sampling steps and other parameters when working with different Checkpoints.


Positive prompt:
hyper realism, (anime Makoto Shinkai:0.4), old shabby house in city street, building, sky, cloud, day, scenery, tree, blue sky, sign, no humans, power lines, house, english text, railing, wide shot
Negative prompt:
nsfw, sketch, duplicate, monochrome, (worst quality:2.0), (low quality:2.0), (blurry:2.0), horror, geometry, bad_prompt_v2, wooden, car
Steps: 40, Sampler: ALL, CFG scale: 7, Seed: 3977717266, Size: 768×768, Model hash: f036d7b40b, Model: ProtoGen_X5.8, Clip skip: 1-2



In this sample, we can observe that different Checkpoints produce varying moods and levels of detail with the same prompt. It’s possible that this particular checkpoint would be better suited to a different prompt. I’ll search for an more interesting prompt to test with this checkpoint and compare it with the results from other checkpoints. Stay tuned for updates!

Stay tuned for more updates on our sampling method tester series! Cheers!