For business inquires, commercial licensing and consultation contact me under [email protected], for custom LoRAs visit my ko-fi page!

Follow me on Twitter: @YamerOfficial Discord: yamer_ai

If you have enjoyed this checkpoint:

After the success of the Terror checkpoints there has been a void in the SDXL 1.0 field, with 𝓗𝓨𝓢𝓣𝓔𝓡𝓘𝓐 a new wave of horror will come and with that a lot more crativity and a unique style, the checkpoint if focused on dark themed images, vaporwave, horror and creepy style images can be perfectly generated with this checkpoint.

This checkpoint was made with the help of DataVoid, without his help this project would not have been completed.

𝓗𝓨𝓢𝓣𝓔𝓡𝓘𝓐 is unique in many ways, one of them is the use of prompts, with HYSTERIA you will be able to generate images in a whole new way that has never seen before, images look beautiful and terrific at the same time and they have their own unique creepy style that adds a bit of magic to each image, play with CFG and fin your best settings.

𝓦𝓱𝔂 𝓪 𝓱𝓸𝓻𝓻𝓸𝓻 𝓬𝓱𝓮𝓬𝓴𝓹𝓸𝓲𝓷𝓽?

For a while now, I've aimed to shed more light on horror and creepy imagery. Mainstream checkpoints tend to lean towards NSFW or anime themes, leaving little room for horror. That's precisely why this checkpoint exists to fill that gap with its distinct style.

Since the release of the Terror models for SD 1.5, I hadn't ventured into creating a horror-specific SDXL 1.0 checkpoint until now. Give this checkpoint a try and provide some honest feedback. Your feedback will contribute to refining the next version!

Creator note:

Hi, I'm an Italian creator on a mission to spread the joy of using AI to generate images and the progress it has made in the past few years. I craft checkpoints and prompts that anyone can use to generate their own art and share it. My ultimate aim is to be a good creator, sharing the models I create as a hobby with others.

The primary goal of this checkpoint is to be multi use, good with most styles and that can give you the creator, a good starting point to create your AI generated images and start your own career in the AI world.
All the various versions follow the general idea of an unstable model, but they individually showcase distinct styles. V2 for instance, isn't a direct improvement of V1 and the same applies to all the other versions. Every version introduces its own unique style, and with each iteration I try my best to enhance the aesthetics and visuals, ensuring each model stands out with its own distinct identity! 😸

Why is this checkpoint better than regular SDXL1.0:

1. No embedding needed

2. Better variety of style

3. The refiner is not needed

4. Less AI generated look to the image. (When creating realistic images for example)

5. No face fix needed to generate good faces

6. Better photography composition

7. Better realistic details in all generations

8. Reflections, lighting, skin detail, hair, etc look more natural

9. Better saturation, overall quality, texture and tonality

10. Less blurry images

11. No adetailer required (Just use hires fix)

12. Style is stronger. (More defined and unique)

13. Better with SFW and NSFW. (A nsfw LoRA is recommended for specific nsfw results)

14. Better coloration of the images.

15. More variability.

16. Better close ups.

17. Less image artifacts.

18. Sharper and darker lines.

19. A better look to abstract concepts.

20. Liberty to try various styles and adaptability to all settings

^w^ It works best with:

• LoRA: XL YAMER'S STYLE ♠️ Princeps Omnia LoRA

• Restore Face: It is not needed to generate high quality images (Not used in the current showcase.)

• Clip skip: 1-2 (The model works well with clip skip set to both.)

• SDXL Refiner: Not used with my models!

1) Reality is often mischievous, create your own.
2) Imagination will take you a million light years from home. But will it bring you back?
3) Be chaotic, be creative, never stop improving and never put a limit to yourself.

    -Yamer Grimlock

P͓̽e͓̽r͓̽s͓̽o͓̽n͓̽a͓̽l͓̽ ͓̽R͓̽a͓̽t͓̽i͓̽n͓̽g͓̽:͓̽

• Quality: 9/10

• Stability (Variety): 7/10, the lower = the more variety with one prompt

• Flexibility: 8/10

• CFG resistance: 15/30

• Style strength: 8.5/10

• Style Variety: 5.5/10