New Name. It has nothing to do with Neptunia or Tsunako style, is just that i like the name and that no other model has it. All models are different, unless it says v2 (new version of same model) or X (versions with LoRas added) after the name, they are different.

-

Available on Pixai:

Zero Dimension

Zero Dimension X

Heart Dimension

Golden Dimension

-

• Zero Dimension: No LoRas added to the merge and the model uses Chenkin v0.5 CLIP. It has a great LoRa and Artist style compatibility.

• Zero Dimension X: LoRas added to the merge, this enhances details. Still has compatibility with LoRas and Artist styles but is less than non-X version. Due to LoRas used it has now a 2.5D base style and is a lot different than the other one but you can use negative and positive tags to remove it. I recommend using it with high resolutions and a min of 20 steps.

• Heart Dimension: No LoRas added to the merge and the model uses Chenkin v0.5 CLIP. "Cute" version (makes characters more Moe).

• Golden Dimension: No LoRas added to the merge and the model uses Chenkin v0.5 CLIP. This one generates a more normal anatomy and is more detailed by default due to using Cyberfix Models and base style is more 2.5D. Due to being more detailed and not having LoRas for stability, it can have problems with complex patters and eyes.

-

The images i upload use DPM++ 4M SDE Karras, Euler Beta or ER SDE and without using any LoRA, CFG Rescale, Hiresfix, ADetailer or Upscale, so the quality can be improved. Close distance is good; medium is ok and far is ok/meh. I use Panchovix ReForge so the output you can get will be a lot different than mine.

-

Samplers and Schedulers:

ER_SDE Beta: CFG 3+ Good quality, delivers sharp and detailed images. Only downside it that sometimes doesn't follow prompts.

Euler a Normal/Simple/SGM Uniform CFG 3+ for general use, less detailed but works better with low steps.

Euler Beta/SGM Uniform CFG 3+ for sharper images and more detailed.

DPM++ 2/3/4M SDE Karras CFG 3+ for more sharpness, details and recommended if you use 3d/"realism" prompts.

For ER_SDE/Euler/Euler a start with 10steps max 35 steps.

For DPM start with 16 steps max 35 steps.

Resolution:

Works with all SDXL resolutions, i personally use 1024/1152x1536 and sometimes 1280x1536. For action or dynamic/fighting 1024x1536 is better, 1152x1535 works better for general images.

Recommended base prompts (but you can use the ones you like):

Positive:

masterpiece, best quality, high resolution, aesthetic, excellent

Negative:

worst quality, bad quality, low quality, lowres, bad anatomy, interlocked fingers, bad feet, bad hands, watermark, signature, username, logo

If you want to reduce outlines add: thick outlines, black outline

All models have Chenkin/NAI/Mugen merged in but will show up as Illustrious, the reason is just to get to more people, more people know illustrious.

You can upload my models on other generator sites but only if you don't use them to gain money, if i discover you are trying to get money i will appeal it.

All models have VAE merged in: XL_VAE_C - G9.5

Golden dimension has: XL_VAE_C - G9

It can be too colorful for some, so you can use the original SDXL VAE