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. There are 2 versions of the same model. 1 without LoRas for better compatibility and one with LoRas merged in (these will take a little more time to upload) to get the most details without needing to search or use detail LoRas (you can still use them but is not recommended). It will take some time to release the other models (my internet is trash).

Available on Pixai:

Heart Dimension

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

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

I will use the same prompts and seed for other model; my creativity right now is dead (same images).

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

Samplers and Schedulers:

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 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

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

Positive:

masterpiece, best quality, newest, high resolution, aesthetic, excellent

Negative:

worst quality, old, early, low quality, lowres, signature, username, logo, bad hands, mutated hands

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.

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

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