Tensor.Art
Create

HotaruLabs

CHECKPOINT
Reprint


Updated:

119

Created by JujoHotaru

"HotaruLabs" series are experimental(intermediate) models, used to develop my "Breed" series checkpoints.

7 types are uploaded. To download each types, switch tabs ↑ above.

These models have special features :

  • Include many originally trained LoRA's to adjust painting style (saturation, tone), eye shape, and quality (finely detailed pupils, finely detailed outlines, reducing grain noise etc).

  • Highly detailed backgrounds.

  • Tuned to work better with my LoRA's (eye shape, mouth shape, facial expressions).

  • Support NSFW outputs.

More various other LoRA's are released on my CivitAI models list or HuggingFace repository. Please check it out.

Recommended output settings

  • CFG Scale: 7 - 10

  • Clip skip: 1 - 2

  • Sampler : DPM++ 2M SDE Karras / DPM++ 3M SDE Karras

  • Sampling steps: 30 - 50

  • Resolution: mainly tested on 512x512800x600640x960 and 1024x768

  • HiRes Fix: use SwinIR_4xR-ESRGAN 4x+ or 4x-UltraSharp. with denoise strength 0.2-0.6.

  • Negative embeddings: EasyNegative(v1), EasyNegativeV2, or SimpleNegative

  • Negative prompt: bad face

  • VAE : HotaruVAE is included(baked) in this model. No need to use external VAE by default, but

    you can change to another VAE by setting on WebUI.

  • Tweaking details: Use HyperDetailer.

Recommended quality prompts (optional)

insanely detailed, absurdres, ultra-highres, ultra-detailed, best quality BREAK slender, kawaii, perfect symmetrical face, ultra cute girl, ultra cute face, ultra detailed eyes, ultra detailed hair, ultra cute, ultra beautiful BREAK (PUT YOUR PROMPTS HERE)

Version Detail

SD 1.5

Project Permissions

Model reprinted from : https://civitai.com/models/439260?modelVersionId=489295

Reprinted models are for communication and learning purposes only, not for commercial use. Original authors can contact us to transfer the models through our Discord channel --- #claim-models.

Comments

Related Posts

The image generated by the model, publishing a post will appear here
Describe the image you want to generate, then press Enter to send.