Text-to-Image
art
Not-For-All-Audiences
lisa_genshin / README.md
narugo's picture
Upload model for lisa/リサ/丽莎 (Genshin Impact), on 2024-03-27 23:55:19 CST
163142a verified
metadata
license: mit
datasets:
  - CyberHarem/lisa_genshin
pipeline_tag: text-to-image
tags:
  - art
  - not-for-all-audiences

LoRA model of lisa/リサ/丽莎 (Genshin Impact)

What Is This?

This is the LoRA model of waifu lisa/リサ/丽莎 (Genshin Impact).

How Is It Trained?

  • This model is trained with kohya-ss/sd-scripts, and the test images are generated with a1111's webui and API sdk.
  • The auto-training framework is maintained by DeepGHS Team. The architecture of base model is is SD1.5.
  • Dataset used for training is the stage3-p480-1200 in CyberHarem/lisa_genshin, which contains 1341 images.
  • Trigger word is lisa_genshin.
  • Pruned core tags for this waifu are long hair, breasts, brown hair, green eyes, large breasts, hat, hair ornament, witch hat, purple headwear, hair between eyes, hair flower. You can add them to the prompt when some features of waifu (e.g. hair color) are not stable.
  • For more details in training, you can take a look at training configuration file.
  • For more details in LoRA, you can download it, and read the metadata with a1111's webui.

How to Use It?

After downloading the safetensors files for the specified step, you need to use them like common LoRA.

  • Recommended LoRA weight is 0.5-0.85.
  • Recommended trigger word weight is 0.7-1.1.

For example, if you want to use the model from step 6631, you need to download 6631/lisa_genshin.safetensors as LoRA. By using this model, you can generate images for the desired characters.

Which Step Should I Use?

We selected 5 good steps for you to choose. The best one is step 6631.

880 images (988.04 MiB) were generated for auto-testing.

Metrics Plot

The base model used for generating preview images is meinamix_v11.

Here are the preview of the recommended steps:

Step Epoch CCIP AI Corrupt Bikini Plus Score Download pattern_0_0 pattern_0_1 pattern_0_2 pattern_1 pattern_2_0 pattern_2_1 pattern_3 pattern_4 pattern_5 portrait_0 portrait_1 portrait_2 full_body_0 full_body_1 profile_0 profile_1 free_0 free_1 shorts maid_0 maid_1 miko yukata suit china bikini_0 bikini_1 bikini_2 sit squat kneel jump crossed_arms angry smile cry grin n_lie_0 n_lie_1 n_stand_0 n_stand_1 n_stand_2 n_sex_0 n_sex_1
6631 19 0.932 0.965 0.835 0.907 Download pattern_0_0 pattern_0_1 pattern_0_2 pattern_1 pattern_2_0 pattern_2_1 pattern_3 pattern_4 pattern_5 portrait_0 portrait_1 portrait_2 full_body_0 full_body_1 profile_0 profile_1 free_0 free_1 shorts maid_0 maid_1 miko yukata suit china bikini_0 bikini_1 bikini_2 sit squat kneel jump crossed_arms angry smile cry grin n_lie_0 n_lie_1 n_stand_0 n_stand_1 n_stand_2 n_sex_0 n_sex_1
1396 4 0.915 0.970 0.844 0.896 Download pattern_0_0 pattern_0_1 pattern_0_2 pattern_1 pattern_2_0 pattern_2_1 pattern_3 pattern_4 pattern_5 portrait_0 portrait_1 portrait_2 full_body_0 full_body_1 profile_0 profile_1 free_0 free_1 shorts maid_0 maid_1 miko yukata suit china bikini_0 bikini_1 bikini_2 sit squat kneel jump crossed_arms angry smile cry grin n_lie_0 n_lie_1 n_stand_0 n_stand_1 n_stand_2 n_sex_0 n_sex_1
1047 3 0.918 0.982 0.838 0.886 Download pattern_0_0 pattern_0_1 pattern_0_2 pattern_1 pattern_2_0 pattern_2_1 pattern_3 pattern_4 pattern_5 portrait_0 portrait_1 portrait_2 full_body_0 full_body_1 profile_0 profile_1 free_0 free_1 shorts maid_0 maid_1 miko yukata suit china bikini_0 bikini_1 bikini_2 sit squat kneel jump crossed_arms angry smile cry grin n_lie_0 n_lie_1 n_stand_0 n_stand_1 n_stand_2 n_sex_0 n_sex_1
6980 20 0.868 0.955 0.838 0.769 Download pattern_0_0 pattern_0_1 pattern_0_2 pattern_1 pattern_2_0 pattern_2_1 pattern_3 pattern_4 pattern_5 portrait_0 portrait_1 portrait_2 full_body_0 full_body_1 profile_0 profile_1 free_0 free_1 shorts maid_0 maid_1 miko yukata suit china bikini_0 bikini_1 bikini_2 sit squat kneel jump crossed_arms angry smile cry grin n_lie_0 n_lie_1 n_stand_0 n_stand_1 n_stand_2 n_sex_0 n_sex_1
1745 5 0.863 0.963 0.838 0.758 Download pattern_0_0 pattern_0_1 pattern_0_2 pattern_1 pattern_2_0 pattern_2_1 pattern_3 pattern_4 pattern_5 portrait_0 portrait_1 portrait_2 full_body_0 full_body_1 profile_0 profile_1 free_0 free_1 shorts maid_0 maid_1 miko yukata suit china bikini_0 bikini_1 bikini_2 sit squat kneel jump crossed_arms angry smile cry grin n_lie_0 n_lie_1 n_stand_0 n_stand_1 n_stand_2 n_sex_0 n_sex_1

Anything Else?

Because the automation of LoRA training always annoys some people. So for the following groups, it is not recommended to use this model and we express regret:

  1. Individuals who cannot tolerate any deviations from the original character design, even in the slightest detail.
  2. Individuals who are facing the application scenarios with high demands for accuracy in recreating character outfits.
  3. Individuals who cannot accept the potential randomness in AI-generated images based on the Stable Diffusion algorithm.
  4. Individuals who are not comfortable with the fully automated process of training character models using LoRA, or those who believe that training character models must be done purely through manual operations to avoid disrespecting the characters.
  5. Individuals who finds the generated image content offensive to their values.

All Steps

We uploaded the files in all steps. you can check the images, metrics and download them in the following links: