Text-to-Image
art
Not-For-All-Audiences
texas_arknights / README.md
narugo's picture
Upload model for texas/テキサス/德克萨斯 (Arknights), on 2024-01-27 13:44:45 UTC
39f47bc verified
|
raw
history blame
19.9 kB
metadata
license: mit
datasets:
  - CyberHarem/texas_arknights
pipeline_tag: text-to-image
tags:
  - art
  - not-for-all-audiences

Lora of texas/テキサス/德克萨斯 (Arknights)

What Is This?

This is the LoRA model of waifu texas/テキサス/德克萨斯 (Arknights).

How Is It Trained?

  • This model is trained with HCP-Diffusion.
  • The auto-training framework is maintained by DeepGHS Team.
  • The base model used for training is deepghs/animefull-latest.
  • Dataset used for training is the stage3-p480-800 in CyberHarem/texas_arknights, which contains 1312 images.
  • Batch size is 4, resolution is 720x720, clustering into 5 buckets.
  • Batch size for regularization dataset is 1, resolution is 720x720, clustering into 20 buckets.
  • Trained for 10000 steps, 40 checkpoints were saved.
  • Trigger word is texas_arknights.
  • Pruned core tags for this waifu are animal_ears, long_hair, black_hair, wolf_ears, bangs, animal_ear_fluff, hair_between_eyes, multicolored_hair, red_hair, two-tone_hair, breasts, tail, wolf_tail, wolf_girl. You do NOT have to add them in your prompts.

How to Use It?

If You Are Using A1111 WebUI v1.7+

Just use it like the classic LoRA. The LoRA we provided are bundled with the embedding file.

If You Are Using A1111 WebUI v1.6 or Lower

After downloading the pt and safetensors files for the specified step, you need to use them simultaneously. The pt file will be used as an embedding, while the safetensors file will be loaded for Lora.

For example, if you want to use the model from step 4250, you need to download 4250/texas_arknights.pt as the embedding and 4250/texas_arknights.safetensors for loading Lora. By using both files together, 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 4250.

2040 images (1.96 GiB) were generated for auto-testing.

Metrics Plot

The base model used for generating preview images is Meina/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_1_0 pattern_1_1 pattern_2 pattern_3 pattern_4_0 pattern_4_1 pattern_4_2 pattern_5 pattern_6 pattern_7 pattern_8 pattern_9_0 pattern_9_1 pattern_10 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
4250 13 0.963 0.970 0.824 0.827 Download pattern_0_0 pattern_0_1 pattern_1_0 pattern_1_1 pattern_2 pattern_3 pattern_4_0 pattern_4_1 pattern_4_2 pattern_5 pattern_6 pattern_7 pattern_8 pattern_9_0 pattern_9_1 pattern_10 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
4750 15 0.944 0.951 0.823 0.777 Download pattern_0_0 pattern_0_1 pattern_1_0 pattern_1_1 pattern_2 pattern_3 pattern_4_0 pattern_4_1 pattern_4_2 pattern_5 pattern_6 pattern_7 pattern_8 pattern_9_0 pattern_9_1 pattern_10 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
1500 5 0.939 0.963 0.826 0.770 Download pattern_0_0 pattern_0_1 pattern_1_0 pattern_1_1 pattern_2 pattern_3 pattern_4_0 pattern_4_1 pattern_4_2 pattern_5 pattern_6 pattern_7 pattern_8 pattern_9_0 pattern_9_1 pattern_10 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
9750 30 0.941 0.943 0.819 0.765 Download pattern_0_0 pattern_0_1 pattern_1_0 pattern_1_1 pattern_2 pattern_3 pattern_4_0 pattern_4_1 pattern_4_2 pattern_5 pattern_6 pattern_7 pattern_8 pattern_9_0 pattern_9_1 pattern_10 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
7500 23 0.935 0.940 0.820 0.750 Download pattern_0_0 pattern_0_1 pattern_1_0 pattern_1_1 pattern_2 pattern_3 pattern_4_0 pattern_4_1 pattern_4_2 pattern_5 pattern_6 pattern_7 pattern_8 pattern_9_0 pattern_9_1 pattern_10 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: