Views
No views yet
Disty0/sotediffusion-wuerstchen3-decoder into the model name and press download.Disty0/sotediffusion-wuerstchen3-decoder after the download process is complete.newest, extremely aesthetic, best quality,very displeasing, worst quality, monochrome, realistic, oldest, loli,pip install diffusers1import torch
2from diffusers import StableCascadeCombinedPipeline
3
4device = "cuda"
5dtype = torch.bfloat16 # or torch.float16
6model = "Disty0/sotediffusion-wuerstchen3-decoder"
7
8pipe = StableCascadeCombinedPipeline.from_pretrained(model, torch_dtype=dtype)
9
10# send everything to the gpu:
11pipe = pipe.to(device, dtype=dtype)
12pipe.prior_pipe = pipe.prior_pipe.to(device, dtype=dtype)
13
14# or enable model offload to save vram:
15# pipe.enable_model_cpu_offload()
16
17
18
19prompt = "newest, extremely aesthetic, best quality, 1girl, solo, cat ears, pink hair, orange eyes, long hair, bare shoulders, looking at viewer, smile, indoors, casual, living room, playing guitar,"
20negative_prompt = "very displeasing, worst quality, monochrome, realistic, oldest, loli,"
21output = pipe(
22 width=1024,
23 height=1536,
24 prompt=prompt,
25 negative_prompt=negative_prompt,
26 decoder_guidance_scale=2.0,
27 prior_guidance_scale=7.0,
28 prior_num_inference_steps=30,
29 output_type="pil",
30 num_inference_steps=10
31).images[0]
32
33## do something with the output image| parameter | value |
|---|---|
| amp | bf16 |
| weights | fp32 |
| save weights | fp16 |
| resolution | 1024x1024 |
| effective batch size | 128 |
| unet learning rate | 1e-5 |
| te learning rate | 4e-6 |
| optimizer | Adafactor |
| images | 6M |
| epochs | 3 |
| parameter | value |
|---|---|
| amp | bf16 |
| weights | fp32 |
| save weights | fp16 |
| resolution | 1024x1024 |
| effective batch size | 128 |
| unet learning rate | 4e-6 |
| te learning rate | none |
| optimizer | Adafactor |
| images | 120K |
| epochs | 16 |
python /mnt/DataSSD/AI/Apps/kohya_ss/sd-scripts/finetune/tag_images_by_wd14_tagger.py --model_dir "/mnt/DataSSD/AI/models/wd14_tagger_model" --repo_id "SmilingWolf/wd-swinv2-tagger-v3" --recursive --remove_underscore --use_rating_tags --character_tags_first --character_tag_expand --append_tags --onnx --caption_separator ", " --general_threshold 0.35 --character_threshold 0.50 --batch_size 4 --caption_extension ".txt" ./| dataset name | total images |
|---|---|
| newest | 1.848.331 |
| recent | 1.380.630 |
| mid | 993.227 |
| early | 566.152 |
| oldest | 160.397 |
| pixiv | 343.614 |
| visual novel cg | 231.358 |
| anime wallpaper | 104.790 |
| Total | 5.628.499 |
aesthetic tags, quality tags, date tags, custom tags, rating tags, character, series, rest of the tags| tag | date |
|---|---|
| newest | 2022 to 2024 |
| recent | 2019 to 2021 |
| mid | 2015 to 2018 |
| early | 2011 to 2014 |
| oldest | 2005 to 2010 |
| score greater than | tag | count |
|---|---|---|
| 0.90 | extremely aesthetic | 125.451 |
| 0.80 | very aesthetic | 887.382 |
| 0.70 | aesthetic | 1.049.857 |
| 0.50 | slightly aesthetic | 1.643.091 |
| 0.40 | not displeasing | 569.543 |
| 0.30 | not aesthetic | 445.188 |
| 0.20 | slightly displeasing | 341.424 |
| 0.10 | displeasing | 237.660 |
| rest of them | very displeasing | 328.712 |
| score greater than | tag | count |
|---|---|---|
| 0.980 | best quality | 1.270.447 |
| 0.900 | high quality | 498.244 |
| 0.750 | great quality | 351.006 |
| 0.500 | medium quality | 366.448 |
| 0.250 | normal quality | 368.380 |
| 0.125 | bad quality | 279.050 |
| 0.025 | low quality | 538.958 |
| rest of them | worst quality | 1.955.966 |
| tag | count |
|---|---|
| general | 1.416.451 |
| sensitive | 3.447.664 |
| nsfw | 427.459 |
| explicit nsfw | 336.925 |
| dataset name | custom tag |
|---|---|
| image boards | date, |
| text | The text says "text", |
| characters | character, series |
| pixiv | art by Display_Name, |
| visual novel cg | Full_VN_Name (short_3_letter_name), visual novel cg, |
| anime wallpaper | date, anime wallpaper, |