[Bug]: Textual Inversion not correctly added to the infotext

ameyukisora commented 7 months ago

Checklist

[X] The issue exists after disabling all extensions
[X] The issue exists on a clean installation of webui
[ ] The issue is caused by an extension, but I believe it is caused by a bug in the webui
[X] The issue exists in the current version of the webui
[X] The issue has not been reported before recently
[ ] The issue has been reported before but has not been fixed yet

What happened?

The Lora information is missing, and the Textual Inversion information is only added to the infotext upon the first generation after launch. my settings second generation

Steps to reproduce the problem

Launch the webui and generate images twice using Lora and TI.

What should have happened?

Textual Inversion and Lora information were added.

What browsers do you use to access the UI ?

Google Chrome

Sysinfo

sysinfo-2024-02-15-12-29.json

Console logs

Python 3.10.6 (tags/v3.10.6:9c7b4bd, Aug  1 2022, 21:53:49) [MSC v.1932 64 bit (AMD64)]
Version: f0.0.12-latest-155-gd81e353d
Commit hash: d81e353d8928147bbd973068d0efbb2802affe0f
loading WD14-tagger reqs from D:\Program\webui_forge_cu121_torch21\webui\extensions\stable-diffusion-webui-wd14-tagger\requirements.txt
Checking WD14-tagger requirements.
Launching Web UI with arguments:
Total VRAM 4096 MB, total RAM 32384 MB
Trying to enable lowvram mode because your GPU seems to have 4GB or less. If you don't want this use: --always-normal-vram
Set vram state to: LOW_VRAM
Device: cuda:0 NVIDIA GeForce RTX 3050 Laptop GPU : native
VAE dtype: torch.bfloat16
2024-02-15 19:41:02.076125: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.
WARNING:tensorflow:From D:\Program\webui_forge_cu121_torch21\system\python\lib\site-packages\keras\src\losses.py:2976: The name tf.losses.sparse_softmax_cross_entropy is deprecated. Please use tf.compat.v1.losses.sparse_softmax_cross_entropy instead.

no module 'xformers'. Processing without...
no module 'xformers'. Processing without...
No module 'xformers'. Proceeding without it.
D:\Program\webui_forge_cu121_torch21\system\python\lib\site-packages\pytorch_lightning\utilities\distributed.py:258: LightningDeprecationWarning: `pytorch_lightning.utilities.distributed.rank_zero_only` has been deprecated in v1.8.1 and will be removed in v2.0.0. You can import it from `pytorch_lightning.utilities` instead.
  rank_zero_deprecation(
Using pytorch cross attention
ControlNet preprocessor location: D:\Program\webui_forge_cu121_torch21\webui\models\ControlNetPreprocessor
Tag Autocomplete: Could not locate model-keyword extension, Lora trigger word completion will be limited to those added through the extra networks menu.
sd-webui-prompt-all-in-one background API service started successfully.
== WD14 tagger /gpu:0, uname_result(system='Windows', node='FX507ZC', release='10', version='10.0.22631', machine='AMD64') ==
Loading weights [771c8fd970] from D:\Program\webui_forge_cu121_torch21\webui\models\Stable-diffusion\meinapastel_v4AnimeIllustration.safetensors
2024-02-15 19:41:14,544 - ControlNet - INFO - ControlNet UI callback registered.
model_type EPS
UNet ADM Dimension 0
Running on local URL:  http://127.0.0.1:7860

To create a public link, set `share=True` in `launch()`.
Startup time: 25.6s (prepare environment: 5.5s, import torch: 12.5s, other imports: 0.4s, load scripts: 3.5s, create ui: 0.9s, gradio launch: 0.4s, app_started_callback: 2.2s).
Using pytorch attention in VAE
Working with z of shape (1, 4, 32, 32) = 4096 dimensions.
Using pytorch attention in VAE
extra {'cond_stage_model.clip_l.text_projection', 'cond_stage_model.clip_l.logit_scale'}
left over keys: dict_keys(['alphas_cumprod', 'alphas_cumprod_prev', 'betas', 'log_one_minus_alphas_cumprod', 'model_ema.decay', 'model_ema.num_updates', 'posterior_log_variance_clipped', 'posterior_mean_coef1', 'posterior_mean_coef2', 'posterior_variance', 'sqrt_alphas_cumprod', 'sqrt_one_minus_alphas_cumprod', 'sqrt_recip_alphas_cumprod', 'sqrt_recipm1_alphas_cumprod'])
Loading VAE weights specified in settings: D:\Program\webui_forge_cu121_torch21\webui\models\VAE\animevae.pt
To load target model SD1ClipModel
Begin to load 1 model
Model loaded in 5.4s (load weights from disk: 0.9s, forge load real models: 3.2s, load VAE: 0.8s, calculate empty prompt: 0.5s).
To load target model SD1ClipModel
Begin to load 1 model
unload clone 0
Moving model(s) has taken 0.24 seconds
To load target model BaseModel
Begin to load 1 model
Moving model(s) has taken 0.35 seconds
100%|██████████████████████████████████████████████████████████████████████████████████| 40/40 [00:33<00:00,  1.18it/s]
To load target model AutoencoderKL█████████████████████████████████████████████████████| 40/40 [00:32<00:00,  1.18it/s]
Begin to load 1 model
Moving model(s) has taken 0.47 seconds
Total progress: 100%|██████████████████████████████████████████████████████████████████| 40/40 [00:34<00:00,  1.16it/s]
To load target model BaseModel█████████████████████████████████████████████████████████| 40/40 [00:34<00:00,  1.18it/s]
Begin to load 1 model
Moving model(s) has taken 0.68 seconds
100%|██████████████████████████████████████████████████████████████████████████████████| 40/40 [00:33<00:00,  1.19it/s]
To load target model AutoencoderKL█████████████████████████████████████████████████████| 40/40 [00:32<00:00,  1.19it/s]
Begin to load 1 model
Moving model(s) has taken 0.35 seconds
Total progress: 100%|██████████████████████████████████████████████████████████████████| 40/40 [00:34<00:00,  1.14it/s]
Total progress: 100%|██████████████████████████████████████████████████████████████████| 40/40 [00:34<00:00,  1.19it/s]

Additional information

No response

catboxanon commented 6 months ago

Repurposing this issue for only the Textual Inversion piece since they should be handled as separate issues. LoRA infotext is being tracked in https://github.com/lllyasviel/stable-diffusion-webui-forge/issues/372.

lllyasviel commented 6 months ago

I can reproduce in original webui dev branch so it should be forward to webui issues

catboxanon commented 6 months ago

Looks like this has existed since at least last September. https://github.com/AUTOMATIC1111/stable-diffusion-webui/issues/13117

lllyasviel commented 6 months ago

Looks like this has existed since at least last September. AUTOMATIC1111/stable-diffusion-webui#13117

but it is worse. dev branch has the problem even without refiner

lllyasviel / stable-diffusion-webui-forge