stable-diffusion-webui-forge icon indicating copy to clipboard operation
stable-diffusion-webui-forge copied to clipboard
verified publisher icon lllyasviel

[Bug]: Dynamic Thresholding does not work.

Open Neytiri7 opened this issue 2 years ago • 1 comments

Checklist

  • [ ] The issue exists after disabling all extensions
  • [ ] 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
  • [ ] The issue exists in the current version of the webui
  • [ ] The issue has not been reported before recently
  • [ ] The issue has been reported before but has not been fixed yet

What happened?

The integrated DT does not work, nor does the other DTs you have installed.

Steps to reproduce the problem

  1. DT ON
  2. Create an image
  3. DT OFF
  4. Create an image
  5. Comparison between applied and not applied

What should have happened?

The image with DT applied and the image without DT applied must be different.

What browsers do you use to access the UI ?

No response

Sysinfo

sysinfo-2024-02-12-16-43.json

Console logs

Loading VAE weights specified in settings: O:\AI\SynologyDrive\stable-diffusion-webui-forge\models\VAE\sdxl_vae.safetensors
No Image data blocks found.
No Image data blocks found.
To load target model SDXLClipModel
Begin to load 1 model
Model loaded in 18.8s (load weights from disk: 0.6s, forge load real models: 13.7s, load VAE: 1.5s, load textual inversion embeddings: 0.9s, calculate empty prompt: 2.0s).
                                  To load target model SDXL
Begin to load 1 model00:00, ?it/s]
loading in lowvram mode 1395.780122756958
Moving model(s) has taken 0.65 seconds
100%|██████████████████████████████████████████████████████████████████████████████████| 20/20 [00:36<00:00,  1.84s/it]
To load target model AutoencoderKL███████████████████▏                                 | 20/41 [00:57<00:37,  1.81s/it]
Begin to load 1 model
Moving model(s) has taken 0.63 seconds
Upscale script freed memory successfully.
tiled upscale: 100%|███████████████████████████████████████████████████████████████████| 15/15 [00:07<00:00,  2.05it/s]
To load target model SDXL
Begin to load 1 model
loading in lowvram mode 1355.797776222229
Moving model(s) has taken 0.72 seconds
100%|██████████████████████████████████████████████████████████████████████████████████| 21/21 [01:33<00:00,  4.46s/it]
To load target model AutoencoderKL█████████████████████████████████████████████████████| 41/41 [02:44<00:00,  4.45s/it]
Begin to load 1 model
Moving model(s) has taken 0.65 seconds

0: 448x640 1 short_sleeved_shirt, 1 long_sleeved_shirt, 2 shortss, 243.7ms
Speed: 6.4ms preprocess, 243.7ms inference, 9.9ms postprocess per image at shape (1, 3, 448, 640)
Upscale script freed memory successfully.
tiled upscale: 100%|███████████████████████████████████████████████████████████████████| 15/15 [00:04<00:00,  3.10it/s]
To load target model SDXL
Begin to load 1 model
loading in lowvram mode 1358.0029296875
Moving model(s) has taken 0.73 seconds
100%|████████████████████████████████████████████████████████████████████████████████████| 9/9 [00:16<00:00,  1.81s/it]
To load target model AutoencoderKL
Begin to load 1 model
Moving model(s) has taken 0.61 seconds
Upscale script freed memory successfully.
tiled upscale: 100%|███████████████████████████████████████████████████████████████████| 12/12 [00:03<00:00,  3.29it/s]
To load target model SDXL
Begin to load 1 model
loading in lowvram mode 1361.9820461273193
Moving model(s) has taken 0.72 seconds
100%|████████████████████████████████████████████████████████████████████████████████████| 9/9 [00:16<00:00,  1.81s/it]
To load target model AutoencoderKL
Begin to load 1 model
Moving model(s) has taken 0.61 seconds
Upscale script freed memory successfully.
tiled upscale: 100%|█████████████████████████████████████████████████████████████████████| 6/6 [00:01<00:00,  3.28it/s]
To load target model SDXL
Begin to load 1 model
loading in lowvram mode 1361.651141166687
Moving model(s) has taken 0.72 seconds
100%|████████████████████████████████████████████████████████████████████████████████████| 9/9 [00:16<00:00,  1.81s/it]
To load target model AutoencoderKL
Begin to load 1 model
Moving model(s) has taken 0.61 seconds
Upscale script freed memory successfully.
tiled upscale: 100%|█████████████████████████████████████████████████████████████████████| 4/4 [00:01<00:00,  3.28it/s]
To load target model SDXL
Begin to load 1 model
loading in lowvram mode 1357.8586988449097
Moving model(s) has taken 0.71 seconds
100%|████████████████████████████████████████████████████████████████████████████████████| 9/9 [00:16<00:00,  1.80s/it]
To load target model AutoencoderKL
Begin to load 1 model
Moving model(s) has taken 0.61 seconds

0: 448x640 4 hands, 151.9ms
Speed: 3.0ms preprocess, 151.9ms inference, 1.0ms postprocess per image at shape (1, 3, 448, 640)
Upscale script freed memory successfully.
tiled upscale: 100%|█████████████████████████████████████████████████████████████████████| 4/4 [00:01<00:00,  2.81it/s]
To load target model SDXL
Begin to load 1 model
loading in lowvram mode 1353.1407747268677
Moving model(s) has taken 0.70 seconds
100%|████████████████████████████████████████████████████████████████████████████████████| 9/9 [00:16<00:00,  1.82s/it]
To load target model AutoencoderKL
Begin to load 1 model
Moving model(s) has taken 0.67 seconds
Upscale script freed memory successfully.
tiled upscale: 100%|█████████████████████████████████████████████████████████████████████| 2/2 [00:00<00:00,  3.29it/s]
To load target model SDXL
Begin to load 1 model
loading in lowvram mode 1352.7377548217773
Moving model(s) has taken 0.70 seconds
100%|████████████████████████████████████████████████████████████████████████████████████| 9/9 [00:16<00:00,  1.82s/it]
To load target model AutoencoderKL
Begin to load 1 model
Moving model(s) has taken 0.65 seconds
Upscale script freed memory successfully.
tiled upscale: 100%|█████████████████████████████████████████████████████████████████████| 2/2 [00:00<00:00,  3.22it/s]
To load target model SDXL
Begin to load 1 model
loading in lowvram mode 1352.334734916687
Moving model(s) has taken 0.70 seconds
100%|████████████████████████████████████████████████████████████████████████████████████| 9/9 [00:16<00:00,  1.82s/it]
To load target model AutoencoderKL
Begin to load 1 model
Moving model(s) has taken 0.64 seconds
Upscale script freed memory successfully.
tiled upscale: 100%|█████████████████████████████████████████████████████████████████████| 4/4 [00:01<00:00,  3.19it/s]
To load target model SDXL
Begin to load 1 model
loading in lowvram mode 1351.9317150115967
Moving model(s) has taken 0.69 seconds
100%|████████████████████████████████████████████████████████████████████████████████████| 9/9 [00:16<00:00,  1.82s/it]
To load target model AutoencoderKL
Begin to load 1 model
Moving model(s) has taken 0.65 seconds

0: 448x640 2 persons, 143.8ms
Speed: 3.4ms preprocess, 143.8ms inference, 44.6ms postprocess per image at shape (1, 3, 448, 640)

0: 448x640 2 faces, 111.0ms
Speed: 3.5ms preprocess, 111.0ms inference, 1.0ms postprocess per image at shape (1, 3, 448, 640)
Upscale script freed memory successfully.
tiled upscale: 100%|█████████████████████████████████████████████████████████████████████| 4/4 [00:01<00:00,  3.16it/s]
To load target model SDXL
Begin to load 1 model
loading in lowvram mode 1327.5142726898193
Moving model(s) has taken 0.72 seconds
100%|████████████████████████████████████████████████████████████████████████████████████| 9/9 [00:16<00:00,  1.83s/it]
To load target model AutoencoderKL
Begin to load 1 model
Moving model(s) has taken 0.58 seconds

0: 448x640 2 persons, 9.5ms
Speed: 2.0ms preprocess, 9.5ms inference, 2.5ms postprocess per image at shape (1, 3, 448, 640)

0: 448x640 2 faces, 8.0ms
Speed: 2.0ms preprocess, 8.0ms inference, 1.5ms postprocess per image at shape (1, 3, 448, 640)

0: 512x768 4 hands, 110.0ms
Speed: 4.3ms preprocess, 110.0ms inference, 2.0ms postprocess per image at shape (1, 3, 512, 768)
Upscale script freed memory successfully.
tiled upscale: 100%|███████████████████████████████████████████████████████████████████| 10/10 [00:03<00:00,  3.21it/s]
To load target model SDXL
Begin to load 1 model
loading in lowvram mode 1317.1859970092773
Moving model(s) has taken 0.71 seconds
100%|████████████████████████████████████████████████████████████████████████████████████| 9/9 [00:16<00:00,  1.84s/it]
To load target model AutoencoderKL
Begin to load 1 model
Moving model(s) has taken 0.88 seconds
Upscale script freed memory successfully.
tiled upscale: 100%|███████████████████████████████████████████████████████████████████| 12/12 [00:03<00:00,  3.13it/s]
To load target model SDXL
Begin to load 1 model
loading in lowvram mode 1354.9590587615967
Moving model(s) has taken 0.74 seconds
100%|████████████████████████████████████████████████████████████████████████████████████| 9/9 [00:16<00:00,  1.83s/it]
To load target model AutoencoderKL
Begin to load 1 model
Moving model(s) has taken 0.67 seconds
Total progress: 100%|██████████████████████████████████████████████████████████████████| 41/41 [07:50<00:00, 11.47s/it]
Total progress: 100%|██████████████████████████████████████████████████████████████████| 41/41 [07:50<00:00,  4.45s/it]

Additional information

A20240213_012539_445085-side

Neytiri7 avatar Feb 12 '24 16:02 Neytiri7

Same problem, and I found that DT can't be used with LatentModified

mxicat avatar Oct 07 '24 09:10 mxicat