I just updated my AutomaticWebUI from v1.6.0-2-g4afaaf8a, over to 1.7 and noticed some weird behaviour now. (Edit: Also tried a fresh installed of 1.7 and the same thing occurs)
I use both the Adetailer and Dynamic Prompts (the latter with the 'Save template to metadata: Write prompt template into the PNG metadata' under Settings enabled). However, it seems like right now when Adetailer is enabled, it overrides the template prompt with the chosen variant/wildcard values. With that, the actual prompt = template every single time, instead of the template prompt containing the variant/wildcard format.
I've attached 2 screenshots below, one without adetailer, and one with adetailer enabled.
In summary, when adetailer is enabled, the template line = prompt line, instead of the variant or wildcard filepath.
Any insights would be greatly appreciated! Thank you in advance.
No adetailer:
With adetailer:
Nothing in console logs are out of the ordinary:
venv "E:\AI\Stable Diffusion\webui\venv\Scripts\Python.exe"
Python 3.10.9 (tags/v3.10.9:1dd9be6, Dec 6 2022, 20:01:21) [MSC v.1934 64 bit (AMD64)]
Version: v1.7.0
Commit hash: cf2772fab0af5573da775e7437e6acdca424f26e
Launching Web UI with arguments: --xformers
Style database not found: E:\AI\Stable Diffusion\webui\styles.csv
[-] ADetailer initialized. version: 23.11.1, num models: 9
Loading weights [ecefb796ff] from E:\AI\Stable Diffusion\webui\models\Stable-diffusion\neverendingDreamNED_v122BakedVae.safetensors
Creating model from config: E:\AI\Stable Diffusion\webui\configs\v1-inference.yaml
Running on local URL: http://127.0.0.1:7861
To create a public link, set share=True in launch().
Startup time: 8.8s (prepare environment: 1.9s, import torch: 2.3s, import gradio: 0.8s, setup paths: 0.7s, initialize shared: 0.3s, other imports: 0.6s, load scripts: 1.3s, create ui: 0.5s, gradio launch: 0.3s).
Applying attention optimization: xformers... done.
Model loaded in 3.0s (load weights from disk: 0.4s, create model: 0.5s, apply weights to model: 1.9s, calculate empty prompt: 0.1s).
100%|██████████████████████████████████████████████████████████████████████████████████| 20/20 [00:02<00:00, 8.35it/s]
Total progress: 100%|██████████████████████████████████████████████████████████████████| 20/20 [00:02<00:00, 9.43it/s]
100%|██████████████████████████████████████████████████████████████████████████████████| 20/20 [00:02<00:00, 9.09it/s]
Total progress: 95%|██████████████████████████████████████████████████████████████▋ | 19/20 [00:01<00:00, 10.65it/s]
0: 640x640 1 face, 4.0ms
Speed: 2.0ms preprocess, 4.0ms inference, 14.0ms postprocess per image at shape (1, 3, 640, 640)
100%|████████████████████████████████████████████████████████████████████████████████████| 9/9 [00:00<00:00, 10.90it/s]
Total progress: 100%|██████████████████████████████████████████████████████████████████| 20/20 [00:03<00:00, 5.91it/s]
100%|██████████████████████████████████████████████████████████████████████████████████| 20/20 [00:02<00:00, 9.96it/s]
Total progress: 95%|██████████████████████████████████████████████████████████████▋ | 19/20 [00:01<00:00, 10.91it/s]
0: 640x640 1 face, 4.0ms
Speed: 2.2ms preprocess, 4.0ms inference, 2.0ms postprocess per image at shape (1, 3, 640, 640)
100%|████████████████████████████████████████████████████████████████████████████████████| 9/9 [00:00<00:00, 10.82it/s]
Total progress: 100%|██████████████████████████████████████████████████████████████████| 20/20 [00:03<00:00, 6.31it/s]
100%|██████████████████████████████████████████████████████████████████████████████████| 20/20 [00:02<00:00, 9.76it/s]
Total progress: 100%|██████████████████████████████████████████████████████████████████| 20/20 [00:01<00:00, 10.14it/s]
100%|██████████████████████████████████████████████████████████████████████████████████| 20/20 [00:02<00:00, 8.74it/s]
Total progress: 100%|██████████████████████████████████████████████████████████████████| 20/20 [00:01<00:00, 10.59it/s]
0: 640x640 1 face, 3.5ms
Speed: 2.0ms preprocess, 3.5ms inference, 1.0ms postprocess per image at shape (1, 3, 640, 640)
100%|████████████████████████████████████████████████████████████████████████████████████| 9/9 [00:00<00:00, 10.65it/s]
Total progress: 100%|██████████████████████████████████████████████████████████████████| 20/20 [00:03<00:00, 6.14it/s]
Total progress: 100%|██████████████████████████████████████████████████████████████████| 20/20 [00:03<00:00, 10.59it/s]
Extensions used:
I just updated my AutomaticWebUI from v1.6.0-2-g4afaaf8a, over to 1.7 and noticed some weird behaviour now. (Edit: Also tried a fresh installed of 1.7 and the same thing occurs)
I use both the Adetailer and Dynamic Prompts (the latter with the 'Save template to metadata: Write prompt template into the PNG metadata' under Settings enabled). However, it seems like right now when Adetailer is enabled, it overrides the template prompt with the chosen variant/wildcard values. With that, the actual prompt = template every single time, instead of the template prompt containing the variant/wildcard format.
I've attached 2 screenshots below, one without adetailer, and one with adetailer enabled.
In summary, when adetailer is enabled, the template line = prompt line, instead of the variant or wildcard filepath.
Any insights would be greatly appreciated! Thank you in advance.
No adetailer:
With adetailer:
Nothing in console logs are out of the ordinary:
venv "E:\AI\Stable Diffusion\webui\venv\Scripts\Python.exe"
Python 3.10.9 (tags/v3.10.9:1dd9be6, Dec 6 2022, 20:01:21) [MSC v.1934 64 bit (AMD64)]
Version: v1.7.0
Commit hash: cf2772fab0af5573da775e7437e6acdca424f26e
Launching Web UI with arguments: --xformers
Style database not found: E:\AI\Stable Diffusion\webui\styles.csv
[-] ADetailer initialized. version: 23.11.1, num models: 9
Loading weights [ecefb796ff] from E:\AI\Stable Diffusion\webui\models\Stable-diffusion\neverendingDreamNED_v122BakedVae.safetensors
Creating model from config: E:\AI\Stable Diffusion\webui\configs\v1-inference.yaml
Running on local URL: http://127.0.0.1:7861
To create a public link, set
share=Trueinlaunch().Startup time: 8.8s (prepare environment: 1.9s, import torch: 2.3s, import gradio: 0.8s, setup paths: 0.7s, initialize shared: 0.3s, other imports: 0.6s, load scripts: 1.3s, create ui: 0.5s, gradio launch: 0.3s).
Applying attention optimization: xformers... done.
Model loaded in 3.0s (load weights from disk: 0.4s, create model: 0.5s, apply weights to model: 1.9s, calculate empty prompt: 0.1s).
100%|██████████████████████████████████████████████████████████████████████████████████| 20/20 [00:02<00:00, 8.35it/s]
Total progress: 100%|██████████████████████████████████████████████████████████████████| 20/20 [00:02<00:00, 9.43it/s]
100%|██████████████████████████████████████████████████████████████████████████████████| 20/20 [00:02<00:00, 9.09it/s]
Total progress: 95%|██████████████████████████████████████████████████████████████▋ | 19/20 [00:01<00:00, 10.65it/s]
0: 640x640 1 face, 4.0ms
Speed: 2.0ms preprocess, 4.0ms inference, 14.0ms postprocess per image at shape (1, 3, 640, 640)
100%|████████████████████████████████████████████████████████████████████████████████████| 9/9 [00:00<00:00, 10.90it/s]
Total progress: 100%|██████████████████████████████████████████████████████████████████| 20/20 [00:03<00:00, 5.91it/s]
100%|██████████████████████████████████████████████████████████████████████████████████| 20/20 [00:02<00:00, 9.96it/s]
Total progress: 95%|██████████████████████████████████████████████████████████████▋ | 19/20 [00:01<00:00, 10.91it/s]
0: 640x640 1 face, 4.0ms
Speed: 2.2ms preprocess, 4.0ms inference, 2.0ms postprocess per image at shape (1, 3, 640, 640)
100%|████████████████████████████████████████████████████████████████████████████████████| 9/9 [00:00<00:00, 10.82it/s]
Total progress: 100%|██████████████████████████████████████████████████████████████████| 20/20 [00:03<00:00, 6.31it/s]
100%|██████████████████████████████████████████████████████████████████████████████████| 20/20 [00:02<00:00, 9.76it/s]
Total progress: 100%|██████████████████████████████████████████████████████████████████| 20/20 [00:01<00:00, 10.14it/s]
100%|██████████████████████████████████████████████████████████████████████████████████| 20/20 [00:02<00:00, 8.74it/s]
Total progress: 100%|██████████████████████████████████████████████████████████████████| 20/20 [00:01<00:00, 10.59it/s]
0: 640x640 1 face, 3.5ms
Speed: 2.0ms preprocess, 3.5ms inference, 1.0ms postprocess per image at shape (1, 3, 640, 640)
100%|████████████████████████████████████████████████████████████████████████████████████| 9/9 [00:00<00:00, 10.65it/s]
Total progress: 100%|██████████████████████████████████████████████████████████████████| 20/20 [00:03<00:00, 6.14it/s]
Total progress: 100%|██████████████████████████████████████████████████████████████████| 20/20 [00:03<00:00, 10.59it/s]
Extensions used: