You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Greetings.
So far Stable Diffusion worked fine. I tried to install the TensorRT now. I installed it via the url and it seemed to work. I then restarted the ui. On startup it says (its german): https://ibb.co/XWQqssW
I can then still start the web-ui interface and generate images. I cant find any mentioning of a TensorRT though. Uninstalling the TensorRT gets rid of the error message and it works as before.
How to get TensorRT working now? I got a RTX 3080 which is not even optimal for that but I presume it should work?!
This issue is a recognized problem stemming from a bug in the installer. People are already working on a fix.
Temporary Solution:
In the meantime, you don't need to wait for the official fix. Please refer to this workaround detailed in issue #27. Following these steps should resolve the problem for you.
God bless you it might've worked. No more error message at least. However I dont see any TensorRT tab nor is there anything else than "None" or "Automatic" in the SD Unet dropdown menu. Under "installed" there is "Stable-Diffusion-WebUI-TensorRT" checked though.
I also dont know where to find the โGenerate Default Enginesโ button.
Launching Web UI with arguments:
No module 'xformers'. Proceeding without it.
[-] ADetailer initialized. version: 23.7.9, num models: 9
Loading weights [e6415c4892] from C:\ProgramData\Anaconda3\tortoise-tts\stable-diffusion-webui\models\Stable-diffusion\realisticVisionV20_v20.safetensors
Creating model from config: C:\ProgramData\Anaconda3\tortoise-tts\stable-diffusion-webui\configs\v1-inference.yaml
LatentDiffusion: Running in eps-prediction mode
DiffusionWrapper has 859.52 M params.
Couldn't find VAE named vae-ft-ema-560000-ema-pruned.ckpt; using None instead
Applying attention optimization: Doggettx... done.
Textual inversion embeddings loaded(1): easynegative
Model loaded in 7.6s (load weights from disk: 0.7s, create model: 0.3s, apply weights to model: 5.6s, apply half(): 0.3s, move model to device: 0.5s, calculate empty prompt: 0.1s).
*** Error executing callback ui_tabs_callback for C:\ProgramData\Anaconda3\tortoise-tts\stable-diffusion-webui\extensions\Stable-Diffusion-WebUI-TensorRT\scripts\trt.py
Traceback (most recent call last):
File "C:\ProgramData\Anaconda3\tortoise-tts\stable-diffusion-webui\modules\script_callbacks.py", line 153, in ui_tabs_callback
res += c.callback() or []
File "C:\ProgramData\Anaconda3\tortoise-tts\stable-diffusion-webui\extensions\Stable-Diffusion-WebUI-TensorRT\ui_trt.py", line 751, in on_ui_tabs
choices=get_valid_lora_checkpoints(),
File "C:\ProgramData\Anaconda3\tortoise-tts\stable-diffusion-webui\extensions\Stable-Diffusion-WebUI-TensorRT\ui_trt.py", line 536, in get_valid_lora_checkpoints
return [
File "C:\ProgramData\Anaconda3\tortoise-tts\stable-diffusion-webui\extensions\Stable-Diffusion-WebUI-TensorRT\ui_trt.py", line 539, in
if v["version"] == get_version_from_model(shared.sd_model)
File "C:\ProgramData\Anaconda3\tortoise-tts\stable-diffusion-webui\extensions\Stable-Diffusion-WebUI-TensorRT\ui_trt.py", line 26, in get_version_from_model
if sd_model.is_sd1:
File "C:\ProgramData\Anaconda3\tortoise-tts\stable-diffusion-webui\venv\lib\site-packages\torch\nn\modules\module.py", line 1614, in getattr
raise AttributeError("'{}' object has no attribute '{}'".format(
AttributeError: 'LatentDiffusion' object has no attribute 'is_sd1'
So this one here might be important?! "*** Error executing callback ui_tabs_callback for C:\ProgramData\Anaconda3\tortoise-tts\stable-diffusion-webui\extensions\Stable-Diffusion-WebUI-TensorRT\scripts\trt.py"
Activity
IndigoDosSantos commentedon Oct 19, 2023
Issue Explanation:
This issue is a recognized problem stemming from a bug in the installer. People are already working on a fix.
Temporary Solution:
In the meantime, you don't need to wait for the official fix. Please refer to this workaround detailed in issue #27. Following these steps should resolve the problem for you.
Bananamax commentedon Oct 19, 2023
God bless you it might've worked. No more error message at least. However I dont see any TensorRT tab nor is there anything else than "None" or "Automatic" in the SD Unet dropdown menu. Under "installed" there is "Stable-Diffusion-WebUI-TensorRT" checked though.
I also dont know where to find the โGenerate Default Enginesโ button.
contentis commentedon Oct 20, 2023
Can you check the shell for any errors when launch web UI?
Bananamax commentedon Oct 20, 2023
Launching Web UI with arguments:
No module 'xformers'. Proceeding without it.
[-] ADetailer initialized. version: 23.7.9, num models: 9
Loading weights [e6415c4892] from C:\ProgramData\Anaconda3\tortoise-tts\stable-diffusion-webui\models\Stable-diffusion\realisticVisionV20_v20.safetensors
Creating model from config: C:\ProgramData\Anaconda3\tortoise-tts\stable-diffusion-webui\configs\v1-inference.yaml
LatentDiffusion: Running in eps-prediction mode
DiffusionWrapper has 859.52 M params.
Couldn't find VAE named vae-ft-ema-560000-ema-pruned.ckpt; using None instead
Applying attention optimization: Doggettx... done.
Textual inversion embeddings loaded(1): easynegative
Model loaded in 7.6s (load weights from disk: 0.7s, create model: 0.3s, apply weights to model: 5.6s, apply half(): 0.3s, move model to device: 0.5s, calculate empty prompt: 0.1s).
*** Error executing callback ui_tabs_callback for C:\ProgramData\Anaconda3\tortoise-tts\stable-diffusion-webui\extensions\Stable-Diffusion-WebUI-TensorRT\scripts\trt.py
Traceback (most recent call last):
File "C:\ProgramData\Anaconda3\tortoise-tts\stable-diffusion-webui\modules\script_callbacks.py", line 153, in ui_tabs_callback
res += c.callback() or []
File "C:\ProgramData\Anaconda3\tortoise-tts\stable-diffusion-webui\extensions\Stable-Diffusion-WebUI-TensorRT\ui_trt.py", line 751, in on_ui_tabs
choices=get_valid_lora_checkpoints(),
File "C:\ProgramData\Anaconda3\tortoise-tts\stable-diffusion-webui\extensions\Stable-Diffusion-WebUI-TensorRT\ui_trt.py", line 536, in get_valid_lora_checkpoints
return [
File "C:\ProgramData\Anaconda3\tortoise-tts\stable-diffusion-webui\extensions\Stable-Diffusion-WebUI-TensorRT\ui_trt.py", line 539, in
if v["version"] == get_version_from_model(shared.sd_model)
File "C:\ProgramData\Anaconda3\tortoise-tts\stable-diffusion-webui\extensions\Stable-Diffusion-WebUI-TensorRT\ui_trt.py", line 26, in get_version_from_model
if sd_model.is_sd1:
File "C:\ProgramData\Anaconda3\tortoise-tts\stable-diffusion-webui\venv\lib\site-packages\torch\nn\modules\module.py", line 1614, in getattr
raise AttributeError("'{}' object has no attribute '{}'".format(
AttributeError: 'LatentDiffusion' object has no attribute 'is_sd1'
So this one here might be important?! "*** Error executing callback ui_tabs_callback for C:\ProgramData\Anaconda3\tortoise-tts\stable-diffusion-webui\extensions\Stable-Diffusion-WebUI-TensorRT\scripts\trt.py"
Bananamax commentedon Oct 27, 2023
So its a ruse its not loading any tensorRT modules. What a shame