[Bug]: txt2video won't generate videos

helishmopter commented 9 months ago

Checklist

[ ] The issue exists after disabling all extensions
[X] The issue exists on a clean installation of webui
[X] 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?

Clean installation to 1.8 won't allow generating videos in txt2video tab (modelscope, zeroscope). Clicking 'generate' will result in just changing to grey buttons to 'interrupt' and 'skip', but no calculation happening in webUI or terminal. Reverting to 1.7 fixed the issue for now.

Steps to reproduce the problem

clean install automatic1111
add extension txt2video
generate video in txt2video tab (either txt2vid or vid2vid)

What should have happened?

produce video

What browsers do you use to access the UI ?

Mozilla Firefox, Brave, Microsoft Edge

Sysinfo

sysinfo-2024-03-03-16-49.json

Console logs

venv "D:\stable_diffusion\stable-diffusion-webui\venv\Scripts\Python.exe"
Python 3.10.6 (tags/v3.10.6:9c7b4bd, Aug  1 2022, 21:53:49) [MSC v.1932 64 bit (AMD64)]
Version: v1.7.0
Commit hash: cf2772fab0af5573da775e7437e6acdca424f26e
Launching Web UI with arguments: --api --xformers --autolaunch
Style database not found: D:\stable_diffusion\stable-diffusion-webui\styles.csv
Loading weights [6ce0161689] from D:\stable_diffusion\stable-diffusion-webui\models\Stable-diffusion\v1-5-pruned-emaonly.safetensors
2024-03-03 11:52:33,327 - AnimateDiff - INFO - Injecting LCM to UI.
2024-03-03 11:52:33,455 - AnimateDiff - INFO - Hacking i2i-batch.
D:\stable_diffusion\stable-diffusion-webui\extensions\sd-webui-text2video\scripts\text2vid.py:48: GradioDeprecationWarning: The `style` method is deprecated. Please set these arguments in the constructor instead.
  with gr.Row(elem_id='t2v-core').style(equal_height=False, variant='compact'):
Creating model from config: D:\stable_diffusion\stable-diffusion-webui\configs\v1-inference.yaml

Additional information

console log is for 1.7. i wrote this bug report after reverting back from 1.8

MrFrankDavis commented 9 months ago

I'm experiencing the exact same issue. I downloaded Forge UI and tried installing the text2video extension, and it did exactly the same thing as Automatic1111. I also noticed the Deforum extension tab is missing, but it shows as installed on my extension tab.

TheOneTrueNiz commented 9 months ago

Also dealing with the same issue with 1.8

sclewis90 commented 7 months ago

I also have run into this issue. My stable diffusion install runs fine otherwise, AMD Radeon 7900xt GPU, arch linux. Followed all the instructions appropriately and can click generate but just get two grey buttons and no video generation

AUTOMATIC1111 / stable-diffusion-webui