1580158
/
SD-CN-Animation
mirror of https://github.com/volotat/SD-CN-Animation.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

reference_only exception

pull/132/head
Alexey Borsky 2023-05-16 10:52:08 +03:00
parent 8d63dd5471
commit 9e08b4c7d3
3 changed files with 9 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
readme.md
View File

@ -60,6 +60,7 @@ To install the extension go to 'Extensions' tab in [Automatic1111 web-ui](https:
* If you see error like this ```IndexError: list index out of range``` try to restart webui, it should fix it. * If you see error like this ```IndexError: list index out of range``` try to restart webui, it should fix it.
* The extension might work incorrectly if 'Apply color correction to img2img results to match original colors.' option is enabled. Make sure to disable it in 'Settings' tab -> 'Stable Diffusion' section. * The extension might work incorrectly if 'Apply color correction to img2img results to match original colors.' option is enabled. Make sure to disable it in 'Settings' tab -> 'Stable Diffusion' section.
* If you have an error like 'Need to enable queue to use generators.', please update webui to the latest version. Beware that only [Automatic1111 web-ui](https://github.com/AUTOMATIC1111/stable-diffusion-webui) is fully supported. * If you have an error like 'Need to enable queue to use generators.', please update webui to the latest version. Beware that only [Automatic1111 web-ui](https://github.com/AUTOMATIC1111/stable-diffusion-webui) is fully supported.
* The extension is not compatible with Macs. If you have a case that extension is working for you or do you know how to make it compatible, please open a new discussion.
## Last version changes: v0.9 ## Last version changes: v0.9
* Fixed issues #69, #76, #91, #92. * Fixed issues #69, #76, #91, #92.
@ -73,3 +74,7 @@ To install the extension go to 'Extensions' tab in [Automatic1111 web-ui](https:
* Added ControlNet to txt2vid mode as well as fixing #86 issue, thanks to [@mariaWitch](https://github.com/mariaWitch) * Added ControlNet to txt2vid mode as well as fixing #86 issue, thanks to [@mariaWitch](https://github.com/mariaWitch)
* Fixed a major issue when ConrtolNet used wrong input images. Because of this vid2vid results were way worse than they should be. * Fixed a major issue when ConrtolNet used wrong input images. Because of this vid2vid results were way worse than they should be.
* Text to video mode now supports video as a guidance for ControlNet. It allows to create much stronger video stylizations. * Text to video mode now supports video as a guidance for ControlNet. It allows to create much stronger video stylizations.
<!--
* ControlNet with preprocessers like "reference_only", "reference_adain", "reference_adain+attn" are not reseted with video frames to have an ability to control style of the video.
-->

2
scripts/base_ui.py
View File

@ -171,7 +171,7 @@ def export_settings(*args):
raise Exception(msg) raise Exception(msg)
# convert CN params into a readable dict # convert CN params into a readable dict
cn_remove_list = ['low_vram', 'is_ui', 'input_mode', 'batch_images', 'output_dir', 'loopback'] cn_remove_list = ['low_vram', 'is_ui', 'input_mode', 'batch_images', 'output_dir', 'loopback', 'image']
args_dict['ControlNets'] = [] args_dict['ControlNets'] = []
for script_input in args_dict['script_inputs']: for script_input in args_dict['script_inputs']:

5
scripts/core/utils.py
View File

@ -121,8 +121,9 @@ def get_mode_args(mode, args_dict):
def set_CNs_input_image(args_dict, image): def set_CNs_input_image(args_dict, image):
for script_input in args_dict['script_inputs']: for script_input in args_dict['script_inputs']:
if type(script_input).__name__ == 'UiControlNetUnit': if type(script_input).__name__ == 'UiControlNetUnit':
script_input.batch_images = [np.array(image)] if script_input.module not in ["reference_only", "reference_adain", "reference_adain+attn"]:
script_input.image = np.array(image) script_input.image = np.array(image)
script_input.batch_images = [np.array(image)]
import time import time
import datetime import datetime