DeepBeepMeep commited on
Commit
dd4fde4
·
1 Parent(s): 2a8428c

New command parameters to prefill UI and configuration options

Browse files
Files changed (2) hide show
  1. README.md +4 -0
  2. gradio_server.py +2 -2
README.md CHANGED
@@ -19,6 +19,7 @@ In this repository, we present **Wan2.1**, a comprehensive and open suite of vid
19
 
20
 
21
  ## 🔥 Latest News!!
 
22
  * Mar 18 2022: 👋 Wan2.1GP v2.1: More Loras !: added support for 'Safetensors' and 'Replicate' Lora formats.\
23
  You will need to refresh the requirements with a *pip install -r requirements.txt*
24
  * Mar 17 2022: 👋 Wan2.1GP v2.0: The Lora festival continues:
@@ -242,6 +243,9 @@ You can define multiple lines of macros. If there is only one macro line, the ap
242
  --seed no : set default seed value\
243
  --frames no : set the default number of frames to generate\
244
  --steps no : set the default number of denoising steps\
 
 
 
245
  --check-loras : filter loras that are incompatible (will take a few seconds while refreshing the lora list or while starting the app)\
246
  --advanced : turn on the advanced mode while launching the app
247
 
 
19
 
20
 
21
  ## 🔥 Latest News!!
22
+ * Mar 18 2022: 👋 Wan2.1GP v2.11: Added more command line parameters to prefill the generation settings + customizable output directory and choice of type of metadata for generated videos. Many thanks to Tophness for his contributions. You will need one more *pip install -r requirements.txt* to reflect new dependencies\
23
  * Mar 18 2022: 👋 Wan2.1GP v2.1: More Loras !: added support for 'Safetensors' and 'Replicate' Lora formats.\
24
  You will need to refresh the requirements with a *pip install -r requirements.txt*
25
  * Mar 17 2022: 👋 Wan2.1GP v2.0: The Lora festival continues:
 
243
  --seed no : set default seed value\
244
  --frames no : set the default number of frames to generate\
245
  --steps no : set the default number of denoising steps\
246
+ --res resolution : default resolution, choices=["480p", "720p", "823p", "1024p", "1280p"]\
247
+ --teacache speed multiplier: Tea cache speed multiplier, choices=["0", "1.5", "1.75", "2.0", "2.25", "2.5"]\
248
+ --slg : turn on skip layer guidance for improved quality\
249
  --check-loras : filter loras that are incompatible (will take a few seconds while refreshing the lora list or while starting the app)\
250
  --advanced : turn on the advanced mode while launching the app
251
 
gradio_server.py CHANGED
@@ -236,7 +236,7 @@ def _parse_args():
236
  )
237
 
238
  parser.add_argument(
239
- "--skip-guidance",
240
  action="store_true",
241
  help="Enable skip guidance"
242
  )
@@ -1982,7 +1982,7 @@ def create_demo():
1982
  ("OFF", 0),
1983
  ("ON", 1),
1984
  ],
1985
- value= 1 if args.skip_guidance else 0,
1986
  visible=True,
1987
  scale = 1,
1988
  label="Skip Layer guidance"
 
236
  )
237
 
238
  parser.add_argument(
239
+ "--slg",
240
  action="store_true",
241
  help="Enable skip guidance"
242
  )
 
1982
  ("OFF", 0),
1983
  ("ON", 1),
1984
  ],
1985
+ value= 1 if args.slg else 0,
1986
  visible=True,
1987
  scale = 1,
1988
  label="Skip Layer guidance"