kijai
99d012230f
Catch missing taew2_1.safetensors better
2025-08-02 02:09:42 +03:00
kijai
a9925496d5
update some workflows
2025-08-02 02:03:01 +03:00
kijai
907d1b0b0f
5B + context windows
2025-08-02 00:34:10 +03:00
kijai
25fe9ea642
handle cancellation better
2025-08-01 21:57:08 +03:00
kijai
168f3ccbee
Update nodes.py
2025-08-01 21:24:35 +03:00
kijai
d9be7b9c26
Allow other schedulers for 5B
2025-08-01 21:21:55 +03:00
kijai
e05864e751
Update nodes.py
2025-08-01 18:31:40 +03:00
kijai
83bb0e7f35
fp8 text encoder fixes
2025-08-01 17:42:32 +03:00
kijai
8321e19009
Fix single text encoder after previous change
2025-08-01 14:45:29 +03:00
kijai
5406a72f62
Improve text encoder cache and add alternative node which leaves nothing to memory after encoding
...
WanVideoTextEncodeCached -node will load T5 when the prompt is not found in the cache, then unload it completely.
2025-08-01 12:36:19 +03:00
kijai
9edab74562
Default non_blocking to False
...
too many RAM issues
2025-08-01 02:29:07 +03:00
kijai
7eebde487f
typo
2025-08-01 00:54:54 +03:00
kijai
945700d56e
5B fixes
2025-07-31 22:41:56 +03:00
kijai
5bacc50088
Add safety check for context windows to avoid crash on tensor slicing
2025-07-31 17:09:05 +03:00
kijai
b60814fb6b
Fix split prompting, get rid of diffusers on model class
2025-07-31 15:11:47 +03:00
kijai
10b67de349
Fix loading TAEW from extra paths
2025-07-31 13:47:59 +03:00
kijai
4cf2ffc979
Merge branch 'main' of https://github.com/kijai/ComfyUI-WanVideoWrapper
2025-07-31 12:50:17 +03:00
kijai
ef23a6213d
return denoised samples as well for previewing unfinished latents
2025-07-31 12:50:10 +03:00
Jukka Seppänen
ee1e762a7f
Update readme.md
2025-07-31 12:37:16 +03:00
kijai
0cc4583653
flowedit fix
2025-07-31 12:21:40 +03:00
kijai
e545b18627
vid2vid fix
...
Need to use add_noise_to_samples = True now for vid2vid, defaulting to False to not break 2.2 dual sampler workflows, but hardcode to always be True if denoise is used to not break old workflows
2025-07-30 19:41:51 +03:00
kijai
4eabdcce78
wrong way around
2025-07-30 18:45:19 +03:00
kijai
138b377d1d
Fix loading fp8 models where everything is fp8...
2025-07-30 17:34:56 +03:00
kijai
9a5d752ba1
Support custom sigmas on more schedulers
2025-07-30 16:20:48 +03:00
kijai
ec066008a8
Make start/end step work with vid2vid
2025-07-30 15:59:22 +03:00
kijai
406643f8ee
Create wanvideo_2_2_5B_I2V_example_WIP.json
2025-07-30 00:46:46 +03:00
kijai
6ef3ee83ef
Update nodes.py
2025-07-30 00:40:42 +03:00
kijai
3f4e8433bd
Add node to allow getting BasicScheduler sigmas
2025-07-29 23:06:01 +03:00
kijai
1570287db1
Update nodes_model_loading.py
2025-07-29 18:10:02 +03:00
kijai
15a57d22f7
fix slightly increased memory use
2025-07-29 18:08:32 +03:00
kijai
f835baa3d3
fix riflex
2025-07-29 10:52:39 +03:00
kijai
01e452c0d1
Update wanvideo2_2_I2V_A14B_example_WIP.json
2025-07-29 09:14:45 +03:00
kijai
234cffbf24
Fix comfy org scaled models giving black output
2025-07-29 08:05:48 +03:00
kijai
de11d52348
Update wanvideo2_2_I2V_A14B_example_WIP.json
2025-07-29 02:46:01 +03:00
kijai
6875b99611
remove this for now
2025-07-29 02:33:20 +03:00
kijai
e4fb931878
Update wanvideo2_2_I2V_A14B_example_WIP.json
2025-07-29 02:33:12 +03:00
kijai
5238f40fe3
Update nodes.py
2025-07-29 02:20:20 +03:00
kijai
a49936b645
Create wanvideo2_2_I2V_A14B_example_WIP.json
2025-07-29 02:20:17 +03:00
kijai
a3032e4363
clear lora patches first
2025-07-29 01:45:25 +03:00
kijai
7e290c67bf
Fix comfy progress bar when not doing full steps
2025-07-28 23:16:06 +03:00
kijai
fb7073259f
detect 2.2 I2V
...
untested
2025-07-28 22:43:37 +03:00
kijai
498c6859fe
Merge branch 'pr/883'
2025-07-28 22:16:48 +03:00
kijai
08d4569794
Update nodes.py
2025-07-28 21:42:35 +03:00
kijai
d6e9af7090
2.2 stuff
2025-07-28 21:38:40 +03:00
kabachuha
fd285a7e7d
implement tangential guidance
2025-07-28 21:08:10 +03:00
kijai
998a69cc0a
Update utils.py
2025-07-28 10:46:46 +03:00
kijai
3659c3f6e6
Progress bar for text encoding
2025-07-28 10:00:17 +03:00
kijai
ee6e790d80
Update nodes.py
2025-07-28 09:50:50 +03:00
kijai
5e725ff8fb
Allow running T5 no cpu
...
This is actually surprisingly fast, on AMD Ryzen 9 9900X it's faster to not move the T5 to GPU than to keep it on CPU all the way.
2025-07-28 09:39:36 +03:00
Jukka Seppänen
925ec31578
Merge pull request #876 from AustinMroz/main
...
Fix animated latent preview compatibility
2025-07-27 19:33:11 +03:00
kijai