kijai
ae768f53a4
Make merge_lora switches with multiple loras behave like it used to and how the tooltip indicates
2025-09-06 19:28:16 +03:00
kijai
bafd5503ac
Fix unianim error when using ref pose
2025-09-05 23:38:08 +03:00
kijai
edea93286c
Small potential tweaks to Pusa vram use
2025-09-05 16:00:18 +03:00
kijai
fbf8f169b6
Update nodes.py
2025-09-05 15:59:01 +03:00
kijai
0ad2b00cc0
Fix force_offload on Multi/InfiniteTalk long I2V node
2025-09-05 15:54:11 +03:00
kijai
9b864b987b
Don't error even if redundant offloading is enabled for single text encode
2025-09-04 16:20:44 +03:00
kijai
cbbf44f3bc
Add Pusa 2.2 example
2025-09-04 02:22:54 +03:00
kijai
c38da2242d
version
2025-09-03 22:49:02 +03:00
kijai
d05796ffb3
Update requirements.txt
2025-09-03 22:48:22 +03:00
kijai
488b6628c7
typo
2025-09-03 22:47:42 +03:00
kijai
8131eaef23
update tooltip
2025-09-03 22:26:07 +03:00
kijai
242637db5c
Accept per latent noise multiplier list for Pusa as well
2025-09-03 22:18:37 +03:00
kijai
24ec3f6960
Add WanVideoLoraSelectByName
...
select lora by name string
2025-09-03 20:22:41 +03:00
kijai
02da8fed47
sigma plot tweaks
2025-09-03 20:01:55 +03:00
kijai
7a29bcb18a
Fix sigma graph
2025-09-03 19:49:00 +03:00
kijai
617ce55938
Fix up pusa noise multipliers indexing
2025-09-03 19:24:47 +03:00
kijai
e76bf4d899
Add Pusa additional noise handling
2025-09-03 18:32:34 +03:00
kijai
493106b555
Revert this as it didn't end up working
...
Pusa extra latents seem to need to be encoded individually
2025-09-03 15:48:14 +03:00
kijai
54391300b1
Never use main_device with unmerged loras
2025-09-03 10:00:51 +03:00
kijai
c57ffd8150
update example
2025-09-03 00:41:23 +03:00
kijai
838e095dbd
Update model.py
2025-09-02 23:46:04 +03:00
kijai
863ea45d23
Update model.py
2025-09-02 23:34:34 +03:00
kijai
44f9584f16
Fix S2V
2025-09-02 23:31:47 +03:00
kijai
cc3b79ab18
Update nodes.py
2025-09-02 21:08:02 +03:00
kijai
cdfa3a8661
Update nodes.py
2025-09-02 21:05:04 +03:00
kijai
1492310544
Update nodes.py
2025-09-02 20:49:24 +03:00
kijai
0ad24cd7e7
Allow for multiple I2V images for context windows
...
Similarly as multiple prompts already work, use the new WanVideoEncodeLatentBatch -node to encode them
2025-09-02 19:28:33 +03:00
kijai
c538cd4c8a
Fix unmerged lora
...
oops
2025-09-02 18:48:25 +03:00
kijai
3183589eff
Merge branch 'main' of https://github.com/kijai/ComfyUI-WanVideoWrapper
2025-09-02 17:09:12 +03:00
kijai
4cf23a5a40
Can't do this inplace with all models
2025-09-02 17:09:05 +03:00
Jukka Seppänen
0405dde5a2
Merge pull request #1165 from zinigor/fix/unbound-local-error
...
Moved dimension update to where the count is initialized.
2025-09-02 15:06:44 +03:00
kijai
42d7180759
keep scale_weight on gpu to avoid needless casts
2025-09-02 01:04:16 +03:00
kijai
82608009c8
use a copy of the scheduler if provided by the scheduler node to make sure it's always reset
2025-09-01 23:04:05 +03:00
kijai
f9755820de
handle negative latent indices with extra latents
2025-09-01 14:19:51 +03:00
kijai
56e3366c26
Fix pusa steps
2025-09-01 13:50:41 +03:00
kijai
43d8a2c8a5
flowmatch_pusa split sampling fixes
2025-09-01 13:34:49 +03:00
kijai
d4d942c5ee
Update nodes.py
2025-09-01 11:17:22 +03:00
kijai
30c2fca799
WanVideoScheduler fixes
...
support flowmatch pusa when using the node
2025-09-01 11:07:41 +03:00
kijai
d9038d575f
Allow setting both start and end step by sigma
2025-08-31 19:04:01 +03:00
kijai
b8acd3ee48
Allow using fp16 multitalk model with GGUF again
2025-08-31 18:57:59 +03:00
kijai
9f84cd2254
Fix offloading when using stand-in lora
2025-08-31 18:45:13 +03:00
kijai
b9b46638ac
Fix FantasyPortrait + GGUF main model
2025-08-31 18:41:08 +03:00
kijai
b1c8b8a280
remove flex attention as redundant
2025-08-31 18:14:38 +03:00
kijai
79395b872c
Update pyproject.toml
2025-08-31 18:10:07 +03:00
kijai
cedac626e2
Update __init__.py
2025-08-31 18:09:24 +03:00
kijai
4870b8f081
Update __init__.py
2025-08-31 18:06:20 +03:00
kijai
81dac31735
Merge branch 's2v'
2025-08-31 18:05:30 +03:00
kijai
26a11c3044
Update nodes.py
2025-08-31 18:01:53 +03:00
kijai
10d3a0fbef
Update model.py
2025-08-30 23:34:14 +03:00
kijai
40308f1c70
Allow basic FantasyPortrait + S2V
2025-08-30 22:33:32 +03:00
kijai
df0b8c419a
Fix
2025-08-30 18:01:05 +03:00
kijai
45f129b287
Revert this for now to avoid issues on some systems
...
Prefetching still works, but using cuda stream caused issue on some systems, investigate reasons later
2025-08-30 14:09:16 +03:00
kijai
a7cf6d4ed1
Update nodes.py
2025-08-29 21:33:12 +03:00
kijai
7dd0e1ac61
Update nodes_model_loading.py
2025-08-29 21:21:24 +03:00
kijai
f36fa45c29
Loading fixes when using merged loras
2025-08-29 20:57:28 +03:00
kijai
3a290cfd15
Update nodes_model_loading.py
2025-08-29 20:41:40 +03:00
kijai
8f6507fa64
Update nodes.py
2025-08-29 18:10:18 +03:00
kijai
1e4cc84a30
Fix previous
2025-08-29 17:35:27 +03:00
kijai
88cf36936b
skip this if not on cuda
2025-08-29 17:29:25 +03:00
kijai
876b5bda5c
Update nodes.py
2025-08-29 17:17:37 +03:00
kijai
5f7a5d533b
Reduce memory use in the Framepack loop
2025-08-29 16:59:23 +03:00
kijai
6a2053c9d1
Update nodes_model_loading.py
2025-08-29 15:26:47 +03:00
kijai
0c8a883a36
Update nodes.py
2025-08-29 15:25:31 +03:00
kijai
044ff9f25e
don't use model management for cuda stream...
2025-08-29 15:21:49 +03:00
kijai
6978686272
Update model.py
2025-08-29 15:16:02 +03:00
kijai
740157bd61
Fix MultiTalk when using the Multi/InfiniteTalk node
...
InfiniteTalk was also mistakenly using only first frame mask... but honestly after trying the reference method, the result was worse, so I'll default to single frame mask in all cases for now.
2025-08-29 14:48:12 +03:00
kijai
704cca215b
Fix control lora when not last lora to be loaded
2025-08-29 14:45:03 +03:00
kijai
999a314652
Fix GGUF offloading
2025-08-29 12:58:36 +03:00
kijai
f9be754980
cleanup
2025-08-29 00:17:05 +03:00
kijai
a21e4b3210
Update model.py
2025-08-28 20:54:36 +03:00
kijai
469d9168da
Update wanvideo2_2_S2V_framepack_pose_testing.json
2025-08-28 19:31:47 +03:00
kijai
a053336c1a
Update nodes.py
2025-08-28 18:52:10 +03:00
kijai
6faa24b7f2
Implement Framepack long geneneration method
...
RoPE handling is comfyanon's code
2025-08-28 18:48:39 +03:00
kijai
a5621b8739
Add pose input
2025-08-27 22:43:28 +03:00
kijai
5266959a93
Create wanvideo2_2_S2V_context_window_testing.json
2025-08-27 21:41:34 +03:00
kijai
a37b12235f
Add loudness norm node
2025-08-27 20:51:08 +03:00
kijai
90c3bbb6c2
better context window indices, cleanup
2025-08-27 18:47:31 +03:00
kijai
4bc1ffee24
Update wanvideo_Fun_2_2_control_example_03.json
2025-08-27 16:12:31 +03:00
kijai
56bd2ec5f6
Update WanVideoScheduler -node
2025-08-27 13:19:07 +03:00
kijai
a507a5763d
update WanVideoScheduler -node
2025-08-27 13:03:24 +03:00
kijai
c89b82e479
Merge branch 'main' into s2v
2025-08-27 12:24:08 +03:00
kijai
e241998f53
Fix Uni3C
2025-08-27 12:21:25 +03:00
kijai
0538f5d600
Update nodes.py
2025-08-27 02:41:24 +03:00
kijai
a84d142cb2
Update nodes.py
2025-08-27 02:40:27 +03:00
kijai
5d17484cc5
continue
2025-08-27 02:25:39 +03:00
kijai
636b252c7e
Merge branch 'main' into s2v
2025-08-26 22:41:37 +03:00
kijai
2a3ca69c83
Fix offloading when using merged loras
2025-08-26 22:34:12 +03:00
kijai
e85e1ff9e6
Update model.py
2025-08-26 22:05:22 +03:00
kijai
8e65fae3c5
Update model.py
2025-08-26 22:02:36 +03:00
kijai
96f7f6accd
fix normal model loading
2025-08-26 22:02:02 +03:00
kijai
3c79851230
ref latent
2025-08-26 21:30:10 +03:00
kijai
63d4b6aada
Update nodes.py
2025-08-26 19:07:38 +03:00
kijai
748ec89aa8
init
2025-08-26 19:02:24 +03:00
kijai
a1ca0985ec
Merge branch 'dev'
2025-08-26 16:39:26 +03:00
kijai
30f185a19b
Update pyproject.toml
2025-08-26 16:39:17 +03:00
kijai
4f13aa46d4
Update nodes.py
2025-08-26 01:12:22 +03:00
kijai
dfb2a59211
Update nodes.py
2025-08-26 01:11:20 +03:00
kijai
5f5f8ae30a
Merge branch 'main' into dev
2025-08-26 00:33:49 +03:00
kijai
82d2ab44e5
update workflows
2025-08-26 00:27:08 +03:00
kijai
efcef40b00
fix name
2025-08-26 00:18:05 +03:00
kijai