Commit Graph
100 Commits
Author SHA1 Message Date
kijai 32e5c4d200 update examples 2025-07-04 17:19:51 +03:00
kijai 3d7801cee4 Update nodes.py 2025-07-04 16:57:20 +03:00
kijai ca3c58bb1a Merge branch 'main' into multitalk 2025-07-04 16:43:53 +03:00
kijai 811dd32713 Update wanvideo_ATI_testing_01.json 2025-07-04 16:43:19 +03:00
kijai 74c6d25486 update WanVideoVACEStartToEndFrame 2025-07-04 16:43:13 +03:00
kijai 974dd656da some offloading for multitalk 2025-07-03 21:56:19 +03:00
kijai 4e6a85a148 Merge branch 'main' into multitalk 2025-07-03 21:56:06 +03:00
kijai 70e3c6b524 update 2025-07-03 21:41:44 +03:00
kijai eb6de2e8d0 Update nodes.py 2025-07-03 19:18:28 +03:00
kijaiandRudra-ai-coder 475f371016 Multiple talkers
Initial commit, works but needs more utility for the mask creation.

Based mostly on Rudra-ai-coder's modifications.

Co-Authored-By: Rudra-ai-coder <177262225+rudra-ai-coder@users.noreply.github.com>
2025-07-03 19:03:12 +03:00
kijai 06b932792f Update nodes.py 2025-07-02 17:30:35 +03:00
kijai 74a441ef93 Update nodes.py 2025-07-02 17:24:57 +03:00
kijai de279dd060 update 2025-07-02 17:15:18 +03:00
kijai ebe3068a8d progress bar 2025-07-02 16:59:45 +03:00
kijai 8e9fb0e11c Update nodes.py 2025-07-02 16:47:19 +03:00
kijai d687833c15 Create wanvideo_multitalk_test_02.json 2025-07-02 16:47:15 +03:00
kijai 0a11c67a0c MultiTalk sampling
New node (WanVideoImageToVideoMultiTalk) that also enables the continuous sampling method from the original code. Compared to context windows this works better for shorter clips, but degrades longer it goes.
2025-07-02 16:18:04 +03:00
kijai 49430f900b Fix for transformers 4.53.0 2025-07-01 12:00:28 +03:00
kijai f621d2a5fc Update model.py 2025-06-30 20:31:39 +03:00
kijai 8479624614 fix split prompting 2025-06-20 17:31:01 +03:00
kijai 2da36b7fda context window progress bar
better than nothing, and allow cancelling mid context
2025-06-20 17:29:27 +03:00
kijai b605308687 Update nodes.py 2025-06-20 16:33:55 +03:00
kijai 547bd4e45a Update nodes.py 2025-06-20 16:18:07 +03:00
kijai 4334ed58b4 Update nodes.py 2025-06-20 15:26:13 +03:00
kijai c44eca13a9 Update nodes.py 2025-06-20 15:22:25 +03:00
kijai c3ab39b068 Update requirements.txt 2025-06-20 15:18:13 +03:00
kijai 157fbb1b7f Merge branch 'main' into multitalk 2025-06-20 13:53:31 +03:00
kijai 2b96d9cef2 WanVideoLoraSelectMulti 2025-06-20 13:53:13 +03:00
kijai 8387a64b15 bump version 2025-06-20 10:57:13 +03:00
kijai 38c98a6476 Create wanvideo_multitalk_test_01.json 2025-06-20 01:08:16 +03:00
kijai 263333a0d1 tiny vae adjustment 2025-06-19 20:38:23 +03:00
kijai 09b4c3a865 support context windows, torch compile fixes 2025-06-19 20:29:32 +03:00
kijai f3614e6720 Update nodes.py 2025-06-19 00:56:36 +03:00
kijai 96e8914b33 Fix audio cfg 2025-06-18 21:19:24 +03:00
kijai 1fe72d27aa loudness norm 2025-06-18 18:35:06 +03:00
kijai b5cae8bf1a Fix FLF2V model 2025-06-18 15:49:01 +03:00
kijai 58104b620f init 2025-06-18 15:41:53 +03:00
Jukka Seppänen 058286fc0f Merge pull request #657 from ObiLeek/main
refactor(decode): Replace min-max scaling with standard [-1, 1] conversion
2025-06-17 15:14:03 +03:00
kijai dd1f3c3ecb fix 2025-06-17 12:14:56 +03:00
kijai b322192d93 Support minimaxremover
https://minimax-remover.github.io/
2025-06-17 09:45:12 +03:00
kijai c3ee35f3ec Update basic_flowmatch.py 2025-06-13 13:06:12 +03:00
kijai ad43eed0d0 Add MagCache and consolidate cache_args to support both
Not really getting great results yet with MagCache, but at least pretty much on bar with TeaCache so it can be an option that hopefully improves in time
2025-06-13 12:31:13 +03:00
kijai e7c39757f6 Allow compiling crossattn
I don't remember why I even disabled this... seems to work, big effect with NAG
2025-06-12 19:04:15 +03:00
kijai f6df3d75ef Merge branch 'pr/643' 2025-06-12 18:32:20 +03:00
kijai 34fecc3063 Update nodes.py 2025-06-12 18:19:52 +03:00
kijai d34cabc985 Cleanup, create own node for NAG 2025-06-12 18:18:28 +03:00
kijai 23796233df Some fixes and adjustments 2025-06-12 17:26:54 +03:00
kijai bac29263da Update nodes.py 2025-06-12 16:39:36 +03:00
kijai ced1ddaa1a Update basic_flowmatch.py 2025-06-12 16:29:53 +03:00
kijai 5917f51837 Small adjustments and options to dwpose detection 2025-06-12 16:29:31 +03:00
kijai 6eddec54a6 fix 2025-06-09 23:18:01 +03:00
kijai 9b380ec3c0 Allow loading state dicts from .pt sub dicts 2025-06-09 22:33:07 +03:00
kijai 39412cf422 Node to use ATI on native workflows 2025-06-09 04:24:37 +03:00
kijai 820ac3008e Update nodes.py 2025-06-07 21:48:50 +03:00
kijai d3a09a1a6b bump version 2025-06-07 11:57:38 +03:00
kijai 87a980f6bf This can still be append 2025-06-06 12:10:42 +03:00
kijai a290f75b5e Update model.py 2025-06-05 23:41:17 +03:00
kijai 9c27705dac Update nodes.py 2025-06-05 23:04:40 +03:00
kijai efb87445d5 Update nodes.py 2025-06-05 19:28:56 +03:00
kijai 6139017535 Update wanvideo_ATI_testing_01.json 2025-06-05 18:44:37 +03:00
kijai 45dca5c41c Fix ATI start/end percent controls 2025-06-04 10:02:20 +03:00
kijai bdd3828596 Update nodes.py 2025-06-03 20:47:27 +03:00
kijai 821881429b Update nodes.py 2025-06-03 10:03:58 +03:00
kijai bd6c853051 Better track parsing 2025-06-03 08:11:40 +03:00
kijai f4a1157f71 Fix typo 2025-06-03 08:04:08 +03:00
kijai e2f42b5773 realisdance 2025-06-03 08:02:59 +03:00
kijai 9e8978731b Update wanvideo_ATI_testing_01.json 2025-05-31 20:46:44 +03:00
kijai 7d63a771d8 Better ATI visualization 2025-05-31 20:44:33 +03:00
kijai da3c7def22 Update wanvideo_ATI_testing_01.json 2025-05-31 19:42:05 +03:00
kijai abf61ad833 More efficient and compatible tensor reshape for ATI motion_patch 2025-05-31 19:30:06 +03:00
kijai 774b055452 Create wanvideo_ATI_testing_01.json 2025-05-31 02:07:59 +03:00
kijai 8bc74daad9 cleanup 2025-05-31 01:58:21 +03:00
kijai cd2884d88a Initial ATI support
https://github.com/bytedance/ATI
2025-05-31 01:17:18 +03:00
kijai c4a8f6d835 Clearer error when trying to use uni3c controlnet with incompatible model 2025-05-30 18:11:36 +03:00
kijai 5c676d3a49 Allow further filtering of LoRA layers to apply 2025-05-30 16:24:44 +03:00
kijai ef40577b70 fixes 2025-05-30 12:29:38 +03:00
kijai fb73022a06 controlnet device fix 2025-05-29 18:42:46 +03:00
kijai 0323a9d2c7 Fix TAEW decoding 2025-05-29 18:37:13 +03:00
kijai 129f368380 Fix uni3c on fp16 and add strength parameters 2025-05-29 13:25:52 +03:00
kijai 87ae18e203 Error on trying to use VACE with I2V models. 2025-05-29 00:14:35 +03:00
kijai 07c7fc6c2a Don't show Phantom references in live preview 2025-05-27 19:14:22 +03:00
kijai 81e7022ab5 Force steps to match possible cfg schedule length 2025-05-27 18:06:36 +03:00
kijai 934dc127a8 Update wanvideo_phantom_subject2vid_example_01.json 2025-05-27 17:32:05 +03:00
kijai ea01ae9ed9 Allow scheduling phantom cfg too 2025-05-27 15:27:38 +03:00
kijai 0f7de6bac2 Fix 14B controlnet loading 2025-05-26 23:42:26 +03:00
kijai 23e3368de3 Initial Dilated Controlnet support
https://huggingface.co/TheDenk/wan2.1-t2v-1.3b-controlnet-hed-v1
https://huggingface.co/TheDenk/wan2.1-t2v-14b-controlnet-hed-v1
2025-05-26 21:54:48 +03:00
kijai ece2917a41 Fix compile 2025-05-26 15:49:03 +03:00
kijai ef1ed29178 partial Uni3C implementation 2025-05-26 12:35:36 +03:00
Jukka Seppänen d9ca90c1f0 Merge pull request #545 from anastasiuspernat/main
Fix chained VACE embeddings ignored with WanVideo Context Options
2025-05-26 00:46:53 +03:00
kijai fe7a3d5b46 Forgot to remove these 2025-05-23 18:44:59 +03:00
kijai 370837233a Fix more VACEs than 2....
silly mistake, more than 2 never worked
2025-05-21 19:15:30 +03:00
kijai 7875031efe Support list input for VACE strength
Allows finer control of VACE strength over timesteps
2025-05-21 19:04:25 +03:00
kijai fa7015315a Possibly reduce TeaCache VRAM use a bit
Uses 500-700MB less at 1280x720
2025-05-20 21:07:15 +03:00
kijai d547482ad6 Update nodes.py 2025-05-18 21:09:36 +03:00
kijai fd562e9730 Update nodes.py 2025-05-16 13:17:11 +03:00
kijai 7bba1e8e17 typo 2025-05-16 11:03:26 +03:00
kijai 1c3060f59f remove torchao quants, fix long unianimate crash 2025-05-15 20:25:43 +03:00
kijai 4494bda603 bump version 2025-05-15 12:47:23 +03:00
kijai ec9f310486 update VACE example 2025-05-15 11:09:32 +03:00
kijai 6aec1d97a8 better error for VACE module loading 2025-05-14 18:23:37 +03:00