AI/ComfyUI-WanVideoWrapper
1
0
Fork 0
mirror of https://github.com/kijai/ComfyUI-WanVideoWrapper.git synced 2026-01-28 12:20:55 +03:00
Code Activity
320 Commits 8 Branches 0 Tags
syncammaster
Commit Graph

320 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
kijai
2e7c00a03b initial syncammaster 2025-04-17 01:21:47 +03:00
kijai
f919c4fd3d Allow using custom sigmas, fix some cases with multiple VACE embeds 2025-04-13 16:35:40 +03:00
kijai
941acc434d Add some schedulers 2025-04-12 17:18:53 +03:00
Jukka Seppänen
fdc7176efd Update readme.md 2025-04-11 19:20:02 +03:00
Jukka Seppänen
892a6f21e6 Merge pull request #364 from green-s/swarm-previews 
Add SwarmUI preview support
 2025-04-11 19:17:57 +03:00
Jukka Seppänen
4c9b5be250 Merge pull request #397 from ComfyNodePRs/update-publish-yaml 
Update Github Action for Publishing to Comfy Registry
 2025-04-11 19:17:32 +03:00
kijai
b425970700 Update pyproject.toml 2025-04-11 19:17:05 +03:00
kijai
a9ddb65dd3 Create wanvideo_1_3B_ReCamMaster_example_01.json 2025-04-11 19:16:40 +03:00
kijai
ea71dfda1a restructure, add visualization node 2025-04-11 18:40:50 +03:00
kijai
2dc25c150e allow other dimensions 2025-04-11 00:56:54 +03:00
kijai
94f59f09c8 map camera types 2025-04-10 23:27:36 +03:00
kijai
740fdd749a initial recammaster support 2025-04-10 23:04:32 +03:00
kijai
11e9166d0b Fix low vram lora load 2025-04-10 18:04:17 +03:00
kijai
280f9952e5 Fix fp32 with some versions of sageattn 2025-04-10 12:10:44 +03:00
kijai
6f2f2db9a5 Force some image inputs to be divisible by 16 2025-04-09 16:49:16 +03:00
kijai
8570c7dbe8 Temporary fix for vram_management 2025-04-09 10:04:29 +03:00
kijai
179f85bf3d less unnecessary recompiles 2025-04-09 01:11:30 +03:00
kijai
f3f12aa6cf Fix batched_cfg and some possible dtype tweaks to avoid recompiles 2025-04-08 20:08:33 +03:00
kijai
7de8ac25a6 Some VACE tweaks 2025-04-08 18:27:06 +03:00
Sam Green
d019407a04 Add SwarmUI preview support. 2025-04-08 05:51:36 +01:00
kijai
a39e4e2d0a Update wanvideo_Fun_control_example_01.json 2025-04-07 23:05:04 +03:00
kijai
96633b5101 Remove fp16 from the wrapper T5 loader as it ruins results. 2025-04-07 22:47:59 +03:00
kijai
21b895a414 Add outpaint example to VACE example 2025-04-07 22:26:04 +03:00
kijai
7d23826136 tiled encoding fixes and add as option for VACE endore 2025-04-07 20:21:36 +03:00
kijai
c4dce1cdba bump version 2025-04-07 13:50:16 +03:00
kijai
f8155ab47f Allow loading Fun Reward LoRAs 
https://huggingface.co/alibaba-pai/Wan2.1-Fun-Reward-LoRAs/tree/main
 2025-04-07 12:38:56 +03:00
kijai
dce705f5d7 Further reduce VRAM use of VACE when block swapping enabled 2025-04-06 21:55:52 +03:00
kijai
a05d3ac8ac Considerably reduce VACE memory use 
I don't understand why the initial code did it like it did, keeping the VACE results as a list uses way less memory and so far haven't faced any issues and results remain identical.
 2025-04-06 17:18:13 +03:00
kijai
1d91e497aa bit better VACE offloading 2025-04-06 12:13:36 +03:00
kijai
131dad0fc7 Update wanvideo_1_3B_VACE_examples_01.json 2025-04-06 11:36:37 +03:00
kijai
d743cfda4d Update wanvideo_skyreels_a2_example_01.json 2025-04-05 20:51:29 +03:00
kijai
15366bc9d5 update skyreels a2 example 2025-04-05 20:32:20 +03:00
kijai
7f72cd012a Update wanvideo_skyreels_a2_example_01.json 2025-04-05 19:38:41 +03:00
kijai
fd7e778997 Add Skyreels A2 example 
Not really sure if everything is correct, up for testing
 2025-04-05 19:34:17 +03:00
kijai
34ee8efb9a Allow more than 2 clip embeds 2025-04-05 18:56:28 +03:00
kijai
56a4221a38 Add extra latent to front instead (as it probably should) 2025-04-05 16:18:37 +03:00
kijai
36249e1a97 Basic Skyreels A2 support 
converted model here:

https://huggingface.co/Kijai/WanVideo_comfy/blob/main/Wan2_1_SkyreelsA2_fp8_e4m3fn.safetensors

Encode the reference and input to the ImageToVideoEncode -node, take into account the extra latent when choosing frame count (should be -4 to normal), otherwise the standard I2V workflow.
 2025-04-05 15:53:56 +03:00
kijai
ae40c3c131 Update nodes.py 2025-04-05 15:18:36 +03:00
kijai
d6a6629c08 Update nodes.py 2025-04-04 18:06:33 +03:00
kijai
2ed2c5cbc1 Fix non-vace (again) 2025-04-04 17:50:52 +03:00
kijai
04534e5eed Allow using multiple VACE embeds, fix VACE blockswap error when vace blocks not set and blockswap is set 
Experimental
 2025-04-04 15:23:39 +03:00
kijai
78559ef1f4 Update nodes.py 2025-04-04 03:06:23 +03:00
kijai
45e39e758d Allow selecting VACE blocks 2025-04-04 02:26:24 +03:00
kijai
237c79fe0c Allow loading VACE separately 
The base 1.3B model was not trained at all, we can load only the VACE blocks/patch embed separate too:

https://huggingface.co/Kijai/WanVideo_comfy/blob/main/Wan2_1_VACE_1_3B_preview_bf16.safetensors
 2025-04-04 02:14:43 +03:00
kijai
4cff47c7e0 error if user tries to use scaled fp8 text encoder on the wrapper node 2025-04-03 22:56:07 +03:00
kijai
8ef37ee049 Update wanvideo_1_3B_VACE_examples_01.json 2025-04-03 22:41:23 +03:00
kijai
734864c61e bump version 2025-04-03 22:38:52 +03:00
kijai
e4912d03de non_blocking teacache offload 2025-04-03 20:06:15 +03:00
kijai
d261c0597f Create wanvideo_1_3B_VACE_examples_01.json 2025-04-03 19:42:29 +03:00
kijai
20314371f9 Include optional control signal to VACE start/end node 2025-04-03 19:04:30 +03:00