 kijai
|
7c81d7ce10
|
Better support for the official FirstLastFrame2Video -model (FLF2V)
https://huggingface.co/Kijai/WanVideo_comfy/blob/main/Wan2_1-FLF2V-14B-720P_fp16.safetensors
https://huggingface.co/Kijai/WanVideo_comfy/blob/main/Wan2_1-FLF2V-14B-720P_fp8_e4m3fn.safetensors
|
2025-04-16 19:40:04 +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 |
|
|
kijai
|
ea71dfda1a
|
restructure, add visualization node
|
2025-04-11 18:40:50 +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
|
6f2f2db9a5
|
Force some image inputs to be divisible by 16
|
2025-04-09 16:49:16 +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 |
|
|
kijai
|
96633b5101
|
Remove fp16 from the wrapper T5 loader as it ruins results.
|
2025-04-07 22:47:59 +03:00 |
|
|
kijai
|
7d23826136
|
tiled encoding fixes and add as option for VACE endore
|
2025-04-07 20:21:36 +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
|
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
|
e4912d03de
|
non_blocking teacache offload
|
2025-04-03 20:06:15 +03:00 |
|
|
kijai
|
20314371f9
|
Include optional control signal to VACE start/end node
|
2025-04-03 19:04:30 +03:00 |
|
|
kijai
|
fb6e3114b5
|
Add WanVideoVACEStartToEndFrame -helper node, fix VACE start step
Pretty big bug I had there with VACE, it was never applied on first step.. oops!
|
2025-04-03 18:22:59 +03:00 |
|
|
kijai
|
ce8d908ed6
|
Fix context windows without VACE
|
2025-04-03 17:16:48 +03:00 |
|
|
kijai
|
1aa6498bbe
|
Compile VACE blocks as well
|
2025-04-03 17:05:39 +03:00 |
|
|
kijai
|
f820f38c8f
|
Allow offloading and block swapping VACE blocks as well
|
2025-04-02 17:27:17 +03:00 |
|
|
kijai
|
11b2c316d2
|
Update nodes.py
|
2025-04-02 15:29:32 +03:00 |
|
|
kijai
|
8db001b586
|
VACE ref image input fixes
|
2025-04-02 15:24:25 +03:00 |
|
|
kijai
|
1d2b2057f5
|
Update nodes.py
|
2025-04-02 14:46:00 +03:00 |
|
|
kijai
|
53a050af42
|
Context windows with VACE
|
2025-04-02 14:15:39 +03:00 |
|
|
kijai
|
ce6522c227
|
Add start/end percent controls for VACE
|
2025-04-02 11:10:12 +03:00 |
|
|
kijai
|
1cdce191ed
|
Update nodes.py
|
2025-04-02 02:47:09 +03:00 |
|
|
kijai
|
79474aa63d
|
Update nodes.py
|
2025-04-02 02:00:41 +03:00 |
|
|
kijai
|
d9979f0acd
|
fix block swap for VACE
|
2025-04-02 01:28:22 +03:00 |
|
|
kijai
|
f090f9edec
|
Update nodes.py
|
2025-04-02 01:02:25 +03:00 |
|
|
kijai
|
3322d868ab
|
vace ref image fixes
|
2025-04-02 00:44:47 +03:00 |
|
|
kijai
|
80bcac3803
|
Update nodes.py
|
2025-04-02 00:30:56 +03:00 |
|
|
kijai
|
90b79e44d3
|
Re-factor VACE input
|
2025-04-02 00:20:07 +03:00 |
|
|
kijai
|
2d2a184723
|
Update nodes.py
|
2025-04-01 22:19:48 +03:00 |
|
|
kijai
|
96b236c4df
|
Basic VACE (preview version) support
no ref image or masking yet, but control signal seems to work
|
2025-04-01 22:05:33 +03:00 |
|
|
kijai
|
3869b0482b
|
cleanup
|
2025-04-01 19:13:53 +03:00 |
|
|
kijai
|
eca5e7520d
|
Update nodes.py
|
2025-04-01 13:56:29 +03:00 |
|
|
kijai
|
ceb4bb50cf
|
Update nodes.py
|
2025-04-01 13:51:41 +03:00 |
|
|
kijai
|
23c9a6d634
|
Add dynamo_recompile_limit as adjustable option, revert to old euler for flowedit
|
2025-04-01 11:44:45 +03:00 |
|
|
kijai
|
40f1ea730c
|
autoscale temporal mask better
|
2025-03-31 22:27:50 +03:00 |
|
|
Jukka Seppänen
|
9100eecccf
|
Merge pull request #354 from xStrom/clipvision
Load clip vision models from the `clip_vision` folder.
|
2025-03-31 12:15:58 +03:00 |
|
|
Sam Green
|
81c640d758
|
Fix typo
|
2025-03-31 02:13:39 +01:00 |
|