Wan 2.1 Ultra Advanced Gradio APP for - Works as low as 4GB VRAM - 1-Click Installers for Windows, RunPod, Massed Compute - Batch Processing - T2V - I2V - V2V
Added 2025-02-26 00:59:29 +0000 UTCInstaller and APP : https://www.patreon.com/posts/123105403
Full step by step tutorial published : https://youtu.be/hnAhveNy-8s
Download from here : https://www.patreon.com/posts/123105403
I have been working 14 hours today to make this APP before sleeping for you guys :)
We have all the features of Wan 2.1 model
Text to Video 1.3B (as low as 3.5 GB VRAM) - Really fast - 480x832px or 832x480px
Video to Video 1.3B (as low as 3.5 GB VRAM) - Really fast - 480x832px or 832x480px
Text to Video 14B (as low as 17 GB VRAM) - still may work at below VRAM but slower - 720x1280px or 1280x720px
Image to Video 14B (as low as 17 GB VRAM) - still may work at below VRAM but slower - 720x1280px or 1280x720px
When you analyze the above and below images
First video is animated from the input image with following prompt
A hooded wraith stands motionless in a torrential downpour, lightning cracking across the stormy sky behind it. Its face is an impenetrable void of darkness beneath the tattered hood. Rain cascades down its ragged, flowing cloak, which appears to disintegrate into wisps of shadow at the edges. The mysterious figure holds an enormous sword of pure energy, crackling with electric blue lightning that pulses and flows through the blade like liquid electricity. The weapon drags slightly on the wet ground, sending ripples of power across the puddles forming at the figure's feet. Three glowing blue gems embedded in its chest pulse in rhythm with the storm's lightning strikes, each flash illuminating the decaying, ancient fabric of its attire. The rain intensifies around the figure, droplets seemingly slowing as they near the dark entity, while forks of lightning repeatedly illuminate its imposing silhouette. The atmosphere grows heavier with each passing moment as the wraith slowly raises its crackling blade, the blue energy intensifying and casting eerie shadows across the ruined landscape.
The cat video is purely 1.3B model generation via below prompt
A cute cat walking gracefully on a lush green grass field, its tail swaying gently as it moves. Close-up, moving camera following the cat's steps.
Comments
hi should still work and generate results. looks like gradio related error
Furkan Gözükara
2025-03-01 22:22:45 +0000 UTCHi. Sometimes after a generation it gives me this error: ERROR:asyncio:Exception in callback _ProactorBasePipeTransport._call_connection_lost(None) handle: Traceback (most recent call last): File "C:\python310\lib\asyncio\events.py", line 80, in _run self._context.run(self._callback, *self._args) File "C:\python310\lib\asyncio\proactor_events.py", line 162, in _call_connection_lost self._sock.shutdown(socket.SHUT_RDWR) ConnectionResetError: [WinError 10054] Connessione in corso interrotta forzatamente dall'host remoto ERROR:asyncio:Exception in callback _ProactorBasePipeTransport._call_connection_lost(None) handle: Traceback (most recent call last): File "C:\python310\lib\asyncio\events.py", line 80, in _run self._context.run(self._callback, *self._args) File "C:\python310\lib\asyncio\proactor_events.py", line 162, in _call_connection_lost self._sock.shutdown(socket.SHUT_RDWR) ConnectionResetError: [WinError 10054] Connessione in corso interrotta forzatamente dall'host remoto
michele carlone
2025-03-01 19:24:03 +0000 UTCyes i am really getting burned out haha :D
Furkan Gözükara
2025-02-27 22:35:36 +0000 UTCAs much as I appreciate your work ethic. Please don't overdo it. Would hate to see you get burned out. :)
Adam Lucas
2025-02-27 19:02:13 +0000 UTCthe support for 5090 arrived :D
Furkan Gözükara
2025-02-27 10:30:51 +0000 UTCOkay thanks. I thought that since it was updating other things (like step count) it might have been able to but if not that's okay. It's just that the full res 14B one was saying was going to take hours to complete just a few seconds clip on my 3090 (maybe for about a 10 sec clip though I'm not sure). Which is much longer than Cosmos at about the same resolution. Though he 1.3 B one is a lot faster but lower res.
cool1
2025-02-27 00:18:20 +0000 UTConly works for multi image generation. sadly we cant cancel running process
Furkan Gözükara
2025-02-27 00:12:16 +0000 UTCOn the "text to video" option pressing the cancel button doesn't seem to have an effect other than showing "cancel button pressed", it continues increasing the percentage and and step count after it shows "cancel button pressed."
cool1
2025-02-26 22:52:10 +0000 UTCi am trying to compile flash attention right now for 5000 series gpus
Furkan Gözükara
2025-02-26 15:01:05 +0000 UTCyes that was the culprit :D since i have rtx 5090 and 3090 ti i had to cancel 5090 atm due to missing torch libraries
Furkan Gözükara
2025-02-26 09:58:18 +0000 UTCthank you so much
Furkan Gözükara
2025-02-26 09:57:45 +0000 UTCbest of all but not fast true :D
Furkan Gözükara
2025-02-26 09:57:39 +0000 UTCthanks a lot
Furkan Gözükara
2025-02-26 09:57:33 +0000 UTCAmazing job 👏🏼
AiInfluence
2025-02-26 07:20:46 +0000 UTCThis model is good. Certainly not fast though.
EnjoyerOfAll
2025-02-26 06:47:09 +0000 UTCset REM at this line like this: REM SET CUDA_VISIBLE_DEVICES=0 - this is used to set certain CUDA device visible only used
hacbachvotinh
2025-02-26 06:05:32 +0000 UTCGreat job, you are a hero to the community.
hacbachvotinh
2025-02-26 06:03:34 +0000 UTCNot arrived yet missing torch vision cu128 for windows
Furkan Gözükara
2025-02-26 02:00:20 +0000 UTCSadly we cant yet waiting torch vision after that hopefully I will update
Furkan Gözükara
2025-02-26 02:00:01 +0000 UTCDownload v2 zip and use start bat file fixed
Furkan Gözükara
2025-02-26 01:58:36 +0000 UTCYou are welcome thanks for comment
Furkan Gözükara
2025-02-26 01:58:15 +0000 UTCAlso curious if this is 5090 ready. Does this require the hotly awaited Torch update?
LO!
2025-02-26 01:54:53 +0000 UTCHow well does this work on the RTX 5090? Is there a higher resolution model that takes advantage of the 32gb of vram?
Dinh Vu
2025-02-26 01:16:55 +0000 UTCTraceback (most recent call last): File "C:\Users\xxxx\Deep\WAN\Wan2.1\App.py", line 13, in import wan File "C:\Users\xxxx\Deep\WAN\Wan2.1\wan\__init__.py", line 1, in from . import configs, distributed, modules File "C:\Users\xxxx\Deep\WAN\Wan2.1\wan\modules\__init__.py", line 3, in from .t5 import T5Decoder, T5Encoder, T5EncoderModel, T5Model File "C:\Users\xxxx\Deep\WAN\Wan2.1\wan\modules\t5.py", line 472, in class T5EncoderModel: File "C:\Users\xxxx\Deep\WAN\Wan2.1\wan\modules\t5.py", line 478, in T5EncoderModel device=torch.cuda.current_device(), File "C:\Users\xxxx\Deep\WAN\Wan2.1\venv\lib\site-packages\torch\cuda\__init__.py", line 940, in current_device _lazy_init() File "C:\Users\xxxx\Deep\WAN\Wan2.1\venv\lib\site-packages\torch\cuda\__init__.py", line 319, in _lazy_init torch._C._cuda_init() RuntimeError: No CUDA GPUs are available My Cuda is installed and found. Torch installed properly... Not sure why the error.
BecauseReasons
2025-02-26 01:11:46 +0000 UTCThanks mate, your a legend!
Arcadius
2025-02-26 01:02:20 +0000 UTC
