should the wan2.1 take 40 minutes to generate a 5 second clip on a 3090? using the default settings

ZZono50 should the wan2.1 take 40 minutes to generate a 5 second clip on a 3090? using t...

F

Furkan Gözükara SECourses•3/11/25, 6:32 PM

yes

F

Furkan Gözükara SECourses•3/11/25, 6:32 PM

still we are lacking teacache

F

Furkan Gözükara SECourses•3/11/25, 6:32 PM

hopefully it will half the duration

A

art-ai_usa-girl•3/12/25, 10:09 PM

https://huggingface.co/spaces/Skywork/skyreels-a1-talking-head

Skyreels A1 Talking Head - a Hugging Face Space by Skywork

Aart-ai_usa-girl https://huggingface.co/spaces/Skywork/skyreels-a1-talking-head

F

Furkan Gözükara SECourses•3/12/25, 10:15 PM

lets try

F

Furkan Gözükara SECourses•3/12/25, 10:20 PM

looks even weaker than v express

F

Furkan Gözükara SECourses•3/12/25, 10:20 PM

F

Furkan Gözükara SECourses•3/12/25, 10:21 PM

and gave only 4 second output lol

F

Furkan Gözükara SECourses•3/12/25, 10:22 PM

generating v express

FFurkan Gözükara SECourses and gave only 4 second output lol

A

art-ai_usa-girl•3/12/25, 10:43 PM

yeah only 4 second

Aart-ai_usa-girl yeah only 4 second

F

Furkan Gözükara SECourses•3/12/25, 10:49 PM

github has long

F

Furkan Gözükara SECourses•3/12/25, 10:49 PM

i may make installer

FFurkan Gözükara SECourses i may make installer

A

art-ai_usa-girl•3/13/25, 1:10 AM

thank you ,,,, you are the best

W

woni•3/13/25, 8:49 AM

guys does stable diffusion in google collab still working?

A

art-ai_usa-girl•3/13/25, 10:09 PM

has anybody tested this ? https://github.com/NJU-PCALab/STAR

GitHub

GitHub - NJU-PCALab/STAR: STAR: Spatial-Temporal Augmentation with ...

STAR: Spatial-Temporal Augmentation with Text-to-Video Models for Real-World Video Super-Resolution - NJU-PCALab/STAR

Aart-ai_usa-girl has anybody tested this ? https://github.com/NJU-PCALab/STAR

F

Furkan Gözükara SECourses•3/13/25, 10:13 PM

i plan to make app for this

I

Inoshi•3/14/25, 5:22 PM

hi ! there is a text to voice model Sesame ai released https://huggingface.co/sesame are you going to create something around this ?

sesame (Sesame)

IInoshi hi ! there is a text to voice model Sesame ai released https://huggingface.co/se...

F

Furkan Gözükara SECourses•3/14/25, 10:39 PM

yes i plan to but how good it is? i saw today

I

Inoshi•3/14/25, 11:10 PM

i am trying to figure out how to control the voice better, but in terms of cloning it sounds pretty decent. i havent really tried other text to speech models though

F

Furkan Gözükara SECourses•3/15/25, 10:56 AM

@Capybara you can open your thread here. more fitting section

C

Capybara•3/15/25, 10:58 AM

alr

C

Capybara•3/15/25, 10:59 AM

Hello, any tips for making the visual sector of an anti collision system? Ideas for making it more user friendly

CCapybara Hello, any tips for making the visual sector of an anti collision system? Ideas ...

F

Furkan Gözükara SECourses•3/15/25, 11:00 AM

i never made anti collision system but it depends on where you are making it

F

Furkan Gözükara SECourses•3/15/25, 11:00 AM

in a game?

F

Furkan Gözükara SECourses•3/15/25, 11:00 AM

a toy?

Z

Zono50OP•3/15/25, 6:58 PM

@Furkan Gözükara SECourses can you add a way for the loros to automatically implement their trigger words?

ZZono50 <@205854764540362752> can you add a way for the loros to automatically implemen...

F

Furkan Gözükara SECourses•3/15/25, 8:57 PM

yes i will add all loras with trigger words hopefully

C

cyberbol•3/16/25, 9:39 AM

https://trajectorycrafter.github.io/

This can be very helpfull, hopefully they lower vram usage

TrajectoryCrafter

TrajectoryCrafter.

C

cyberbol•3/16/25, 9:40 AM

https://tight-inversion.github.io/
Also this. Dr FUrkan, how to clone huggins ? Its possible clone to windows system ?

Tight Inversion

Tight Inversion: Image-Conditioned Inversion for Real Image Editing

C

cyberbol•3/16/25, 9:41 AM

SANA Sprint... also looks amazing
https://nvlabs.github.io/Sana/Sprint/

Ccyberbol https://trajectorycrafter.github.io/ This can be very helpfull, hopefully they ...

F

Furkan Gözükara SECourses•3/16/25, 12:11 PM

decent

Ccyberbol https://tight-inversion.github.io/ Also this. Dr FUrkan, how to clone huggins ?...

F

Furkan Gözükara SECourses•3/16/25, 12:12 PM

this can run locally

C

cyberbol•3/16/25, 12:12 PM

And SANA SPRINT i think models alre not realised yet

Ccyberbol And SANA SPRINT i think models alre not realised yet

F

Furkan Gözükara SECourses•3/16/25, 12:15 PM

yep not published yet i think

FFurkan Gözükara SECourses this can run locally

D

Dazzastrous [4090]•3/16/25, 5:11 PM

on a 50 series dont think it runbs on 4090 needs 28gb vram

D

Dazzastrous [4090]•3/16/25, 5:11 PM

SANA sprint is super fast 1024 image in a secondo

DDazzastrous [4090]SANA sprint is super fast 1024 image in a secondo

F

Furkan Gözükara SECourses•3/16/25, 6:06 PM

yep

DDazzastrous [4090]on a 50 series dont think it runbs on 4090 needs 28gb vram

F

Furkan Gözükara SECourses•3/16/25, 6:07 PM

5090 makes difference in some cases

F

Furkan Gözükara SECourses•3/16/25, 6:07 PM

like 14b model fitting into vram with fp8

F

Furkan Gözükara SECourses•3/16/25, 6:07 PM

just finished testing :d

F

Furkan Gözükara SECourses•3/16/25, 6:07 PM

GPU VRAM Usages Table With Respected To Number of Persistent Params+

All tests made on secondary GPU thus they are 100% accurate

Therefore, make sure that you have such empty VRAM before starting the Wan 2.1 SECourses App 

1280x720 px, 81 frames, 14b text to video model - BF16 precision (torch.bfloat16)

0 is : 14168 MB - Below 24 GB GPUs
1,000,000,000 is : 15658 MB
2,000,000,000 is : 17664 MB
3,000,000,000 is : 20134 MB
3,750,000,000 is : 21134 MB
4,000,000,000 is : 21500 MB
4,250,000,000 is : 22000 MB - 24 GB GPUs
8,250,000,000 is : 29870 MB - 32 GB GPUs
22,000,000,000 is : 41700 MB - 48 GB GPUs

1280x720 px, 81 frames, 14b text to video model - FP8 precision (torch.float8_e4m3fn)

0 is : 14168 MB - Below 24 GB GPUs
1,000,000,000 is : 14918 MB
8,000,000,000 is : 21260 MB
8,750,000,000 is : 21980 MB - 24 GB GPUs
22,000,000,000 is : 27330 MB - 32 GB GPUs


480x832 px, 81 frames, 14b 480p image to video model - BF16 precision (torch.bfloat16)

0 is : 8618 MB - Below 12 GB GPUs
1,000,000,000 is : 9354 MB
1,500,000,000 is : 10090 MB - 12 GB GPUs
2,000,000,000 is : 11370 MB
3,000,000,000 is : 13080 MB
3,500,000,000 is : 14038 MB - 16 GB GPUs
4,000,000,000 is : 15140 MB
8,000,000,000 is : 22100 MB - 24 GB GPUs
12,000,000,000 is : 30060 MB - 32 GB GPUs
22,000,000,000 is : 38300 MB - 48 GB GPUs


480x832 px, 81 frames, 14b 480p image to video model - FP8 precision (torch.float8_e4m3fn)

0 is : 8618 MB - Below 12 GB GPUs
2,500,000,000 is : 9794 MB - 12 GB GPUs
7,500,000,000 is : 14850 MB - 16 GB GPUs
8,000,000,000 is : 15392 MB
15,000,000,000 is : 21700 MB - 24 GB GPUs
22,000,000,000 is : 23080 MB - 32 GB GPUs


720x1280 px, 81 frames, 14b 720p image to video model - BF16 precision (torch.bfloat16)

0 is : 18326 MB - Below 24 GB GPUs
2,000,000,000 is : 20360 MB
3,000,000,000 is : 22010 MB - 24 GB GPUs
6,000,000,000 is : 28380 MB
6,500,000,000 is : 29330 MB
6,750,000,000 is : 29790 MB - 32 GB GPUs
16,000,000,000 is : 47030 MB - 48 GB GPUs
22,000,000,000 is : 47800 MB - 80 GB GPUs


720x1280 px, 81 frames, 14b 720p image to video model - FP8 precision (torch.float8_e4m3fn)

0 is : 18326 MB - Below 24 GB GPUs
3,000,000,000 is : 19763 MB
6,000,000,000 is : 22020 MB - 24 GB GPUs
14,000,000,000 is : 29840 MB
15,000,000,000 is : 30790 MB - 32 GB GPUs
22,000,000,000 is : 32013 MB - 48 GB GPUs

GPU VRAM Usages Table With Respected To Number of Persistent Params+

All tests made on secondary GPU thus they are 100% accurate

Therefore, make sure that you have such empty VRAM before starting the Wan 2.1 SECourses App 

1280x720 px, 81 frames, 14b text to video model - BF16 precision (torch.bfloat16)

0 is : 14168 MB - Below 24 GB GPUs
1,000,000,000 is : 15658 MB
2,000,000,000 is : 17664 MB
3,000,000,000 is : 20134 MB
3,750,000,000 is : 21134 MB
4,000,000,000 is : 21500 MB
4,250,000,000 is : 22000 MB - 24 GB GPUs
8,250,000,000 is : 29870 MB - 32 GB GPUs
22,000,000,000 is : 41700 MB - 48 GB GPUs

1280x720 px, 81 frames, 14b text to video model - FP8 precision (torch.float8_e4m3fn)

0 is : 14168 MB - Below 24 GB GPUs
1,000,000,000 is : 14918 MB
8,000,000,000 is : 21260 MB
8,750,000,000 is : 21980 MB - 24 GB GPUs
22,000,000,000 is : 27330 MB - 32 GB GPUs


480x832 px, 81 frames, 14b 480p image to video model - BF16 precision (torch.bfloat16)

0 is : 8618 MB - Below 12 GB GPUs
1,000,000,000 is : 9354 MB
1,500,000,000 is : 10090 MB - 12 GB GPUs
2,000,000,000 is : 11370 MB
3,000,000,000 is : 13080 MB
3,500,000,000 is : 14038 MB - 16 GB GPUs
4,000,000,000 is : 15140 MB
8,000,000,000 is : 22100 MB - 24 GB GPUs
12,000,000,000 is : 30060 MB - 32 GB GPUs
22,000,000,000 is : 38300 MB - 48 GB GPUs


480x832 px, 81 frames, 14b 480p image to video model - FP8 precision (torch.float8_e4m3fn)

0 is : 8618 MB - Below 12 GB GPUs
2,500,000,000 is : 9794 MB - 12 GB GPUs
7,500,000,000 is : 14850 MB - 16 GB GPUs
8,000,000,000 is : 15392 MB
15,000,000,000 is : 21700 MB - 24 GB GPUs
22,000,000,000 is : 23080 MB - 32 GB GPUs


720x1280 px, 81 frames, 14b 720p image to video model - BF16 precision (torch.bfloat16)

0 is : 18326 MB - Below 24 GB GPUs
2,000,000,000 is : 20360 MB
3,000,000,000 is : 22010 MB - 24 GB GPUs
6,000,000,000 is : 28380 MB
6,500,000,000 is : 29330 MB
6,750,000,000 is : 29790 MB - 32 GB GPUs
16,000,000,000 is : 47030 MB - 48 GB GPUs
22,000,000,000 is : 47800 MB - 80 GB GPUs


720x1280 px, 81 frames, 14b 720p image to video model - FP8 precision (torch.float8_e4m3fn)

0 is : 18326 MB - Below 24 GB GPUs
3,000,000,000 is : 19763 MB
6,000,000,000 is : 22020 MB - 24 GB GPUs
14,000,000,000 is : 29840 MB
15,000,000,000 is : 30790 MB - 32 GB GPUs
22,000,000,000 is : 32013 MB - 48 GB GPUs

GPU VRAM Usages Table With Respected To Number of Persistent Params+

All tests made on secondary GPU thus they are 100% accurate

Therefore, make sure that you have such empty VRAM before starting the Wan 2.1 SECourses App 

1280x720 px, 81 frames, 14b text to video model - BF16 precision (torch.bfloat16)

0 is : 14168 MB - Below 24 GB GPUs
1,000,000,000 is : 15658 MB
2,000,000,000 is : 17664 MB
3,000,000,000 is : 20134 MB
3,750,000,000 is : 21134 MB
4,000,000,000 is : 21500 MB
4,250,000,000 is : 22000 MB - 24 GB GPUs
8,250,000,000 is : 29870 MB - 32 GB GPUs
22,000,000,000 is : 41700 MB - 48 GB GPUs

1280x720 px, 81 frames, 14b text to video model - FP8 precision (torch.float8_e4m3fn)

0 is : 14168 MB - Below 24 GB GPUs
1,000,000,000 is : 14918 MB
8,000,000,000 is : 21260 MB
8,750,000,000 is : 21980 MB - 24 GB GPUs
22,000,000,000 is : 27330 MB - 32 GB GPUs


480x832 px, 81 frames, 14b 480p image to video model - BF16 precision (torch.bfloat16)

0 is : 8618 MB - Below 12 GB GPUs
1,000,000,000 is : 9354 MB
1,500,000,000 is : 10090 MB - 12 GB GPUs
2,000,000,000 is : 11370 MB
3,000,000,000 is : 13080 MB
3,500,000,000 is : 14038 MB - 16 GB GPUs
4,000,000,000 is : 15140 MB
8,000,000,000 is : 22100 MB - 24 GB GPUs
12,000,000,000 is : 30060 MB - 32 GB GPUs
22,000,000,000 is : 38300 MB - 48 GB GPUs


480x832 px, 81 frames, 14b 480p image to video model - FP8 precision (torch.float8_e4m3fn)

0 is : 8618 MB - Below 12 GB GPUs
2,500,000,000 is : 9794 MB - 12 GB GPUs
7,500,000,000 is : 14850 MB - 16 GB GPUs
8,000,000,000 is : 15392 MB
15,000,000,000 is : 21700 MB - 24 GB GPUs
22,000,000,000 is : 23080 MB - 32 GB GPUs


720x1280 px, 81 frames, 14b 720p image to video model - BF16 precision (torch.bfloat16)

0 is : 18326 MB - Below 24 GB GPUs
2,000,000,000 is : 20360 MB
3,000,000,000 is : 22010 MB - 24 GB GPUs
6,000,000,000 is : 28380 MB
6,500,000,000 is : 29330 MB
6,750,000,000 is : 29790 MB - 32 GB GPUs
16,000,000,000 is : 47030 MB - 48 GB GPUs
22,000,000,000 is : 47800 MB - 80 GB GPUs


720x1280 px, 81 frames, 14b 720p image to video model - FP8 precision (torch.float8_e4m3fn)

0 is : 18326 MB - Below 24 GB GPUs
3,000,000,000 is : 19763 MB
6,000,000,000 is : 22020 MB - 24 GB GPUs
14,000,000,000 is : 29840 MB
15,000,000,000 is : 30790 MB - 32 GB GPUs
22,000,000,000 is : 32013 MB - 48 GB GPUs

GPU VRAM Usages Table With Respected To Number of Persistent Params+

All tests made on secondary GPU thus they are 100% accurate

Therefore, make sure that you have such empty VRAM before starting the Wan 2.1 SECourses App 

1280x720 px, 81 frames, 14b text to video model - BF16 precision (torch.bfloat16)

0 is : 14168 MB - Below 24 GB GPUs
1,000,000,000 is : 15658 MB
2,000,000,000 is : 17664 MB
3,000,000,000 is : 20134 MB
3,750,000,000 is : 21134 MB
4,000,000,000 is : 21500 MB
4,250,000,000 is : 22000 MB - 24 GB GPUs
8,250,000,000 is : 29870 MB - 32 GB GPUs
22,000,000,000 is : 41700 MB - 48 GB GPUs

1280x720 px, 81 frames, 14b text to video model - FP8 precision (torch.float8_e4m3fn)

0 is : 14168 MB - Below 24 GB GPUs
1,000,000,000 is : 14918 MB
8,000,000,000 is : 21260 MB
8,750,000,000 is : 21980 MB - 24 GB GPUs
22,000,000,000 is : 27330 MB - 32 GB GPUs


480x832 px, 81 frames, 14b 480p image to video model - BF16 precision (torch.bfloat16)

0 is : 8618 MB - Below 12 GB GPUs
1,000,000,000 is : 9354 MB
1,500,000,000 is : 10090 MB - 12 GB GPUs
2,000,000,000 is : 11370 MB
3,000,000,000 is : 13080 MB
3,500,000,000 is : 14038 MB - 16 GB GPUs
4,000,000,000 is : 15140 MB
8,000,000,000 is : 22100 MB - 24 GB GPUs
12,000,000,000 is : 30060 MB - 32 GB GPUs
22,000,000,000 is : 38300 MB - 48 GB GPUs


480x832 px, 81 frames, 14b 480p image to video model - FP8 precision (torch.float8_e4m3fn)

0 is : 8618 MB - Below 12 GB GPUs
2,500,000,000 is : 9794 MB - 12 GB GPUs
7,500,000,000 is : 14850 MB - 16 GB GPUs
8,000,000,000 is : 15392 MB
15,000,000,000 is : 21700 MB - 24 GB GPUs
22,000,000,000 is : 23080 MB - 32 GB GPUs


720x1280 px, 81 frames, 14b 720p image to video model - BF16 precision (torch.bfloat16)

0 is : 18326 MB - Below 24 GB GPUs
2,000,000,000 is : 20360 MB
3,000,000,000 is : 22010 MB - 24 GB GPUs
6,000,000,000 is : 28380 MB
6,500,000,000 is : 29330 MB
6,750,000,000 is : 29790 MB - 32 GB GPUs
16,000,000,000 is : 47030 MB - 48 GB GPUs
22,000,000,000 is : 47800 MB - 80 GB GPUs


720x1280 px, 81 frames, 14b 720p image to video model - FP8 precision (torch.float8_e4m3fn)

0 is : 18326 MB - Below 24 GB GPUs
3,000,000,000 is : 19763 MB
6,000,000,000 is : 22020 MB - 24 GB GPUs
14,000,000,000 is : 29840 MB
15,000,000,000 is : 30790 MB - 32 GB GPUs
22,000,000,000 is : 32013 MB - 48 GB GPUs

A

art-ai_usa-girl•3/16/25, 7:41 PM

LatentSync was just updated to 1.5 https://github.com/bytedance/LatentSync

GitHub

GitHub - bytedance/LatentSync: Taming Stable Diffusion for Lip Sync!

Taming Stable Diffusion for Lip Sync! Contribute to bytedance/LatentSync development by creating an account on GitHub.

Aart-ai_usa-girl LatentSync was just updated to 1.5 https://github.com/bytedance/LatentSync

F

Furkan Gözükara SECourses•3/16/25, 7:48 PM

great

D

Dazzastrous [4090]•3/16/25, 9:12 PM