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 SECoursesOP•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 SECoursesOP•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 SECoursesOP•3/16/25, 6:07 PM

5090 makes difference in some cases

F

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

like 14b model fitting into vram with fp8

F

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

just finished testing :d

F

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

great

D

Dazzastrous [4090]•3/16/25, 9:12 PM

oh oh on options screen v38 of wan you have 1,2,3,4,5,7,6

DDazzastrous [4090]oh oh on options screen v38 of wan you have 1,2,3,4,5,**7,6 **

F

Furkan Gözükara SECoursesOP•3/16/25, 9:13 PM

what do you mean

D

Dazzastrous [4090]•3/16/25, 9:13 PM

on the download models

F

Furkan Gözükara SECoursesOP•3/16/25, 9:13 PM

yes it is like that

F

Furkan Gözükara SECoursesOP•3/16/25, 9:13 PM

:d

D

Dazzastrous [4090]•3/16/25, 9:14 PM

numerical order

D

Dazzastrous [4090]•3/16/25, 9:14 PM

so 6 for all models still?

F

Furkan Gözükara SECoursesOP•3/16/25, 9:15 PM

yep

D

Dazzastrous [4090]•3/16/25, 9:15 PM

F

Furkan Gözükara SECoursesOP•3/16/25, 9:15 PM

it is accurate

D

Dazzastrous [4090]•3/16/25, 9:16 PM

not with people with ocd lol

D

Dazzastrous [4090]•3/16/25, 9:37 PM

ok i download made a fresh reinstall of wan 38 and its sticking on 0%

F

Furkan Gözükara SECoursesOP•3/16/25, 9:38 PM

just wait :d

D

Dazzastrous [4090]•3/16/25, 9:41 PM

still 0%

D

Dazzastrous [4090]•3/16/25, 9:46 PM

and still 0%

DDazzastrous [4090]and still 0% 😭

F

Furkan Gözükara SECoursesOP•3/16/25, 9:51 PM

what do you see on ram and gpu

D

Dazzastrous [4090]•3/16/25, 10:00 PM

i rebooted

D

Dazzastrous [4090]•3/16/25, 10:05 PM

23.4 gb and ram = 3.8

D

Dazzastrous [4090]•3/16/25, 10:05 PM

in task manager performance my gpu is at the bottom used to be at the top lol

D

Dazzastrous [4090]•3/16/25, 10:09 PM

[CMD] Model loaded successfully.
[CMD] Using resolution: width=480 height=832
Only

num_frames % 4 != 1

num_frames % 4 != 1

num_frames % 4 != 1

num_frames % 4 != 1 is acceptable. We round it up to 121.
0%| | 0/50 [00:00<?, ?it/s]WAN 2.1 14B Image-to-Video 480P

D

Dazzastrous [4090]•3/16/25, 10:09 PM

not working right for me

D

Dazzastrous [4090]•3/16/25, 10:10 PM

prev version was ok

DDazzastrous [4090][CMD] Model loaded successfully. [CMD] Using resolution: width=480 height=832 On...

F

Furkan Gözükara SECoursesOP•3/16/25, 10:12 PM

how many frames you have?

F

Furkan Gözükara SECoursesOP•3/16/25, 10:12 PM

what do you see on cmd ram gpu?

D

Dazzastrous [4090]•3/16/25, 10:18 PM

gave me a runtime error something about tensors on cpu and gpu

D

Dazzastrous [4090]•3/16/25, 10:19 PM

and the aspect ratio keeps changing back from portrait to 16.9

D

Dazzastrous [4090]•3/16/25, 10:24 PM

knocked it down to 81 frames

D

Dazzastrous [4090]•3/16/25, 10:24 PM

using 0.5 ram

D

Dazzastrous [4090]•3/16/25, 10:24 PM

but ive used higher than 81 before and produced upto 16 sec vids

D

Dazzastrous [4090]•3/16/25, 10:26 PM

21.97 it/s

A

art-ai_usa-girl•3/17/25, 1:14 PM

MIDI: Multi-Instance Diffusion for Single Image to 3D Scene Generation https://huanngzh.github.io/MIDI-Page/

MIDI: Multi-Instance Diffusion for Single Image to 3D Scene ...

MIDI is a novel paradigm for compositional 3D scene generation from a single image, extending pre-trained 3D object generation models to multi-instance diffusion models for simultaneous generation of multiple 3D instances.

T

theJindesan•3/17/25, 6:46 PM

@Furkan Gözükara SECourses Are you seeing the full 32GB in windows from your 5090? Mine only reports 31.5GB and its the difference between fitting the full Wan Model or not.. My 3090 reports 24.0 - in the same task manager so I'm thinking its not the 1024 calculation.

TtheJindesan <@205854764540362752> Are you seeing the full 32GB in windows from your 5090? M...

W

Weatherby•3/17/25, 8:19 PM

Which is your primary gpu connected to your display?

WWeatherby Which is your primary gpu connected to your display?

T

theJindesan•3/17/25, 9:18 PM

Onboard Intel. Both headless. 3090 shows the full 24.0

T

theJindesan•3/17/25, 9:19 PM

T

theJindesan•3/17/25, 9:20 PM