Zengtudor/Wan2.1
1
0
Fork 0
mirror of https://github.com/Wan-Video/Wan2.1.git synced 2025-06-07 15:54:52 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity
23 Commits 6 Branches 0 Tags 16 MiB
d0ff85adc9
Commit Graph

23 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
pftq
d0ff85adc9
VAE Tiling Support - credits to deepbeepmeep's WanGP 2025-03-18 22:17:31 -07:00
pftq
09ba994635
VAE Tiling Support - credits to deepbeepmeep's WanGP 2025-03-18 22:16:33 -07:00
pftq
a0de59e928
Batch feature mirrored to T2V 2025-03-17 13:52:15 -07:00
pftq
70410ac7c3
Update README.md 2025-03-17 13:31:13 -07:00
pftq
d2d47c81c1
Added negative prompt option 2025-03-17 13:30:12 -07:00
pftq
68db072ae0
Update README.md 2025-03-17 12:50:44 -07:00
pftq
410f74c499
Update README.md 2025-03-17 12:47:59 -07:00
pftq
fb6348dd6f
Update requirements.txt 2025-03-15 12:07:03 -07:00
pftq
236dd43edd
Merge branch 'main' into main 2025-02-27 10:44:35 -08:00
pftq
3aec13addb
Added optional --variety_batch flag to vary the CFG and Steps within a batch. 2025-02-27 10:37:55 -08:00
章谨
6797c48002 update comfyui 2025-02-27 12:56:36 +08:00
pftq
5bd54ebe00
Fixed I2V Frames Hardcoded at 81 - updated frame_num to F for consistency 2025-02-26 13:23:28 -08:00
pftq
99d10e4dbb
Fixed I2V Frames Hardcoded at 81 in WanI2V.generate() 
Look for # 20250226 pftq
 2025-02-26 13:14:57 -08:00
pftq
3d8f5f1a04
Added --batch_size parameter to generate multiple videos per run without reloading the model. 
Fixed seed synchronization handling by pre-generating them before the batch.
 2025-02-26 07:55:30 -08:00
Yingda Chen
190e928681
add modelscope download cli 2025-02-26 22:31:12 +08:00
WanX-Video
d7b01803de
update gradio (#58) 2025-02-26 20:33:18 +08:00
cocktailpeanut
89b065f4fe
os.path.sep instead of / (#12) 2025-02-26 18:57:30 +08:00
Adrian Corduneanu
0e3c42a830
Update text2video.py to reduce GPU memory by emptying cache (#44) 
* Update text2video.py to reduce GPU memory by emptying cache

If offload_model is set, empty_cache() must be called after the model is moved to CPU to actually free the GPU. I verified on a RTX 4090 that without calling empty_cache the model remains in memory and the subsequent vae decoding never finishes.

* Update text2video.py only one empty_cache needed before vae decode
 2025-02-26 18:56:57 +08:00
WanX-Video
73648654c5
Update requirements.txt 2025-02-26 12:02:30 +08:00
WanX-Video
a815a48c3e
Update README.md 2025-02-26 11:18:26 +08:00
WanX-Video
04e8653c99
Update README.md 2025-02-25 22:54:11 +08:00
WanX-Video-1
5512ca4b33 init upload 2025-02-25 22:27:54 +08:00
WanX-Video-1
65386b2e03 init upload 2025-02-25 22:07:47 +08:00