patientx and GitHub
f12bcde392
Merge branch 'comfyanonymous:master' into master
2025-03-03 15:10:56 +03:00
comfyanonymous
f86c724ef2
Temporal area composition.
...
New ConditioningSetAreaPercentageVideo node.
2025-03-03 06:50:31 -05:00
patientx and GitHub
6c34d0a58a
Update zluda.py
2025-03-02 22:43:11 +03:00
patientx and GitHub
7763bf823e
Merge branch 'comfyanonymous:master' into master
2025-03-02 17:18:12 +03:00
comfyanonymous
9af6320ec9
Make 2d area composition nodes work on video models.
2025-03-02 08:19:16 -05:00
patientx and GitHub
0c4bebf5fb
Merge branch 'comfyanonymous:master' into master
2025-03-01 14:59:20 +03:00
comfyanonymous
4dc6709307
Rename argument in last commit and document the options.
2025-03-01 02:43:49 -05:00
Chenlei Hu and GitHub
4d55f16ae8
Use enum list for --fast options ( #7024 )
2025-03-01 02:37:35 -05:00
patientx and GitHub
c235a51d82
Update zluda.py
2025-02-28 16:41:56 +03:00
patientx and GitHub
af43425ab5
Update model_management.py
2025-02-28 16:37:55 +03:00
patientx and GitHub
1871a594ba
Merge branch 'comfyanonymous:master' into master
2025-02-28 11:47:19 +03:00
comfyanonymous
cf0b549d48
--fast now takes a number as argument to indicate how fast you want it.
...
The idea is that you can indicate how much quality vs speed you want.
At the moment:
--fast 2 enables fp16 accumulation if your pytorch supports it.
--fast 5 enables fp8 matrix mult on fp8 models and the optimization above.
--fast without a number enables all optimizations.
2025-02-28 02:48:20 -05:00
comfyanonymous
eb4543474b
Use fp16 for intermediate for fp8 weights with --fast if supported.
2025-02-28 02:17:50 -05:00
comfyanonymous
1804397952
Use fp16 if checkpoint weights are fp16 and the model supports it.
2025-02-27 16:39:57 -05:00
patientx and GitHub
cc65ca4c42
Merge branch 'comfyanonymous:master' into master
2025-02-28 00:39:40 +03:00
comfyanonymous
f4dac8ab6f
Wan code small cleanup.
2025-02-27 07:22:42 -05:00
patientx and GitHub
c4fb9f2a63
Merge branch 'comfyanonymous:master' into master
2025-02-27 13:06:17 +03:00
89253e9fe5
Support Cambricon MLU ( #6964 )
...
Co-authored-by: huzhan <huzhan@cambricon.com >
2025-02-26 20:45:13 -05:00
comfyanonymous
3ea3bc8546
Fix wan issues when prompt length is long.
2025-02-26 20:34:02 -05:00
patientx and GitHub
b04a1f4127
Merge branch 'comfyanonymous:master' into master
2025-02-27 01:24:29 +03:00
comfyanonymous
0270a0b41c
Reduce artifacts on Wan by doing the patch embedding in fp32.
2025-02-26 16:59:26 -05:00
patientx and GitHub
4f968c3c56
Merge branch 'comfyanonymous:master' into master
2025-02-26 17:11:50 +03:00
comfyanonymous
c37f15f98e
Add fast preview support for Wan models.
2025-02-26 08:56:23 -05:00
patientx and GitHub
1193f3fbb1
Merge branch 'comfyanonymous:master' into master
2025-02-26 16:47:39 +03:00
comfyanonymous
4bca7367f3
Don't try to use clip_fea on t2v model.
2025-02-26 08:38:09 -05:00
patientx and GitHub
debf69185c
Merge branch 'comfyanonymous:master' into master
2025-02-26 16:00:33 +03:00
comfyanonymous
b6fefe686b
Better wan memory estimation.
2025-02-26 07:51:22 -05:00
patientx and GitHub
583f140eda
Merge branch 'comfyanonymous:master' into master
2025-02-26 13:26:25 +03:00
comfyanonymous
fa62287f1f
More code reuse in wan.
...
Fix bug when changing the compute dtype on wan.
2025-02-26 05:22:29 -05:00
patientx and GitHub
743996a1f7
Merge branch 'comfyanonymous:master' into master
2025-02-26 12:56:06 +03:00
comfyanonymous
0844998db3
Slightly better wan i2v mask implementation.
2025-02-26 03:49:50 -05:00
comfyanonymous
4ced06b879
WIP support for Wan I2V model.
2025-02-26 01:49:43 -05:00
patientx and GitHub
1e91ff59a1
Merge branch 'comfyanonymous:master' into master
2025-02-26 09:24:15 +03:00
comfyanonymous
cb06e9669b
Wan seems to work with fp16.
2025-02-25 21:37:12 -05:00
patientx and GitHub
6e894524e2
Merge branch 'comfyanonymous:master' into master
2025-02-26 04:14:10 +03:00
comfyanonymous
9a66bb972d
Make wan work with all latent resolutions.
...
Cleanup some code.
2025-02-25 19:56:04 -05:00
patientx and GitHub
4269943ac3
Merge branch 'comfyanonymous:master' into master
2025-02-26 03:13:47 +03:00
comfyanonymous
ea0f939df3
Fix issue with wan and other attention implementations.
2025-02-25 19:13:39 -05:00
comfyanonymous
f37551c1d2
Change wan rope implementation to the flux one.
...
Should be more compatible.
2025-02-25 19:11:14 -05:00
patientx and GitHub
879db7bdfc
Merge branch 'comfyanonymous:master' into master
2025-02-26 02:07:25 +03:00
comfyanonymous
63023011b9
WIP support for Wan t2v model.
2025-02-25 17:20:35 -05:00
patientx and GitHub
6cf0fdcc3c
Merge branch 'comfyanonymous:master' into master
2025-02-25 17:12:14 +03:00
comfyanonymous
f40076096e
Cleanup some lumina te code.
2025-02-25 04:10:26 -05:00
patientx and GitHub
d705fe2e0b
Merge branch 'comfyanonymous:master' into master
2025-02-24 13:42:27 +03:00
comfyanonymous
96d891cb94
Speedup on some models by not upcasting bfloat16 to float32 on mac.
2025-02-24 05:41:32 -05:00
patientx and GitHub
8142770e5f
Merge branch 'comfyanonymous:master' into master
2025-02-23 14:51:43 +03:00
comfyanonymous
ace899e71a
Prioritize fp16 compute when using allow_fp16_accumulation
2025-02-23 04:45:54 -05:00
patientx and GitHub
c15fe75f7b
CUDA error: CUBLAS_STATUS_NOT_SUPPORTED when calling `cublasLtMatmulAlgoGetHeuristic" ,error fix
2025-02-22 15:44:20 +03:00
patientx and GitHub
26eb98b96f
Merge branch 'comfyanonymous:master' into master
2025-02-22 14:42:22 +03:00
comfyanonymous
aff16532d4
Remove some useless code.
2025-02-22 04:45:14 -05:00
