Commits · db8b59ecff7be40377d17ea69487f442b469c536 · chenpangpang / ComfyUI

"vscode:/vscode.git/clone" did not exist on "af4a9ce02425a2e9e99594d7b322bbf49a24bfbc"

14 Mar, 2024 1 commit
- Lower memory usage for loras in lowvram mode at the cost of perf. · db8b59ec
  comfyanonymous authored Mar 13, 2024
  
  db8b59ec
11 Mar, 2024 1 commit
- Change log levels. · 0ed72bef
  comfyanonymous authored Mar 11, 2024
```
Logging level now defaults to info. --verbose sets it to debug.
```
  0ed72bef
10 Mar, 2024 1 commit
- Replace prints with logging and add --verbose argument. · 65397ce6
  comfyanonymous authored Mar 10, 2024
  
  65397ce6
02 Mar, 2024 1 commit
- Add some tesla pascal GPUs to the fp16 working but slower list. · dce35553
  comfyanonymous authored Mar 02, 2024
  
  dce35553
19 Feb, 2024 1 commit
- Enable fp16 by default on mps. · 88f30040
  comfyanonymous authored Feb 19, 2024
  
  88f30040
17 Feb, 2024 2 commits
- Manual cast for bf16 on older GPUs. · 929e266f
  comfyanonymous authored Feb 17, 2024
  
  929e266f
- Make --force-fp32 disable loading models in bf16. · 0b3c5048
  comfyanonymous authored Feb 16, 2024
  
  0b3c5048
16 Feb, 2024 2 commits
- Stable Cascade Stage C. · f83109f0
  comfyanonymous authored Feb 16, 2024
  
  f83109f0
- Small refactor of is_device_* functions. · aeaeca10
  comfyanonymous authored Feb 15, 2024
  
  aeaeca10
05 Feb, 2024 1 commit
- Don't use is_bf16_supported to check for fp16 support. · 66e28ef4
  comfyanonymous authored Feb 04, 2024
  
  66e28ef4
04 Feb, 2024 1 commit
- Speed up SDXL on 16xx series with fp16 weights and manual cast. · 24129d78
  comfyanonymous authored Feb 04, 2024
  
  24129d78
02 Feb, 2024 1 commit
- Always use fp16 for the text encoders. · 4b023906
  comfyanonymous authored Feb 02, 2024
  
  4b023906
15 Jan, 2024 1 commit
- Only auto enable bf16 VAE on nvidia GPUs that actually support it. · f9e55d84
  comfyanonymous authored Jan 15, 2024
  
  f9e55d84
30 Dec, 2023 1 commit
- Add argument to run the VAE on the CPU. · 1b103e0c
  comfyanonymous authored Dec 30, 2023
  
  1b103e0c
29 Dec, 2023 1 commit
- Load weights that can't be lowvramed to target device. · e1e322cf
  comfyanonymous authored Dec 28, 2023
  
  e1e322cf
23 Dec, 2023 1 commit
- --disable-smart-memory now unloads everything like it did originally. · a252963f
  comfyanonymous authored Dec 23, 2023
  
  a252963f
22 Dec, 2023 1 commit
- Greatly improve lowvram sampling speed by getting rid of accelerate. · 36a79531
  comfyanonymous authored Dec 22, 2023
```
Let me know if this breaks anything.
```
  36a79531
17 Dec, 2023 1 commit
- Add --deterministic option to make pytorch use deterministic algorithms. · 2f9d6a97
  comfyanonymous authored Dec 17, 2023
  
  2f9d6a97
11 Dec, 2023 3 commits
- Add an option --fp16-unet to force using fp16 for the unet. · b0aab1e4
  comfyanonymous authored Dec 11, 2023
  
  b0aab1e4
- Use faster manual cast for fp8 in unet. · ba07cb74
  comfyanonymous authored Dec 11, 2023
  
  ba07cb74
- Switch text encoder to manual cast. · 57926635
  comfyanonymous authored Dec 10, 2023
```
Use fp16 text encoder weights for CPU inference to lower memory usage.
```
  57926635
10 Dec, 2023 1 commit
- Disable non blocking on mps. · 340177e6
  comfyanonymous authored Dec 10, 2023
  
  340177e6
08 Dec, 2023 1 commit
- Make --gpu-only put intermediate values in GPU memory instead of cpu. · 9ac0b487
  comfyanonymous authored Dec 08, 2023
  
  9ac0b487
06 Dec, 2023 1 commit
- Slightly faster lora applying. · 2db86b46
  comfyanonymous authored Dec 06, 2023
  
  2db86b46
04 Dec, 2023 2 commits
- Use .itemsize to get dtype size for fp8. · ca82ade7
  comfyanonymous authored Dec 04, 2023
  
  ca82ade7
- UNET weights can now be stored in fp8. · 31b0f6f3
  comfyanonymous authored Dec 04, 2023
```
--fp8_e4m3fn-unet and --fp8_e5m2-unet are the two different formats
supported by pytorch.
```
  31b0f6f3
17 Nov, 2023 1 commit

Add some command line arguments to store text encoder weights in fp8. · 0cf4e869

comfyanonymous authored Nov 17, 2023

Pytorch supports two variants of fp8:
--fp8_e4m3fn-text-enc (the one that seems to give better results)
--fp8_e5m2-text-enc

0cf4e869

13 Nov, 2023 1 commit
- Disable xformers when it can't load properly. · 7339479b
  comfyanonymous authored Nov 13, 2023
  
  7339479b
12 Nov, 2023 1 commit
- Allow different models to estimate memory usage differently. · dd4ba68b
  comfyanonymous authored Nov 12, 2023
  
  dd4ba68b
22 Oct, 2023 1 commit
- Empty the cache when torch cache is more than 25% free mem. · 8594c8be
  comfyanonymous authored Oct 22, 2023
  
  8594c8be
16 Oct, 2023 1 commit
- Add some Quadro cards to the list of cards with broken fp16. · c8013f73
  comfyanonymous authored Oct 16, 2023
  
  c8013f73
13 Oct, 2023 2 commits
- Add a --bf16-unet to test running the unet in bf16. · fd4c5f07
  comfyanonymous authored Oct 13, 2023
  
  fd4c5f07
- Refactor code so model can be a dtype other than fp32 or fp16. · 9a55dadb
  comfyanonymous authored Oct 13, 2023
  
  9a55dadb
12 Oct, 2023 2 commits
- pytorch_attention_enabled can now return True when xformers is enabled. · 88733c99
  comfyanonymous authored Oct 11, 2023
  
  88733c99
- Pull some small changes from the other repo. · 20d3852a
  comfyanonymous authored Oct 11, 2023
  
  20d3852a
23 Sep, 2023 1 commit
- Allow Intel GPUs to LoRA cast on GPU since it supports BF16 natively. · eec449ca
  Simon Lui authored Sep 22, 2023
  
  eec449ca
20 Sep, 2023 1 commit
- Only do the cast on the device if the device supports it. · 1cdfb3db
  comfyanonymous authored Sep 20, 2023
  
  1cdfb3db
17 Sep, 2023 1 commit
- Enable pytorch attention by default on xpu. · 321c5fa2
  comfyanonymous authored Sep 17, 2023
  
  321c5fa2
14 Sep, 2023 1 commit
- Don't run text encoders on xpu because there are issues. · 0966d3ce
  comfyanonymous authored Sep 14, 2023
  
  0966d3ce
04 Sep, 2023 1 commit
- Add a force argument to soft_empty_cache to force a cache empty. · 1938f5c5
  comfyanonymous authored Sep 04, 2023
  
  1938f5c5