comfyanonymous
ef493ebbf8
Raw torch is faster than einops?
2024-08-08 22:09:29 -04:00
comfyanonymous
8e1189dae5
Cleaner code.
2024-08-08 20:07:09 -04:00
comfyanonymous
114af84d12
Try to improve inference speed on some machines.
2024-08-08 17:29:27 -04:00
comfyanonymous
37d704b5d6
Better prints.
2024-08-08 17:29:27 -04:00
Alex "mcmonkey" Goodwin
9150dd0225
PullRequest CI Run: use pull_request_target to allow the CI Dashboard to work ( #4277 )
...
'_target' allows secrets to pass through, and we're just using the secret that allows uploading to the dashboard and are manually vetting PRs before running this workflow anyway
2024-08-08 17:20:48 -04:00
Alex "mcmonkey" Goodwin
1277050a01
minor fix on copypasta action name ( #4276 )
...
my bad sorry
2024-08-08 16:30:59 -04:00
Alex "mcmonkey" Goodwin
4f28c96a6a
add GitHub workflow for CI tests of PRs ( #4275 )
...
When the 'Run-CI-Test' label is added to a PR, it will be tested by the CI, on a small matrix of stable versions.
2024-08-08 16:24:49 -04:00
Alex "mcmonkey" Goodwin
f3139f5361
Add full CI test matrix GitHub Workflow ( #4274 )
...
automatically runs a matrix of full GPU-enabled tests on all new commits to the ComfyUI master branch
2024-08-08 15:40:07 -04:00
comfyanonymous
4f196c19a3
Fix.
2024-08-08 15:16:51 -04:00
comfyanonymous
6e0e401ebe
Support diffusers text attention flux loras.
2024-08-08 14:45:52 -04:00
comfyanonymous
ede5622146
Partial model shift support.
2024-08-08 14:45:06 -04:00
comfyanonymous
6f69d4e0ec
Add Flux fp16 support hack.
2024-08-07 15:08:39 -04:00
comfyanonymous
5a25225024
Make supported_dtypes a priority list.
2024-08-07 15:00:06 -04:00
comfyanonymous
57697eb7cf
Workaround for lora OOM on lowvram mode.
2024-08-07 14:30:54 -04:00
comfyanonymous
25bcb846a8
Fix "Comfy" lora keys.
...
They are in this format now:
diffusion_model.full.model.key.name.lora_up.weight
2024-08-07 13:49:31 -04:00
comfyanonymous
7c94219393
Fix bundled embed.
2024-08-07 13:30:45 -04:00
comfyanonymous
a6d6c2d378
Support for "Comfy" lora format.
...
The keys are just: model.full.model.key.name.lora_up.weight
It is supported by all comfyui supported models.
Now people can just convert loras to this format instead of having to ask
for me to implement them.
2024-08-07 13:18:32 -04:00
comfyanonymous
3e01ab3a66
Controlnet code refactor.
2024-08-07 12:59:28 -04:00
comfyanonymous
04f70b853e
Support format for embeddings bundled in loras.
2024-08-07 03:45:25 -04:00
PhilWun
6dc38ec333
Add type hints to folder_paths.py ( #4191 )
...
* add type hints to folder_paths.py
* replace deprecated standard collections type hints
* fix type error when using Python 3.8
2024-08-06 21:59:34 -04:00
comfyanonymous
001ff4d6a6
Fix OOMs happening in some cases.
...
A cloned model patcher sometimes reported a model was loaded on a device
when it wasn't.
2024-08-06 13:36:04 -04:00
comfyanonymous
74b2ae7ac3
Unload all models if there's an OOM error.
2024-08-06 03:30:28 -04:00
comfyanonymous
5228fbf0ad
Unload models and load them back in lowvram mode no free vram.
2024-08-06 03:22:39 -04:00
Robin Huang
006782db44
Clone taesd with depth of 1 to reduce download size. ( #4232 )
2024-08-06 01:46:09 -04:00
Silver
a4c5e04e27
Add format metadata to CLIP save to make compatible with diffusers safetensors loading ( #4233 )
2024-08-06 01:45:24 -04:00
Chenlei Hu
e4558e56aa
Change browser test CI python to 3.8 ( #4234 )
2024-08-06 01:27:28 -04:00
comfyanonymous
bcb4848096
Flux tweak memory usage.
2024-08-05 21:58:28 -04:00
Robin Huang
96a3497015
Stable release uses cached dependencies ( #4231 )
...
* Release stable based on existing tag.
* Update default cuda to 12.1.
2024-08-05 20:07:16 -04:00
comfyanonymous
f7183e2c73
Improve performance on some lowend GPUs.
2024-08-05 16:24:04 -04:00
comfyanonymous
5c0c9b8503
This probably doesn't work anymore.
2024-08-05 12:31:42 -04:00
bymyself
34d26e8fb6
Don't cache index.html ( #4211 )
2024-08-05 12:25:28 -04:00
a-One-Fan
2e56b50183
Fix Flux FP64 math on XPU ( #4210 )
2024-08-05 01:26:20 -04:00
comfyanonymous
261c6ba855
Support simple diffusers Flux loras.
2024-08-04 22:05:48 -04:00
Silver
b87a10e5f1
Correct spelling 'token_weight_pars_t5' to 'token_weight_pairs_t5' ( #4200 )
2024-08-04 17:10:02 -04:00
comfyanonymous
2ba49bbd82
Set the step in EmptySD3LatentImage to 16.
...
These models work better when the res is a multiple of 16.
2024-08-04 15:59:02 -04:00
comfyanonymous
8e7aa23b6a
ONNX tracing fixes.
2024-08-04 15:45:43 -04:00
comfyanonymous
85fadea55c
Fix issue with some custom nodes.
2024-08-04 10:03:33 -04:00
comfyanonymous
55c9c01bec
ModelSamplingFlux now takes a resolution and adjusts the shift with it.
...
If you want to sample Flux dev exactly how the reference code does use
the same resolution as your image in this node.
2024-08-04 04:06:00 -04:00
comfyanonymous
10ad73d520
Fix crash.
2024-08-03 16:55:38 -04:00
comfyanonymous
e7287d2fc2
Tweak lowvram memory formula.
2024-08-03 16:44:50 -04:00
comfyanonymous
d4ca060482
Lower lowvram memory to 1/3 of free memory.
2024-08-03 15:14:07 -04:00
comfyanonymous
f27f0f8a48
Fix some issues.
2024-08-03 15:06:40 -04:00
comfyanonymous
e83d97d649
Cap lowvram to half of free memory.
2024-08-03 14:50:20 -04:00
comfyanonymous
753d9640f9
Automatically use fp8 for diffusion model weights if:
...
Checkpoint contains weights in fp8.
There isn't enough memory to load the diffusion model in GPU vram.
2024-08-03 13:45:19 -04:00
comfyanonymous
2181bb7a57
Load T5 in fp8 if it's in fp8 in the Flux checkpoint.
2024-08-03 12:39:33 -04:00
comfyanonymous
2878ffd75a
More aggressive batch splitting.
2024-08-03 11:53:30 -04:00
comfyanonymous
ad4292b964
Add ModelSamplingFlux to experiment with the shift value.
...
Default shift on Flux Schnell is 0.0
2024-08-03 03:54:38 -04:00
comfyanonymous
16ac61d4d0
Add advanced model merge node for Flux model.
2024-08-02 23:20:53 -04:00
comfyanonymous
b0eaa09c6a
Better per model memory usage estimations.
2024-08-02 18:09:24 -04:00
comfyanonymous
e2284e5609
Tweak regular SD memory formula.
2024-08-02 17:34:30 -04:00
