Dr.Lt.Data
|
552fbf4605
|
Merge branch 'comfyanonymous:master' into feature/blockweights
|
2023-06-20 09:26:54 +09:00 |
|
comfyanonymous
|
036a22077c
|
Fix k_diffusion math being off by a tiny bit during txt2img.
|
2023-06-19 15:28:54 -04:00 |
|
Dr.Lt.Data
|
7dd3c7240a
|
Merge branch 'comfyanonymous:master' into feature/blockweights
|
2023-06-19 16:12:22 +09:00 |
|
comfyanonymous
|
8883cb0f67
|
Add a way to set patches that modify the attn2 output.
Change the transformer patches function format to be more future proof.
|
2023-06-18 22:58:22 -04:00 |
|
comfyanonymous
|
cd930d4e7f
|
pop clip vision keys after loading them.
|
2023-06-18 21:21:17 -04:00 |
|
comfyanonymous
|
c9e4a8c9e5
|
Not needed anymore.
|
2023-06-18 13:06:59 -04:00 |
|
Dr.Lt.Data
|
09e6066e74
|
Merge branch 'comfyanonymous:master' into feature/blockweights
|
2023-06-19 00:52:37 +09:00 |
|
comfyanonymous
|
fb4bf7f591
|
This is not needed anymore and causes issues with alphas_cumprod.
|
2023-06-18 03:18:25 -04:00 |
|
comfyanonymous
|
45be2e92c1
|
Fix DDIM v-prediction.
|
2023-06-17 20:48:21 -04:00 |
|
Dr.Lt.Data
|
0125032b0a
|
Merge branch 'comfyanonymous:master' into feature/blockweights
|
2023-06-17 10:17:21 +09:00 |
|
comfyanonymous
|
e6e50ab2dd
|
Fix an issue when alphas_comprod are half floats.
|
2023-06-16 17:16:51 -04:00 |
|
Dr.Lt.Data
|
6a51279131
|
Merge branch 'comfyanonymous:master' into feature/blockweights
|
2023-06-16 09:19:24 +09:00 |
|
comfyanonymous
|
ae43f09ef7
|
All the unet weights should now be initialized with the right dtype.
|
2023-06-15 18:42:30 -04:00 |
|
comfyanonymous
|
f7edcfd927
|
Add a --gpu-only argument to keep and run everything on the GPU.
Make the CLIP model work on the GPU.
|
2023-06-15 15:38:52 -04:00 |
|
comfyanonymous
|
7bf89ba923
|
Initialize more unet weights as the right dtype.
|
2023-06-15 15:00:10 -04:00 |
|
comfyanonymous
|
e21d9ad445
|
Initialize transformer unet block weights in right dtype at the start.
|
2023-06-15 14:29:26 -04:00 |
|
Dr.Lt.Data
|
7d5ec16c4c
|
Merge branch 'comfyanonymous:master' into feature/blockweights
|
2023-06-15 11:58:34 +09:00 |
|
comfyanonymous
|
bb1f45d6e8
|
Properly disable weight initialization in clip models.
|
2023-06-14 20:13:08 -04:00 |
|
Dr.Lt.Data
|
9dfca3fb7c
|
Merge branch 'comfyanonymous:master' into feature/blockweights
|
2023-06-15 09:05:22 +09:00 |
|
comfyanonymous
|
21f04fe632
|
Disable default weight values in unet conv2d for faster loading.
|
2023-06-14 19:46:08 -04:00 |
|
comfyanonymous
|
9d54066ebc
|
This isn't needed for inference.
|
2023-06-14 13:05:08 -04:00 |
|
comfyanonymous
|
fa2cca056c
|
Don't initialize CLIPVision weights to default values.
|
2023-06-14 12:57:02 -04:00 |
|
comfyanonymous
|
6b774589a5
|
Set model to fp16 before loading the state dict to lower ram bump.
|
2023-06-14 12:48:02 -04:00 |
|
comfyanonymous
|
0c7cad404c
|
Don't initialize clip weights to default values.
|
2023-06-14 12:47:36 -04:00 |
|
comfyanonymous
|
6971646b8b
|
Speed up model loading a bit.
Default pytorch Linear initializes the weights which is useless and slow.
|
2023-06-14 12:09:41 -04:00 |
|
comfyanonymous
|
388567f20b
|
sampler_cfg_function now uses a dict for the argument.
This means arguments can be added without issues.
|
2023-06-13 16:10:36 -04:00 |
|
Dr.Lt.Data
|
75909ffee6
|
Merge branch 'comfyanonymous:master' into feature/blockweights
|
2023-06-14 00:01:22 +09:00 |
|
comfyanonymous
|
ff9b22d79e
|
Turn on safe load for a few models.
|
2023-06-13 10:12:03 -04:00 |
|
comfyanonymous
|
735ac4cf81
|
Remove pytorch_lightning dependency.
|
2023-06-13 10:11:33 -04:00 |
|
comfyanonymous
|
2b14041d4b
|
Remove useless code.
|
2023-06-13 02:40:58 -04:00 |
|
comfyanonymous
|
274dff3257
|
Remove more useless files.
|
2023-06-13 02:22:19 -04:00 |
|
comfyanonymous
|
f0a2b81cd0
|
Cleanup: Remove a bunch of useless files.
|
2023-06-13 02:19:08 -04:00 |
|
Dr.Lt.Data
|
908b08e337
|
Merge branch 'comfyanonymous:master' into feature/blockweights
|
2023-06-12 20:57:22 +09:00 |
|
comfyanonymous
|
f8c5931053
|
Split the batch in VAEEncode if there's not enough memory.
|
2023-06-12 00:21:50 -04:00 |
|
comfyanonymous
|
c069fc0730
|
Auto switch to tiled VAE encode if regular one runs out of memory.
|
2023-06-11 23:25:39 -04:00 |
|
Dr.Lt.Data
|
b302274aea
|
Merge branch 'comfyanonymous:master' into feature/blockweights
|
2023-06-12 00:43:31 +09:00 |
|
comfyanonymous
|
c64ca8c0b2
|
Refactor unCLIP noise augment out of samplers.py
|
2023-06-11 04:01:18 -04:00 |
|
Dr.Lt.Data
|
5d2d4deca4
|
Merge branch 'comfyanonymous:master' into feature/blockweights
|
2023-06-10 09:21:47 +09:00 |
|
comfyanonymous
|
de142eaad5
|
Simpler base model code.
|
2023-06-09 12:31:16 -04:00 |
|
Dr.Lt.Data
|
568ea50342
|
Merge branch 'comfyanonymous:master' into feature/blockweights
|
2023-06-09 15:49:33 +09:00 |
|
comfyanonymous
|
23cf8ca7c5
|
Fix bug when embedding gets ignored because of mismatched size.
|
2023-06-08 23:48:14 -04:00 |
|
Dr.Lt.Data
|
f9d126afff
|
Merge branch 'comfyanonymous:master' into feature/blockweights
|
2023-06-07 17:46:04 +09:00 |
|
comfyanonymous
|
0e425603fb
|
Small refactor.
|
2023-06-06 13:23:01 -04:00 |
|
Dr.Lt.Data
|
59728bad5f
|
Merge branch 'comfyanonymous:master' into feature/blockweights
|
2023-06-06 19:04:11 +09:00 |
|
comfyanonymous
|
a3a713b6c5
|
Refactor previews into one command line argument.
Clean up a few things.
|
2023-06-06 02:13:05 -04:00 |
|
space-nuko
|
3e17971acb
|
preview method autodetection
|
2023-06-05 18:59:10 -05:00 |
|
space-nuko
|
d5a28fadaa
|
Add latent2rgb preview
|
2023-06-05 18:39:56 -05:00 |
|
space-nuko
|
48f7ec750c
|
Make previews into cli option
|
2023-06-05 13:19:02 -05:00 |
|
space-nuko
|
b4f434ee66
|
Preview sampled images with TAESD
|
2023-06-05 09:20:17 -05:00 |
|
Dr.Lt.Data
|
6fcedbf26a
|
Merge branch 'comfyanonymous:master' into feature/blockweights
|
2023-06-05 21:08:07 +09:00 |
|