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
Dr.Lt.Data
6a51279131
Merge branch 'comfyanonymous:master' into feature/blockweights
2023-06-16 09:19:24 +09:00
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
Dr.Lt.Data
9dfca3fb7c
Merge branch 'comfyanonymous:master' into feature/blockweights
2023-06-15 09:05:22 +09:00
comfyanonymous
6b774589a5
Set model to fp16 before loading the state dict to lower ram bump.
2023-06-14 12:48:02 -04:00
comfyanonymous
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
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
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
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
23332731bd
Merge branch 'comfyanonymous:master' into feature/blockweights
2023-06-04 00:42:47 +09:00
comfyanonymous
700491d81a
Implement global average pooling for controlnet.
2023-06-03 01:49:03 -04:00
comfyanonymous
03da8a3426
This is useless for inference.
2023-05-31 13:03:24 -04:00
comfyanonymous
eb448dd8e1
Auto load model in lowvram if not enough memory.
2023-05-30 12:36:41 -04:00
comfyanonymous
a532888846
Support VAEs in diffusers format.
2023-05-28 02:02:09 -04:00
BlenderNeko
19c014f429
comment out annoying print statement
2023-05-12 23:57:40 +02:00
BlenderNeko
d9e088ddfd
minor changes for tiled sampler
2023-05-12 23:49:09 +02:00
Dr.Lt.Data
8895cbe7b2
Merge branch 'comfyanonymous:master' into feature/blockweights
2023-05-05 17:19:22 +09:00
comfyanonymous
bae4fb4a9d
Fix imports.
2023-05-04 18:10:29 -04:00
comfyanonymous
fcf513e0b6
Refactor.
2023-05-03 17:48:35 -04:00
pythongosssss
5eeecf3fd5
remove unused import
2023-05-03 18:21:23 +01:00
pythongosssss
8912623ea9
use comfy progress bar
2023-05-03 18:19:22 +01:00
pythongosssss
fdf57325f4
Merge remote-tracking branch 'origin/master' into tiled-progress
2023-05-03 17:33:42 +01:00
pythongosssss
27df74101e
reduce duplication
2023-05-03 17:33:19 +01:00
pythongosssss
06ad35b493
added progress to encode + upscale
2023-05-02 19:18:07 +01:00
ltdrdata
a0c63ad4c2
Merge branch 'comfyanonymous:master' into feature/blockweights
2023-05-02 11:28:56 +09:00
comfyanonymous
9c335a553f
LoKR support.
2023-05-01 18:18:23 -04:00
pythongosssss
c8c9926eeb
Add progress to vae decode tiled
2023-04-24 11:55:44 +01:00
comfyanonymous
5282f56434
Implement Linear hypernetworks.
...
Add a HypernetworkLoader node to use hypernetworks.
2023-04-23 12:35:25 -04:00
ltdrdata
a7178cc649
Merge branch 'comfyanonymous:master' into feature/blockweights
2023-04-20 09:04:27 +09:00
comfyanonymous
3696d1699a
Add support for GLIGEN textbox model.
2023-04-19 11:06:32 -04:00
ltdrdata
012873cdbf
Merge branch 'comfyanonymous:master' into feature/blockweights
2023-04-18 10:18:52 +09:00
comfyanonymous
884ea653c8
Add a way for nodes to set a custom CFG function.
2023-04-17 11:05:15 -04:00
ltdrdata
f2c0af4c90
Merge branch 'comfyanonymous:master' into feature/blockweights
2023-04-16 19:32:28 +09:00
comfyanonymous
73c3e11e83
Fix model_management import so it doesn't get executed twice.
2023-04-15 19:04:33 -04:00
comfyanonymous
81d1f00df3
Some refactoring: from_tokens -> encode_from_tokens
2023-04-15 18:46:58 -04:00
BlenderNeko
da115bd78d
ensure backwards compat with optional args
2023-04-14 21:16:55 +02:00
BlenderNeko
73175cf58c
split tokenizer from encoder
2023-04-13 22:06:50 +02:00
Lt.Dr.Data
d8147b6635
Merge branch 'Main' into feature/blockweights
2023-04-03 09:12:13 +09:00
comfyanonymous
809bcc8ceb
Add support for unCLIP SD2.x models.
...
See _for_testing/unclip in the UI for the new nodes.
unCLIPCheckpointLoader is used to load them.
unCLIPConditioning is used to add the image cond and takes as input a
CLIPVisionEncode output which has been moved to the conditioning section.
2023-04-01 23:19:15 -04:00
comfyanonymous
18a6c1db33
Add a TomePatchModel node to the _for_testing section.
...
Tome increases sampling speed at the expense of quality.
2023-03-31 17:19:58 -04:00
ltdrdata
f6ffb027c0
Merge branch 'comfyanonymous:master' into feature/blockweights
2023-03-29 18:53:55 +09:00
comfyanonymous
b2554bc4dd
Split VAE decode batches depending on free memory.
2023-03-29 02:24:37 -04:00
