comfyanonymous
501f19eec6
Fix clip_skip no longer being loaded from yaml file.
2023-03-06 11:34:02 -05:00
comfyanonymous
afff30fc0a
Add --cpu to use the cpu for inference.
2023-03-06 10:50:50 -05:00
comfyanonymous
47acb3d73e
Implement support for t2i style model.
...
It needs the CLIPVision model so I added CLIPVisionLoader and CLIPVisionEncode.
Put the clip vision model in models/clip_vision
Put the t2i style model in models/style_models
StyleModelLoader to load it, StyleModelApply to apply it
ConditioningAppend to append the conditioning it outputs to a positive one.
2023-03-05 18:39:25 -05:00
comfyanonymous
cc8baf1080
Make VAE use common function to get free memory.
2023-03-05 14:20:07 -05:00
comfyanonymous
798c90e1c0
Fix pytorch 2.0 cross attention not working.
2023-03-05 14:14:54 -05:00
comfyanonymous
16130c7546
Add support for new colour T2I adapter model.
2023-03-03 19:13:07 -05:00
comfyanonymous
9d00235b41
Update T2I adapter code to latest.
2023-03-03 18:46:49 -05:00
comfyanonymous
ebfcf0a9c9
Fix issue.
2023-03-03 13:18:01 -05:00
comfyanonymous
4215206281
Add a node to set CLIP skip.
...
Use a more simple way to detect if the model is -v prediction.
2023-03-03 13:04:36 -05:00
comfyanonymous
fed315a76a
To be really simple CheckpointLoaderSimple should pick the right type.
2023-03-03 11:07:10 -05:00
comfyanonymous
94bb0375b0
New CheckpointLoaderSimple to load checkpoints without a config.
2023-03-03 03:37:35 -05:00
comfyanonymous
c1f5855ac1
Make some cross attention functions work on the CPU.
2023-03-03 03:27:33 -05:00
comfyanonymous
1a612e1c74
Add some pytorch scaled_dot_product_attention code for testing.
...
--use-pytorch-cross-attention to use it.
2023-03-02 17:01:20 -05:00
comfyanonymous
69cc75fbf8
Add a way to interrupt current processing in the backend.
2023-03-02 14:42:03 -05:00
comfyanonymous
9502ee45c3
Hopefully fix a strange issue with xformers + lowvram.
2023-02-28 13:48:52 -05:00
comfyanonymous
b31daadc03
Try to improve memory issues with del.
2023-02-28 12:27:43 -05:00
comfyanonymous
2c5f0ec681
Small adjustment.
2023-02-27 20:04:18 -05:00
comfyanonymous
86721d5158
Enable highvram automatically when vram >> ram
2023-02-27 19:57:39 -05:00
comfyanonymous
75fa162531
Remove sample_ from some sampler names.
...
Old workflows will still work.
2023-02-27 01:43:06 -05:00
comfyanonymous
9f4214e534
Preparing to add another function to load checkpoints.
2023-02-26 17:29:01 -05:00
comfyanonymous
3cd7d84b53
Fix uni_pc sampler not working with 1 or 2 steps.
2023-02-26 04:01:01 -05:00
comfyanonymous
dfb397e034
Fix multiple controlnets not working.
2023-02-25 22:12:22 -05:00
comfyanonymous
af3cc1b5fb
Fixed issue when batched image was used as a controlnet input.
2023-02-25 14:57:28 -05:00
comfyanonymous
d2da346b0b
Fix missing variable.
2023-02-25 12:19:03 -05:00
comfyanonymous
4e6b83a80a
Add a T2IAdapterLoader node to load T2I-Adapter models.
...
They are loaded as CONTROL_NET objects because they are similar.
2023-02-25 01:24:56 -05:00
comfyanonymous
fcb25d37db
Prepare for t2i adapter.
2023-02-24 23:36:17 -05:00
comfyanonymous
cf5a211efc
Remove some useless imports
2023-02-24 12:36:55 -05:00
comfyanonymous
87b00b37f6
Added an experimental VAEDecodeTiled.
...
This decodes the image with the VAE in tiles which should be faster and
use less vram.
It's in the _for_testing section so I might change/remove it or even
add the functionality to the regular VAEDecode node depending on how
well it performs which means don't depend too much on it.
2023-02-24 02:10:10 -05:00
comfyanonymous
62df8dd62a
Add a node to load diff controlnets.
2023-02-22 23:22:03 -05:00
comfyanonymous
f04dc2c2f4
Implement DDIM sampler.
2023-02-22 21:10:19 -05:00
comfyanonymous
2976c1ad28
Uni_PC: make max denoise behave more like other samplers.
...
On the KSamplers denoise of 1.0 is the same as txt2img but there was a
small difference on UniPC.
2023-02-22 02:21:06 -05:00
comfyanonymous
c9daec4c89
Remove prints that are useless when xformers is enabled.
2023-02-21 22:16:13 -05:00
comfyanonymous
a7328e4945
Add uni_pc bh2 variant.
2023-02-21 16:11:48 -05:00
comfyanonymous
d80af7ca30
ControlNetApply now stacks.
...
It can be used to apply multiple control nets at the same time.
2023-02-21 01:18:53 -05:00
comfyanonymous
00a9189e30
Support old pytorch.
2023-02-19 16:59:03 -05:00
comfyanonymous
137ae2606c
Support people putting commas after the embedding name in the prompt.
2023-02-19 02:50:48 -05:00
comfyanonymous
2326ff1263
Add: --highvram for when you want models to stay on the vram.
2023-02-17 21:27:02 -05:00
comfyanonymous
09f1d76ed8
Fix an OOM issue.
2023-02-17 16:21:01 -05:00
comfyanonymous
d66415c021
Low vram mode for controlnets.
2023-02-17 15:48:16 -05:00
comfyanonymous
220a72d36b
Use fp16 for fp16 control nets.
2023-02-17 15:31:38 -05:00
comfyanonymous
6135a21ee8
Add a way to control controlnet strength.
2023-02-16 18:08:01 -05:00
comfyanonymous
4efa67fa12
Add ControlNet support.
2023-02-16 10:38:08 -05:00
comfyanonymous
bc69fb5245
Use inpaint models the proper way by using VAEEncodeForInpaint.
2023-02-15 20:44:51 -05:00
comfyanonymous
cef2cc3cb0
Support for inpaint models.
2023-02-15 16:38:20 -05:00
comfyanonymous
07db00355f
Add masks to samplers code for inpainting.
2023-02-15 13:16:38 -05:00
comfyanonymous
e3451cea4f
uni_pc now works with KSamplerAdvanced return_with_leftover_noise.
2023-02-13 12:29:21 -05:00
comfyanonymous
f542f248f1
Show the right amount of steps in the progress bar for uni_pc.
...
The extra step doesn't actually call the unet so it doesn't belong in
the progress bar.
2023-02-11 14:59:42 -05:00
comfyanonymous
f10b8948c3
768-v support for uni_pc sampler.
2023-02-11 04:34:58 -05:00
comfyanonymous
ce0aeb109e
Remove print.
2023-02-11 03:41:40 -05:00
comfyanonymous
5489d5af04
Add uni_pc sampler to KSampler* nodes.
2023-02-11 03:34:09 -05:00
comfyanonymous
1a4edd19cd
Fix overflow issue with inplace softmax.
2023-02-10 11:47:41 -05:00
comfyanonymous
509c7dfc6d
Use real softmax in split op to fix issue with some images.
2023-02-10 03:13:49 -05:00
comfyanonymous
7e1e193f39
Automatically enable lowvram mode if vram is less than 4GB.
...
Use: --normalvram to disable it.
2023-02-10 00:47:56 -05:00
comfyanonymous
324273fff2
Fix embedding not working when on new line.
2023-02-09 14:12:02 -05:00
comfyanonymous
1f6a467e92
Update ldm dir with latest upstream stable diffusion changes.
2023-02-09 13:47:36 -05:00
comfyanonymous
773cdabfce
Same thing but for the other places where it's used.
2023-02-09 12:43:29 -05:00
comfyanonymous
df40d4f3bf
torch.cuda.OutOfMemoryError is not present on older pytorch versions.
2023-02-09 12:33:27 -05:00
comfyanonymous
e8c499ddd4
Split optimization for VAE attention block.
2023-02-08 22:04:20 -05:00
comfyanonymous
5b4e312749
Use inplace operations for less OOM issues.
2023-02-08 22:04:13 -05:00
comfyanonymous
3fd87cbd21
Slightly smarter batching behaviour.
...
Try to keep batch sizes more consistent which seems to improve things on
AMD GPUs.
2023-02-08 17:28:43 -05:00
comfyanonymous
bbdcf0b737
Use relative imports for k_diffusion.
2023-02-08 16:51:19 -05:00
comfyanonymous
708138c77d
Remove print.
2023-02-08 14:51:18 -05:00
comfyanonymous
047775615b
Lower the chances of an OOM.
2023-02-08 14:24:27 -05:00
comfyanonymous
853e96ada3
Increase it/s by batching together some stuff sent to unet.
2023-02-08 14:24:00 -05:00
comfyanonymous
c92633eaa2
Auto calculate amount of memory to use for --lowvram
2023-02-08 11:42:37 -05:00
comfyanonymous
534736b924
Add some low vram modes: --lowvram and --novram
2023-02-08 11:37:10 -05:00
comfyanonymous
a84cd0d1ad
Don't unload/reload model from CPU uselessly.
2023-02-08 03:40:43 -05:00
comfyanonymous
b1a7c9ebf6
Embeddings/textual inversion support for SD2.x
2023-02-05 15:49:03 -05:00
comfyanonymous
1de5aa6a59
Add a CLIPLoader node to load standalone clip weights.
...
Put them in models/clip
2023-02-05 15:20:18 -05:00
comfyanonymous
56d802e1f3
Use transformers CLIP instead of open_clip for SD2.x
...
This should make things a bit cleaner.
2023-02-05 14:36:28 -05:00
comfyanonymous
bf9ccffb17
Small fix for SD2.x loras.
2023-02-05 11:38:25 -05:00
comfyanonymous
678105fade
SD2.x CLIP support for Loras.
2023-02-05 01:54:09 -05:00
comfyanonymous
ef90e9c376
Add a LoraLoader node to apply loras to models and clip.
...
The models are modified in place before being used and unpatched after.
I think this is better than monkeypatching since it might make it easier
to use faster non pytorch unet inference in the future.
2023-02-03 02:46:24 -05:00
comfyanonymous
69df7eba94
Add KSamplerAdvanced node.
...
This node exposes more sampling options and makes it possible for example
to sample the first few steps on the latent image, do some operations on it
and then do the rest of the sampling steps. This can be achieved using the
start_at_step and end_at_step options.
2023-01-31 03:09:38 -05:00
comfyanonymous
1daccf3678
Run softmax in place if it OOMs.
2023-01-30 19:55:01 -05:00
comfyanonymous
f73e57d881
Add support for textual inversion embedding for SD1.x CLIP.
2023-01-29 18:46:44 -05:00
comfyanonymous
50db297cf6
Try to fix OOM issues with cards that have less vram than mine.
2023-01-29 00:50:46 -05:00
comfyanonymous
73f60740c8
Slightly cleaner code.
2023-01-28 02:14:22 -05:00
comfyanonymous
0108616b77
Fix issue with some models.
2023-01-28 01:38:42 -05:00
comfyanonymous
2973ff24c5
Round CLIP position ids to fix float issues in some checkpoints.
2023-01-28 00:19:33 -05:00
comfyanonymous
c4b02059d0
Add ConditioningSetArea node.
...
to apply conditioning/prompts only to a specific area of the image.
Add ConditioningCombine node.
so that multiple conditioning/prompts can be applied to the image at the
same time
2023-01-26 12:06:48 -05:00
comfyanonymous
acdc6f42e0
Fix loading some malformed checkpoints?
2023-01-25 15:20:55 -05:00
comfyanonymous
051f472e8f
Fix sub quadratic attention for SD2 and make it the default optimization.
2023-01-25 01:22:43 -05:00
comfyanonymous
220afe3310
Initial commit.
2023-01-16 22:37:14 -05:00
