ff6b047a74
Fix device print on old torch version.
2023-07-17 15:18:58 -04:00
9871a15cf9
Enable --cuda-malloc by default on torch 2.0 and up.
...
Add --disable-cuda-malloc to disable it.
2023-07-17 15:12:10 -04:00
55d0fca9fa
--windows-standalone-build now enables --cuda-malloc
2023-07-17 14:10:36 -04:00
1679abd86d
Add a command line argument to enable backend:cudaMallocAsync
2023-07-17 11:00:14 -04:00
3a150bad15
Only calculate randn in some samplers when it's actually being used.
2023-07-17 10:11:08 -04:00
ee8f8ee07f
Fix regression with ddim and uni_pc when batch size > 1.
2023-07-17 09:35:19 -04:00
3ded1a3a04
Refactor of sampler code to deal more easily with different model types.
2023-07-17 01:22:12 -04:00
5f57362613
Lower lora ram usage when in normal vram mode.
2023-07-16 02:59:04 -04:00
490771b7f4
Speed up lora loading a bit.
2023-07-15 13:25:22 -04:00
50b1180dde
Fix CLIPSetLastLayer not reverting when removed.
2023-07-15 01:41:21 -04:00
6fb084f39d
Reduce floating point rounding errors in loras.
2023-07-15 00:53:00 -04:00
91ed2815d5
Add a node to merge CLIP models.
2023-07-14 02:41:18 -04:00
b2f03164c7
Prevent the clip_g position_ids key from being saved in the checkpoint.
...
This is to make it match the official checkpoint.
2023-07-12 20:15:02 -04:00
46dc050c9f
Fix potential tensors being on different devices issues.
2023-07-12 19:29:27 -04:00
3e2309f149
fix mps miss import
2023-07-12 10:06:34 +08:00
606a537090
Support SDXL embedding format with 2 CLIP.
2023-07-10 10:34:59 -04:00
6ad0a6d7e2
Don't patch weights when multiplier is zero.
2023-07-09 17:46:56 -04:00
d5323d16e0
latent2rgb matrix for SDXL.
2023-07-09 13:59:09 -04:00
0ae81c03bb
Empty cache after model unloading for normal vram and lower.
2023-07-09 09:56:03 -04:00
d3f5998218
Support loading clip_g from diffusers in CLIP Loader nodes.
2023-07-09 09:33:53 -04:00
a9a4ba7574
Fix merging not working when model2 of model merge node was a merge.
2023-07-08 22:31:10 -04:00
bb5fbd29e9
Merge branch 'condmask-fix' of https://github.com/vmedea/ComfyUI
2023-07-07 01:52:25 -04:00
e7bee85df8
Add arguments to run the VAE in fp16 or bf16 for testing.
2023-07-06 23:23:46 -04:00
608fcc2591
Fix bug with weights when prompt is long.
2023-07-06 02:43:40 -04:00
ddc6f12ad5
Disable autocast in unet for increased speed.
2023-07-05 21:58:29 -04:00
603f02d613
Fix loras not working when loading checkpoint with config.
2023-07-05 19:42:24 -04:00
af7a49916b
Support loading unet files in diffusers format.
2023-07-05 17:38:59 -04:00
e57cba4c61
Add gpu variations of the sde samplers that are less deterministic
...
but faster.
2023-07-05 01:39:38 -04:00
f81b192944
Add logit scale parameter so it's present when saving the checkpoint.
2023-07-04 23:01:28 -04:00
acf95191ff
Properly support SDXL diffusers loras for unet.
2023-07-04 21:15:23 -04:00
c61a95f9f7
Fix size check for conditioning mask
...
The wrong dimensions were being checked, [1] and [2] are the image size.
not [2] and [3]. This results in an out-of-bounds error if one of them
actually matches.
2023-07-04 16:34:42 +02:00
8d694cc450
Fix issue with OSX.
2023-07-04 02:09:02 -04:00
c3e96e637d
Pass device to CLIP model.
2023-07-03 16:09:37 -04:00
5e6bc824aa
Allow passing custom path to clip-g and clip-h.
2023-07-03 15:45:04 -04:00
dc9d1f31c8
Improvements for OSX.
2023-07-03 00:08:30 -04:00
103c487a89
Cleanup.
2023-07-02 11:58:23 -04:00
2c4e0b49b7
Switch to fp16 on some cards when the model is too big.
2023-07-02 10:00:57 -04:00
6f3d9f52db
Add a --force-fp16 argument to force fp16 for testing.
2023-07-01 22:42:35 -04:00
1c1b0e7299
--gpu-only now keeps the VAE on the device.
2023-07-01 15:22:40 -04:00
ce35d8c659
Lower latency by batching some text encoder inputs.
2023-07-01 15:07:39 -04:00
3b6fe51c1d
Leave text_encoder on the CPU when it can handle it.
2023-07-01 14:38:51 -04:00
b6a60fa696
Try to keep text encoders loaded and patched to increase speed.
...
load_model_gpu() is now used with the text encoder models instead of just
the unet.
2023-07-01 13:28:07 -04:00
97ee230682
Make highvram and normalvram shift the text encoders to vram and back.
...
This is faster on big text encoder models than running it on the CPU.
2023-07-01 12:37:23 -04:00
5a9ddf94eb
LoraLoader node now caches the lora file between executions.
2023-06-29 23:40:51 -04:00
9920367d3c
Fix embeddings not working with --gpu-only
2023-06-29 20:43:06 -04:00
62db11683b
Move unet to device right after loading on highvram mode.
2023-06-29 20:43:06 -04:00
4376b125eb
Remove useless code.
2023-06-29 00:26:33 -04:00
89120f1fbe
This is unused but it should be 1280.
2023-06-28 18:04:23 -04:00
2c7c14de56
Support for SDXL text encoder lora.
2023-06-28 02:22:49 -04:00
fcef47f06e
Fix bug.
2023-06-28 00:38:07 -04:00
8248babd44
Use pytorch attention by default on nvidia when xformers isn't present.
...
Add a new argument --use-quad-cross-attention
2023-06-26 13:03:44 -04:00
9b93b920be
Add CheckpointSave node to save checkpoints.
...
The created checkpoints contain workflow metadata that can be loaded by
dragging them on top of the UI or loading them with the "Load" button.
Checkpoints will be saved in fp16 or fp32 depending on the format ComfyUI
is using for inference on your hardware. To force fp32 use: --force-fp32
Anything that patches the model weights like merging or loras will be
saved.
The output directory is currently set to: output/checkpoints but that might
change in the future.
2023-06-26 12:22:27 -04:00
b72a7a835a
Support loras based on the stability unet implementation.
2023-06-26 02:56:11 -04:00
c71a7e6b20
Fix ddim + inpainting not working.
2023-06-26 00:48:48 -04:00
4eab00e14b
Set the seed in the SDE samplers to make them more reproducible.
2023-06-25 03:04:57 -04:00
cef6aa62b2
Add support for TAESD decoder for SDXL.
2023-06-25 02:38:14 -04:00
20f579d91d
Add DualClipLoader to load clip models for SDXL.
...
Update LoadClip to load clip models for SDXL refiner.
2023-06-25 01:40:38 -04:00
b7933960bb
Fix CLIPLoader node.
2023-06-24 13:56:46 -04:00
78d8035f73
Fix bug with controlnet.
2023-06-24 11:02:38 -04:00
05676942b7
Add some more transformer hooks and move tomesd to comfy_extras.
...
Tomesd now uses q instead of x to decide which tokens to merge because
it seems to give better results.
2023-06-24 03:30:22 -04:00
fa28d7334b
Remove useless code.
2023-06-23 12:35:26 -04:00
8607c2d42d
Move latent scale factor from VAE to model.
2023-06-23 02:33:31 -04:00
30a3861946
Fix bug when yaml config has no clip params.
2023-06-23 01:12:59 -04:00
9e37f4c7d5
Fix error with ClipVision loader node.
2023-06-23 01:08:05 -04:00
9f83b098c9
Don't merge weights when shapes don't match and print a warning.
2023-06-22 19:08:31 -04:00
f87ec10a97
Support base SDXL and SDXL refiner models.
...
Large refactor of the model detection and loading code.
2023-06-22 13:03:50 -04:00
9fccf4aa03
Add original_shape parameter to transformer patch extra_options.
2023-06-21 13:22:01 -04:00
51581dbfa9
Fix last commits causing an issue with the text encoder lora.
2023-06-20 19:44:39 -04:00
8125b51a62
Keep a set of model_keys for faster add_patches.
2023-06-20 19:08:48 -04:00
45beebd33c
Add a type of model patch useful for model merging.
2023-06-20 17:34:11 -04:00
036a22077c
Fix k_diffusion math being off by a tiny bit during txt2img.
2023-06-19 15:28:54 -04:00
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
cd930d4e7f
pop clip vision keys after loading them.
2023-06-18 21:21:17 -04:00
c9e4a8c9e5
Not needed anymore.
2023-06-18 13:06:59 -04:00
fb4bf7f591
This is not needed anymore and causes issues with alphas_cumprod.
2023-06-18 03:18:25 -04:00
45be2e92c1
Fix DDIM v-prediction.
2023-06-17 20:48:21 -04:00
e6e50ab2dd
Fix an issue when alphas_comprod are half floats.
2023-06-16 17:16:51 -04:00
ae43f09ef7
All the unet weights should now be initialized with the right dtype.
2023-06-15 18:42:30 -04:00
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
7bf89ba923
Initialize more unet weights as the right dtype.
2023-06-15 15:00:10 -04:00
e21d9ad445
Initialize transformer unet block weights in right dtype at the start.
2023-06-15 14:29:26 -04:00
bb1f45d6e8
Properly disable weight initialization in clip models.
2023-06-14 20:13:08 -04:00
21f04fe632
Disable default weight values in unet conv2d for faster loading.
2023-06-14 19:46:08 -04:00
9d54066ebc
This isn't needed for inference.
2023-06-14 13:05:08 -04:00
fa2cca056c
Don't initialize CLIPVision weights to default values.
2023-06-14 12:57:02 -04:00
6b774589a5
Set model to fp16 before loading the state dict to lower ram bump.
2023-06-14 12:48:02 -04:00
0c7cad404c
Don't initialize clip weights to default values.
2023-06-14 12:47:36 -04:00
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
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
ff9b22d79e
Turn on safe load for a few models.
2023-06-13 10:12:03 -04:00
735ac4cf81
Remove pytorch_lightning dependency.
2023-06-13 10:11:33 -04:00
2b14041d4b
Remove useless code.
2023-06-13 02:40:58 -04:00
274dff3257
Remove more useless files.
2023-06-13 02:22:19 -04:00
f0a2b81cd0
Cleanup: Remove a bunch of useless files.
2023-06-13 02:19:08 -04:00
f8c5931053
Split the batch in VAEEncode if there's not enough memory.
2023-06-12 00:21:50 -04:00
c069fc0730
Auto switch to tiled VAE encode if regular one runs out of memory.
2023-06-11 23:25:39 -04:00
c64ca8c0b2
Refactor unCLIP noise augment out of samplers.py
2023-06-11 04:01:18 -04:00
de142eaad5
Simpler base model code.
2023-06-09 12:31:16 -04:00
23cf8ca7c5
Fix bug when embedding gets ignored because of mismatched size.
2023-06-08 23:48:14 -04:00
0e425603fb
Small refactor.
2023-06-06 13:23:01 -04:00
comfyanonymous
KarryCharon
mara