298977887/ComfyUI
1
0
Fork 0
mirror of https://github.com/comfyanonymous/ComfyUI.git synced 2025-01-11 10:25:16 +00:00
Code Issues Packages Projects Releases Wiki Activity
2,362 Commits 2 Branches 32 Tags 1.1 GiB
a3dffc447a
Commit Graph

887 Commits

Author SHA1 Message Date
comfyanonymous
571ea8cdcc Fix SAG not working with cfg 1.0 2023-12-18 17:03:32 -05:00
comfyanonymous
8cf1daa108 Fix SDXL area composition sometimes not using the right pooled output. 2023-12-18 12:54:23 -05:00
comfyanonymous
2258f85159 Support stable zero 123 model. 
To use it use the ImageOnlyCheckpointLoader to load the checkpoint and
the new Stable_Zero123 node.
 2023-12-18 03:48:04 -05:00
comfyanonymous
2f9d6a97ec Add --deterministic option to make pytorch use deterministic algorithms. 2023-12-17 16:59:21 -05:00
comfyanonymous
e45d920ae3 Don't resize clip vision image when the size is already good. 2023-12-16 03:06:10 -05:00
comfyanonymous
13e6d5366e Switch clip vision to manual cast. 
Make it use the same dtype as the text encoder.
 2023-12-16 02:47:26 -05:00
comfyanonymous
719fa0866f Set clip vision model in eval mode so it works without inference mode. 2023-12-15 18:53:08 -05:00
Hari
574363a8a6 Implement Perp-Neg 2023-12-16 00:28:16 +05:30
comfyanonymous
a5056cfb1f Remove useless code. 2023-12-15 01:28:16 -05:00
comfyanonymous
329c571993 Improve code legibility. 2023-12-14 11:41:49 -05:00
comfyanonymous
6c5990f7db Fix cfg being calculated more than once if sampler_cfg_function. 2023-12-13 20:28:04 -05:00
comfyanonymous
ba04a87d10 Refactor and improve the sag node. 
Moved all the sag related code to comfy_extras/nodes_sag.py
 2023-12-13 16:11:26 -05:00
Rafie Walker
6761233e9d
Implement Self-Attention Guidance (#2201) 
* First SAG test

* need to put extra options on the model instead of patcher

* no errors and results seem not-broken

* Use @ashen-uncensored formula, which works better!!!

* Fix a crash when using weird resolutions. Remove an unnecessary UNet call

* Improve comments, optimize memory in blur routine

* SAG works with sampler_cfg_function
 2023-12-13 15:52:11 -05:00
comfyanonymous
b454a67bb9 Support segmind vega model. 2023-12-12 19:09:53 -05:00
comfyanonymous
824e4935f5 Add dtype parameter to VAE object. 2023-12-12 12:03:29 -05:00
comfyanonymous
32b7e7e769 Add manual cast to controlnet. 2023-12-12 11:32:42 -05:00
comfyanonymous
3152023fbc Use inference dtype for unet memory usage estimation. 2023-12-11 23:50:38 -05:00
comfyanonymous
77755ab8db Refactor comfy.ops 
comfy.ops -> comfy.ops.disable_weight_init

This should make it more clear what they actually do.

Some unused code has also been removed.
 2023-12-11 23:27:13 -05:00
comfyanonymous
b0aab1e4ea Add an option --fp16-unet to force using fp16 for the unet. 2023-12-11 18:36:29 -05:00
comfyanonymous
ba07cb748e Use faster manual cast for fp8 in unet. 2023-12-11 18:24:44 -05:00
comfyanonymous
57926635e8 Switch text encoder to manual cast. 
Use fp16 text encoder weights for CPU inference to lower memory usage.
 2023-12-10 23:00:54 -05:00
comfyanonymous
340177e6e8 Disable non blocking on mps. 2023-12-10 01:30:35 -05:00
comfyanonymous
614b7e731f Implement GLora. 2023-12-09 18:15:26 -05:00
comfyanonymous
cb63e230b4 Make lora code a bit cleaner. 2023-12-09 14:15:09 -05:00
comfyanonymous
174eba8e95 Use own clip vision model implementation. 2023-12-09 11:56:31 -05:00
comfyanonymous
97015b6b38 Cleanup. 2023-12-08 16:02:08 -05:00
comfyanonymous
a4ec54a40d Add linear_start and linear_end to model_config.sampling_settings 2023-12-08 02:49:30 -05:00
comfyanonymous
9ac0b487ac Make --gpu-only put intermediate values in GPU memory instead of cpu. 2023-12-08 02:35:45 -05:00
comfyanonymous
efb704c758 Support attention masking in CLIP implementation. 2023-12-07 02:51:02 -05:00
comfyanonymous
fbdb14d4c4 Cleaner CLIP text encoder implementation. 
Use a simple CLIP model implementation instead of the one from
transformers.

This will allow some interesting things that would too hackish to implement
using the transformers implementation.
 2023-12-06 23:50:03 -05:00
comfyanonymous
2db86b4676 Slightly faster lora applying. 2023-12-06 05:13:14 -05:00
comfyanonymous
1bbd65ab30 Missed this one. 2023-12-05 12:48:41 -05:00
comfyanonymous
9b655d4fd7 Fix memory issue with control loras. 2023-12-04 21:55:19 -05:00
comfyanonymous
26b1c0a771 Fix control lora on fp8. 2023-12-04 13:47:41 -05:00
comfyanonymous
be3468ddd5 Less useless downcasting. 2023-12-04 12:53:46 -05:00
comfyanonymous
ca82ade765 Use .itemsize to get dtype size for fp8. 2023-12-04 11:52:06 -05:00
comfyanonymous
31b0f6f3d8 UNET weights can now be stored in fp8. 
--fp8_e4m3fn-unet and --fp8_e5m2-unet are the two different formats
supported by pytorch.
 2023-12-04 11:10:00 -05:00
comfyanonymous
af365e4dd1 All the unet ops with weights are now handled by comfy.ops 2023-12-04 03:12:18 -05:00
comfyanonymous
61a123a1e0 A different way of handling multiple images passed to SVD. 
Previously when a list of 3 images [0, 1, 2] was used for a 6 frame video
they were concated like this:
[0, 1, 2, 0, 1, 2]

now they are concated like this:
[0, 0, 1, 1, 2, 2]
 2023-12-03 03:31:47 -05:00
comfyanonymous
c97be4db91 Support SD2.1 turbo checkpoint. 2023-11-30 19:27:03 -05:00
comfyanonymous
983ebc5792 Use smart model management for VAE to decrease latency. 2023-11-28 04:58:51 -05:00
comfyanonymous
c45d1b9b67 Add a function to load a unet from a state dict. 2023-11-27 17:41:29 -05:00
comfyanonymous
f30b992b18 .sigma and .timestep now return tensors on the same device as the input. 2023-11-27 16:41:33 -05:00
comfyanonymous
13fdee6abf Try to free memory for both cond+uncond before inference. 2023-11-27 14:55:40 -05:00
comfyanonymous
be71bb5e13 Tweak memory inference calculations a bit. 2023-11-27 14:04:16 -05:00
comfyanonymous
39e75862b2 Fix regression from last commit. 2023-11-26 03:43:02 -05:00
comfyanonymous
50dc39d6ec Clean up the extra_options dict for the transformer patches. 
Now everything in transformer_options gets put in extra_options.
 2023-11-26 03:13:56 -05:00
comfyanonymous
5d6dfce548 Fix importing diffusers unets. 2023-11-24 20:35:29 -05:00
comfyanonymous
3e5ea74ad3 Make buggy xformers fall back on pytorch attention. 2023-11-24 03:55:35 -05:00
comfyanonymous
871cc20e13 Support SVD img2vid model. 2023-11-23 19:41:33 -05:00
comfyanonymous
410bf07771 Make VAE memory estimation take dtype into account. 2023-11-22 18:17:19 -05:00
comfyanonymous
32447f0c39 Add sampling_settings so models can specify specific sampling settings. 2023-11-22 17:24:00 -05:00
comfyanonymous
c3ae99a749 Allow controlling downscale and upscale methods in PatchModelAddDownscale. 2023-11-22 03:23:16 -05:00
comfyanonymous
72741105a6 Remove useless code. 2023-11-21 17:27:28 -05:00
comfyanonymous
6a491ebe27 Allow model config to preprocess the vae state dict on load. 2023-11-21 16:29:18 -05:00
comfyanonymous
cd4fc77d5f Add taesd and taesdxl to VAELoader node. 
They will show up if both the taesd_encoder and taesd_decoder or taesdxl
model files are present in the models/vae_approx directory.
 2023-11-21 12:54:19 -05:00
comfyanonymous
ce67dcbcda Make it easy for models to process the unet state dict on load. 2023-11-20 23:17:53 -05:00
comfyanonymous
d9d8702d8d percent_to_sigma now returns a float instead of a tensor. 2023-11-18 23:20:29 -05:00
comfyanonymous
0cf4e86939 Add some command line arguments to store text encoder weights in fp8. 
Pytorch supports two variants of fp8:
--fp8_e4m3fn-text-enc (the one that seems to give better results)
--fp8_e5m2-text-enc
 2023-11-17 02:56:59 -05:00
comfyanonymous
107e78b1cb Add support for loading SSD1B diffusers unet version. 
Improve diffusers model detection.
 2023-11-16 23:12:55 -05:00
comfyanonymous
7e3fe3ad28 Make deep shrink behave like it should. 2023-11-16 15:26:28 -05:00
comfyanonymous
9f00a18095 Fix potential issues. 2023-11-16 14:59:54 -05:00
comfyanonymous
7ea6bb038c Print warning when controlnet can't be applied instead of crashing. 2023-11-16 12:57:12 -05:00
comfyanonymous
dcec1047e6 Invert the start and end percentages in the code. 
This doesn't affect how percentages behave in the frontend but breaks
things if you relied on them in the backend.

percent_to_sigma goes from 0 to 1.0 instead of 1.0 to 0 for less confusion.

Make percent 0 return an extremely large sigma and percent 1.0 return a
zero one to fix imprecision.
 2023-11-16 04:23:44 -05:00
comfyanonymous
57eea0efbb heunpp2 sampler. 2023-11-14 23:50:55 -05:00
comfyanonymous
728613bb3e Fix last pr. 2023-11-14 14:41:31 -05:00
comfyanonymous
ec3d0ab432 Merge branch 'master' of https://github.com/Jannchie/ComfyUI 2023-11-14 14:38:07 -05:00
comfyanonymous
c962884a5c Make bislerp work on GPU. 2023-11-14 11:38:36 -05:00
comfyanonymous
420beeeb05 Clean up and refactor sampler code. 
This should make it much easier to write custom nodes with kdiffusion type
samplers.
 2023-11-14 00:39:34 -05:00
Jianqi Pan
f2e49b1d57 fix: adaptation to older versions of pytroch 2023-11-14 14:32:05 +09:00
comfyanonymous
94cc718e9c Add a way to add patches to the input block. 2023-11-14 00:08:12 -05:00
comfyanonymous
7339479b10 Disable xformers when it can't load properly. 2023-11-13 12:31:10 -05:00
comfyanonymous
4781819a85 Make memory estimation aware of model dtype. 2023-11-12 04:28:26 -05:00
comfyanonymous
dd4ba68b6e Allow different models to estimate memory usage differently. 2023-11-12 04:03:52 -05:00
comfyanonymous
2c9dba8dc0 sampling_function now has the model object as the argument. 2023-11-12 03:45:10 -05:00
comfyanonymous
8d80584f6a Remove useless argument from uni_pc sampler. 2023-11-12 01:25:33 -05:00
comfyanonymous
248aa3e563 Fix bug. 2023-11-11 12:20:16 -05:00
comfyanonymous
4a8a839b40 Add option to use in place weight updating in ModelPatcher. 2023-11-11 01:11:12 -05:00
comfyanonymous
412d3ff57d Refactor. 2023-11-11 01:11:06 -05:00
comfyanonymous
58d5d71a93 Working RescaleCFG node. 
This was broken because of recent changes so I fixed it and moved it from
the experiments repo.
 2023-11-10 20:52:10 -05:00
comfyanonymous
3e0033ef30 Fix model merge bug. 
Unload models before getting weights for model patching.
 2023-11-10 03:19:05 -05:00
comfyanonymous
002aefa382 Support lcm models. 
Use the "lcm" sampler to sample them, you also have to use the
ModelSamplingDiscrete node to set them as lcm models to use them properly.
 2023-11-09 18:30:22 -05:00
comfyanonymous
ec12000136 Add support for full diff lora keys. 2023-11-08 22:05:31 -05:00
comfyanonymous
064d7583eb Add a CONDConstant for passing non tensor conds to unet. 2023-11-08 01:59:09 -05:00
comfyanonymous
794dd2064d Fix typo. 2023-11-07 23:41:55 -05:00
comfyanonymous
0a6fd49a3e Print leftover keys when using the UNETLoader. 2023-11-07 22:15:55 -05:00
comfyanonymous
fe40109b57 Fix issue with object patches not being copied with patcher. 2023-11-07 22:15:15 -05:00
comfyanonymous
a527d0c795 Code refactor. 2023-11-07 19:33:40 -05:00
comfyanonymous
2a23ba0b8c Fix unet ops not entirely on GPU. 2023-11-07 04:30:37 -05:00
comfyanonymous
844dbf97a7 Add: advanced->model->ModelSamplingDiscrete node. 
This allows changing the sampling parameters of the model (eps or vpred)
or set the model to use zsnr.
 2023-11-07 03:28:53 -05:00
comfyanonymous
656c0b5d90 CLIP code refactor and improvements. 
More generic clip model class that can be used on more types of text
encoders.

Don't apply weighting algorithm when weight is 1.0

Don't compute an empty token output when it's not needed.
 2023-11-06 14:17:41 -05:00
comfyanonymous
b3fcd64c6c Make SDTokenizer class work with more types of tokenizers. 2023-11-06 01:09:18 -05:00
gameltb
7e455adc07 fix unet_wrapper_function name in ModelPatcher 2023-11-05 17:11:44 +08:00
comfyanonymous
1ffa8858e7 Move model sampling code to comfy/model_sampling.py 2023-11-04 01:32:23 -04:00
comfyanonymous
ae2acfc21b Don't convert Nan to zero. 
Converting Nan to zero is a bad idea because it makes it hard to tell when
something went wrong.
 2023-11-03 13:13:15 -04:00
comfyanonymous
d2e27b48f1 sampler_cfg_function now gets the noisy output as argument again. 
This should make things that use sampler_cfg_function behave like before.

Added an input argument for those that want the denoised output.

This means you can calculate the x0 prediction of the model by doing:
(input - cond) for example.
 2023-11-01 21:24:08 -04:00
comfyanonymous
2455aaed8a Allow model or clip to be None in load_lora_for_models. 2023-11-01 20:27:20 -04:00
comfyanonymous
ecb80abb58 Allow ModelSamplingDiscrete to be instantiated without a model config. 2023-11-01 19:13:03 -04:00
comfyanonymous
e73ec8c4da Not used anymore. 2023-11-01 00:01:30 -04:00
comfyanonymous
111f1b5255 Fix some issues with sampling precision. 2023-10-31 23:49:29 -04:00
comfyanonymous
7c0f255de1 Clean up percent start/end and make controlnets work with sigmas. 2023-10-31 22:14:32 -04:00
comfyanonymous
a268a574fa Remove a bunch of useless code. 
DDIM is the same as euler with a small difference in the inpaint code.
DDIM uses randn_like but I set a fixed seed instead.

I'm keeping it in because I'm sure if I remove it people are going to
complain.
 2023-10-31 18:11:29 -04:00
comfyanonymous
1777b54d02 Sampling code changes. 
apply_model in model_base now returns the denoised output.

This means that sampling_function now computes things on the denoised
output instead of the model output. This should make things more consistent
across current and future models.
 2023-10-31 17:33:43 -04:00
comfyanonymous
c837a173fa Fix some memory issues in sub quad attention. 2023-10-30 15:30:49 -04:00
comfyanonymous
125b03eead Fix some OOM issues with split attention. 2023-10-30 13:14:11 -04:00
comfyanonymous
a12cc05323 Add --max-upload-size argument, the default is 100MB. 2023-10-29 03:55:46 -04:00
comfyanonymous
2a134bfab9 Fix checkpoint loader with config. 2023-10-27 22:13:55 -04:00
comfyanonymous
e60ca6929a SD1 and SD2 clip and tokenizer code is now more similar to the SDXL one. 2023-10-27 15:54:04 -04:00
comfyanonymous
6ec3f12c6e Support SSD1B model and make it easier to support asymmetric unets. 2023-10-27 14:45:15 -04:00
comfyanonymous
434ce25ec0 Restrict loading embeddings from embedding folders. 2023-10-27 02:54:13 -04:00
comfyanonymous
723847f6b3 Faster clip image processing. 2023-10-26 01:53:01 -04:00
comfyanonymous
a373367b0c Fix some OOM issues with split and sub quad attention. 2023-10-25 20:17:28 -04:00
comfyanonymous
7fbb217d3a Fix uni_pc returning noisy image when steps <= 3 2023-10-25 16:08:30 -04:00
Jedrzej Kosinski
3783cb8bfd change 'c_adm' to 'y' in ControlNet.get_control 2023-10-25 08:24:32 -05:00
comfyanonymous
d1d2fea806 Pass extra conds directly to unet. 2023-10-25 00:07:53 -04:00
comfyanonymous
036f88c621 Refactor to make it easier to add custom conds to models. 2023-10-24 23:31:12 -04:00
comfyanonymous
3fce8881ca Sampling code refactor to make it easier to add more conds. 2023-10-24 03:38:41 -04:00
comfyanonymous
8594c8be4d Empty the cache when torch cache is more than 25% free mem. 2023-10-22 13:58:12 -04:00
comfyanonymous
8b65f5de54 attention_basic now works with hypertile. 2023-10-22 03:59:53 -04:00
comfyanonymous
e6bc42df46 Make sub_quad and split work with hypertile. 2023-10-22 03:51:29 -04:00
comfyanonymous
a0690f9df9 Fix t2i adapter issue. 2023-10-21 20:31:24 -04:00
comfyanonymous
9906e3efe3 Make xformers work with hypertile. 2023-10-21 13:23:03 -04:00
comfyanonymous
4185324a1d Fix uni_pc sampler math. This changes the images this sampler produces. 2023-10-20 04:16:53 -04:00
comfyanonymous
e6962120c6 Make sure cond_concat is on the right device. 2023-10-19 01:14:25 -04:00
comfyanonymous
45c972aba8 Refactor cond_concat into conditioning. 2023-10-18 20:36:58 -04:00
comfyanonymous
430a8334c5 Fix some potential issues. 2023-10-18 19:48:36 -04:00
comfyanonymous
782a24fce6 Refactor cond_concat into model object. 2023-10-18 16:48:37 -04:00
comfyanonymous
0d45a565da Fix memory issue related to control loras. 
The cleanup function was not getting called.
 2023-10-18 02:43:01 -04:00
comfyanonymous
d44a2de49f Make VAE code closer to sgm. 2023-10-17 15:18:51 -04:00
comfyanonymous
23680a9155 Refactor the attention stuff in the VAE. 2023-10-17 03:19:29 -04:00
comfyanonymous
c8013f73e5 Add some Quadro cards to the list of cards with broken fp16. 2023-10-16 16:48:46 -04:00
comfyanonymous
bb064c9796 Add a separate optimized_attention_masked function. 2023-10-16 02:31:24 -04:00
comfyanonymous
fd4c5f07e7 Add a --bf16-unet to test running the unet in bf16. 2023-10-13 14:51:10 -04:00
comfyanonymous
9a55dadb4c Refactor code so model can be a dtype other than fp32 or fp16. 2023-10-13 14:41:17 -04:00
comfyanonymous
88733c997f pytorch_attention_enabled can now return True when xformers is enabled. 2023-10-11 21:30:57 -04:00
comfyanonymous
20d3852aa1 Pull some small changes from the other repo. 2023-10-11 20:38:48 -04:00
comfyanonymous
ac7d8cfa87 Allow attn_mask in attention_pytorch. 2023-10-11 20:38:48 -04:00
comfyanonymous
1a4bd9e9a6 Refactor the attention functions. 
There's no reason for the whole CrossAttention object to be repeated when
only the operation in the middle changes.
 2023-10-11 20:38:48 -04:00
comfyanonymous
8cc75c64ff Let unet wrapper functions have .to attributes. 2023-10-11 01:34:38 -04:00
comfyanonymous
5e885bd9c8 Cleanup. 2023-10-10 21:46:53 -04:00
comfyanonymous
851bb87ca9 Merge branch 'taesd_safetensors' of https://github.com/mochiya98/ComfyUI 2023-10-10 21:42:35 -04:00
Yukimasa Funaoka
9eb621c95a
Supports TAESD models in safetensors format 2023-10-10 13:21:44 +09:00
comfyanonymous
d1a0abd40b Merge branch 'input-directory' of https://github.com/jn-jairo/ComfyUI 2023-10-09 01:53:29 -04:00
comfyanonymous
72188dffc3 load_checkpoint_guess_config can now optionally output the model. 2023-10-06 13:48:18 -04:00
Jairo Correa
63e5fd1790 Option to input directory 2023-10-04 19:45:15 -03:00
City
9bfec2bdbf Fix quality loss due to low precision 2023-10-04 15:40:59 +02:00
badayvedat
0f17993d05 fix: typo in extra sampler 2023-09-29 06:09:59 +03:00
comfyanonymous
66756de100 Add SamplerDPMPP_2M_SDE node. 2023-09-28 21:56:23 -04:00
comfyanonymous
71713888c4 Print missing VAE keys. 2023-09-28 00:54:57 -04:00
comfyanonymous
d234ca558a Add missing samplers to KSamplerSelect. 2023-09-28 00:17:03 -04:00
comfyanonymous
1adcc4c3a2 Add a SamplerCustom Node. 
This node takes a list of sigmas and a sampler object as input.

This lets people easily implement custom schedulers and samplers as nodes.

More nodes will be added to it in the future.
 2023-09-27 22:21:18 -04:00
comfyanonymous
bf3fc2f1b7 Refactor sampling related code. 2023-09-27 16:45:22 -04:00
comfyanonymous
fff491b032 Model patches can now know which batch is positive and negative. 2023-09-27 12:04:07 -04:00
comfyanonymous
1d6dd83184 Scheduler code refactor. 2023-09-26 17:07:07 -04:00
comfyanonymous
446caf711c Sampling code refactor. 2023-09-26 13:45:15 -04:00
comfyanonymous
76cdc809bf Support more controlnet models. 2023-09-23 18:47:46 -04:00
comfyanonymous
ae87543653 Merge branch 'cast_intel' of https://github.com/simonlui/ComfyUI 2023-09-23 00:57:17 -04:00
Simon Lui
eec449ca8e Allow Intel GPUs to LoRA cast on GPU since it supports BF16 natively. 2023-09-22 21:11:27 -07:00
comfyanonymous
afa2399f79 Add a way to set output block patches to modify the h and hsp. 2023-09-22 20:26:47 -04:00
comfyanonymous
492db2de8d Allow having a different pooled output for each image in a batch. 2023-09-21 01:14:42 -04:00
comfyanonymous
1cdfb3dba4 Only do the cast on the device if the device supports it. 2023-09-20 17:52:41 -04:00
comfyanonymous
7c9a92f552 Don't depend on torchvision. 2023-09-19 13:12:47 -04:00
MoonRide303
2b6b178173 Added support for lanczos scaling 2023-09-19 10:40:38 +02:00
comfyanonymous
b92bf8196e Do lora cast on GPU instead of CPU for higher performance. 2023-09-18 23:04:49 -04:00
comfyanonymous
321c5fa295 Enable pytorch attention by default on xpu. 2023-09-17 04:09:19 -04:00
comfyanonymous
61b1f67734 Support models without previews. 2023-09-16 12:59:54 -04:00
comfyanonymous
43d4935a1d Add cond_or_uncond array to transformer_options so hooks can check what is 
cond and what is uncond.
 2023-09-15 22:21:14 -04:00
comfyanonymous
415abb275f Add DDPM sampler. 2023-09-15 19:22:47 -04:00
comfyanonymous
94e4fe39d8 This isn't used anywhere. 2023-09-15 12:03:03 -04:00
comfyanonymous
44361f6344 Support for text encoder models that need attention_mask. 2023-09-15 02:02:05 -04:00
comfyanonymous
0d8f376446 Set last layer on SD2.x models uses the proper indexes now. 
Before I had made the last layer the penultimate layer because some
checkpoints don't have them but it's not consistent with the others models.

TLDR: for SD2.x models only: CLIPSetLastLayer -1 is now -2.
 2023-09-14 20:28:22 -04:00
comfyanonymous
0966d3ce82 Don't run text encoders on xpu because there are issues. 2023-09-14 12:16:07 -04:00
comfyanonymous
3039b08eb1 Only parse command line args when main.py is called. 2023-09-13 11:38:20 -04:00
comfyanonymous
ed58730658 Don't leave very large hidden states in the clip vision output. 2023-09-12 15:09:10 -04:00
comfyanonymous
fb3b728203 Fix issue where autocast fp32 CLIP gave different results from regular. 2023-09-11 21:49:56 -04:00
comfyanonymous
7d401ed1d0 Add ldm format support to UNETLoader. 2023-09-11 16:36:50 -04:00
comfyanonymous
e85be36bd2 Add a penultimate_hidden_states to the clip vision output. 2023-09-08 14:06:58 -04:00
comfyanonymous
1e6b67101c Support diffusers format t2i adapters. 2023-09-08 11:36:51 -04:00
comfyanonymous
326577d04c Allow cancelling of everything with a progress bar. 2023-09-07 23:37:03 -04:00
comfyanonymous
f88f7f413a Add a ConditioningSetAreaPercentage node. 2023-09-06 03:28:27 -04:00
comfyanonymous
1938f5c5fe Add a force argument to soft_empty_cache to force a cache empty. 2023-09-04 00:58:18 -04:00
comfyanonymous
7746bdf7b0 Merge branch 'generalize_fixes' of https://github.com/simonlui/ComfyUI 2023-09-04 00:43:11 -04:00
Simon Lui
2da73b7073 Revert changes in comfy/ldm/modules/diffusionmodules/util.py, which is unused. 2023-09-02 20:07:52 -07:00
comfyanonymous
a74c5dbf37 Move some functions to utils.py 2023-09-02 22:33:37 -04:00
Simon Lui
4a0c4ce4ef Some fixes to generalize CUDA specific functionality to Intel or other GPUs. 2023-09-02 18:22:10 -07:00
comfyanonymous
77a176f9e0 Use common function to reshape batch to. 2023-09-02 03:42:49 -04:00
comfyanonymous
7931ff0fd9 Support SDXL inpaint models. 2023-09-01 15:22:52 -04:00
comfyanonymous
0e3b641172 Remove xformers related print. 2023-09-01 02:12:03 -04:00
comfyanonymous
5c363a9d86 Fix controlnet bug. 2023-09-01 02:01:08 -04:00
comfyanonymous
cfe1c54de8 Fix controlnet issue. 2023-08-31 15:16:58 -04:00
comfyanonymous
1c012d69af It doesn't make sense for c_crossattn and c_concat to be lists. 2023-08-31 13:25:00 -04:00
comfyanonymous
7e941f9f24 Clean up DiffusersLoader node. 2023-08-30 12:57:07 -04:00
Simon Lui
18617967e5
Fix error message in model_patcher.py 
Found while tinkering.
 2023-08-30 00:25:04 -07:00
comfyanonymous
fe4c07400c Fix "Load Checkpoint with config" node. 2023-08-29 23:58:32 -04:00
comfyanonymous
f2f5e5dcbb Support SDXL t2i adapters with 3 channel input. 2023-08-29 16:44:57 -04:00
comfyanonymous
15adc3699f Move beta_schedule to model_config and allow disabling unet creation. 2023-08-29 14:22:53 -04:00
comfyanonymous
bed116a1f9 Remove optimization that caused border. 2023-08-29 11:21:36 -04:00
comfyanonymous
65cae62c71 No need to check filename extensions to detect shuffle controlnet. 2023-08-28 16:49:06 -04:00
comfyanonymous
4e89b2c25a Put clip vision outputs on the CPU. 2023-08-28 16:26:11 -04:00
comfyanonymous
a094b45c93 Load clipvision model to GPU for faster performance. 2023-08-28 15:29:27 -04:00
comfyanonymous
1300a1bb4c Text encoder should initially load on the offload_device not the regular. 2023-08-28 15:08:45 -04:00
comfyanonymous
f92074b84f Move ModelPatcher to model_patcher.py 2023-08-28 14:51:31 -04:00
comfyanonymous
4798cf5a62 Implement loras with norm keys. 2023-08-28 11:20:06 -04:00
comfyanonymous
b8c7c770d3 Enable bf16-vae by default on ampere and up. 2023-08-27 23:06:19 -04:00
comfyanonymous
1c794a2161 Fallback to slice attention if xformers doesn't support the operation. 2023-08-27 22:24:42 -04:00
comfyanonymous
d935ba50c4 Make --bf16-vae work on torch 2.0 2023-08-27 21:33:53 -04:00
comfyanonymous
a57b0c797b Fix lowvram model merging. 2023-08-26 11:52:07 -04:00
comfyanonymous
f72780a7e3 The new smart memory management makes this unnecessary. 2023-08-25 18:02:15 -04:00
comfyanonymous
c77f02e1c6 Move controlnet code to comfy/controlnet.py 2023-08-25 17:33:04 -04:00
comfyanonymous
15a7716fa6 Move lora code to comfy/lora.py 2023-08-25 17:11:51 -04:00
comfyanonymous
ec96f6d03a Move text_projection to base clip model. 2023-08-24 23:43:48 -04:00
comfyanonymous
30eb92c3cb Code cleanups. 2023-08-24 19:39:18 -04:00
comfyanonymous
51dde87e97 Try to free enough vram for control lora inference. 2023-08-24 17:20:54 -04:00
comfyanonymous
e3d0a9a490 Fix potential issue with text projection matrix multiplication. 2023-08-24 00:54:16 -04:00
comfyanonymous
cc44ade79e Always shift text encoder to GPU when the device supports fp16. 2023-08-23 21:45:00 -04:00
comfyanonymous
a6ef08a46a Even with forced fp16 the cpu device should never use it. 2023-08-23 21:38:28 -04:00
comfyanonymous
00c0b2c507 Initialize text encoder to target dtype. 2023-08-23 21:01:15 -04:00
comfyanonymous
f081017c1a Save memory by storing text encoder weights in fp16 in most situations. 
Do inference in fp32 to make sure quality stays the exact same.
 2023-08-23 01:08:51 -04:00
comfyanonymous
afcb9cb1df All resolutions now work with t2i adapter for SDXL. 2023-08-22 16:23:54 -04:00
comfyanonymous
85fde89d7f T2I adapter SDXL. 2023-08-22 14:40:43 -04:00
comfyanonymous
cf5ae46928 Controlnet/t2iadapter cleanup. 2023-08-22 01:06:26 -04:00
comfyanonymous
763b0cf024 Fix control lora not working in fp32. 2023-08-21 20:38:31 -04:00
comfyanonymous
199d73364a Fix ControlLora on lowvram. 2023-08-21 00:54:04 -04:00
comfyanonymous
d08e53de2e Remove autocast from controlnet code. 2023-08-20 21:47:32 -04:00
comfyanonymous
0d7b0a4dc7 Small cleanups. 2023-08-20 14:56:47 -04:00
Simon Lui
9225465975 Further tuning and fix mem_free_total. 2023-08-20 14:19:53 -04:00
Simon Lui
2c096e4260 Add ipex optimize and other enhancements for Intel GPUs based on recent memory changes. 2023-08-20 14:19:51 -04:00
comfyanonymous
e9469e732d --disable-smart-memory now disables loading model directly to vram. 2023-08-20 04:00:53 -04:00
comfyanonymous
c9b562aed1 Free more memory before VAE encode/decode. 2023-08-19 12:13:13 -04:00
comfyanonymous
b80c3276dc Fix issue with gligen. 2023-08-18 16:32:23 -04:00
comfyanonymous
d6e4b342e6 Support for Control Loras. 
Control loras are controlnets where some of the weights are stored in
"lora" format: an up and a down low rank matrice that when multiplied
together and added to the unet weight give the controlnet weight.

This allows a much smaller memory footprint depending on the rank of the
matrices.

These controlnets are used just like regular ones.
 2023-08-18 11:59:51 -04:00
comfyanonymous
39ac856a33 ReVision support: unclip nodes can now be used with SDXL. 2023-08-18 11:59:36 -04:00
comfyanonymous
76d53c4622 Add support for clip g vision model to CLIPVisionLoader. 2023-08-18 11:13:29 -04:00
Alexopus
e59fe0537a
Fix referenced before assignment 
For https://github.com/BlenderNeko/ComfyUI_TiledKSampler/issues/13
 2023-08-17 22:30:07 +02:00
comfyanonymous
be9c5e25bc Fix issue with not freeing enough memory when sampling. 2023-08-17 15:59:56 -04:00
comfyanonymous
ac0758a1a4 Fix bug with lowvram and controlnet advanced node. 2023-08-17 13:38:51 -04:00
comfyanonymous
c28db1f315 Fix potential issues with patching models when saving checkpoints. 2023-08-17 11:07:08 -04:00
comfyanonymous
3aee33b54e Add --disable-smart-memory for those that want the old behaviour. 2023-08-17 03:12:37 -04:00
comfyanonymous
2be2742711 Fix issue with regular torch version. 2023-08-17 01:58:54 -04:00
comfyanonymous
89a0767abf Smarter memory management. 
Try to keep models on the vram when possible.

Better lowvram mode for controlnets.
 2023-08-17 01:06:34 -04:00
comfyanonymous
2c97c30256 Support small diffusers controlnet so both types are now supported. 2023-08-16 12:45:56 -04:00
comfyanonymous
53f326a3d8 Support diffusers mini controlnets. 2023-08-16 12:28:01 -04:00
comfyanonymous
58f0c616ed Fix clip vision issue with old transformers versions. 2023-08-16 11:36:22 -04:00
comfyanonymous
ae270f79bc Fix potential issue with batch size and clip vision. 2023-08-16 11:05:11 -04:00
comfyanonymous
a2ce9655ca Refactor unclip code. 2023-08-14 23:48:47 -04:00
comfyanonymous
9cc12c833d CLIPVisionEncode can now encode multiple images. 2023-08-14 16:54:05 -04:00
comfyanonymous
0cb6dac943 Remove 3m from PR #1213 because of some small issues. 2023-08-14 00:48:45 -04:00
comfyanonymous
e244b2df83 Add sgm_uniform scheduler that acts like the default one in sgm. 2023-08-14 00:29:03 -04:00
comfyanonymous
58c7da3665 Gpu variant of dpmpp_3m_sde. Note: use 3m with exponential or karras. 2023-08-14 00:28:50 -04:00
comfyanonymous
ba319a34e4 Merge branch 'dpmpp3m' of https://github.com/FizzleDorf/ComfyUI 2023-08-14 00:23:15 -04:00
FizzleDorf
3cfad03a68 dpmpp 3m + dpmpp 3m sde added 2023-08-13 22:29:04 -04:00
comfyanonymous
585a062910 Print unet config when model isn't detected. 2023-08-13 01:39:48 -04:00
comfyanonymous
c8a23ce9e8 Support for yet another lora type based on diffusers. 2023-08-11 13:04:21 -04:00
comfyanonymous
2bc12d3d22 Add --temp-directory argument to set temp directory. 2023-08-11 05:13:03 -04:00
comfyanonymous
c20583286f Support diffuser text encoder loras. 2023-08-10 20:28:28 -04:00
comfyanonymous
cf10c5592c Disable calculating uncond when CFG is 1.0 2023-08-09 20:55:03 -04:00
comfyanonymous
1f0f4cc0bd Add argument to disable auto launching the browser. 2023-08-07 02:25:12 -04:00
comfyanonymous
d8e58f0a7e Detect hint_channels from controlnet. 2023-08-06 14:08:59 -04:00
comfyanonymous
c5d7593ccf Support loras in diffusers format. 2023-08-05 01:40:24 -04:00
comfyanonymous
1ce0d8ad68 Add CMP 30HX card to the nvidia_16_series list. 2023-08-04 12:08:45 -04:00
comfyanonymous
c99d8002f8 Make sure the pooled output stays at the EOS token with added embeddings. 2023-08-03 20:27:50 -04:00
comfyanonymous
4a77fcd6ab Only shift text encoder to vram when CPU cores are under 8. 2023-07-31 00:08:54 -04:00
comfyanonymous
3cd31d0e24 Lower CPU thread check for running the text encoder on the CPU vs GPU. 2023-07-30 17:18:24 -04:00
comfyanonymous
2b13939044 Remove some useless code. 2023-07-30 14:13:33 -04:00
comfyanonymous
95d796fc85 Faster VAE loading. 2023-07-29 16:28:30 -04:00
comfyanonymous
4b957a0010 Initialize the unet directly on the target device. 2023-07-29 14:51:56 -04:00
comfyanonymous
c910b4a01c Remove unused code and torchdiffeq dependency. 2023-07-28 21:32:27 -04:00
comfyanonymous
1141029a4a Add --disable-metadata argument to disable saving metadata in files. 2023-07-28 12:31:41 -04:00
comfyanonymous
fbf5c51c1c Merge branch 'fix_batch_timesteps' of https://github.com/asagi4/ComfyUI 2023-07-27 16:13:48 -04:00
comfyanonymous
68be24eead Remove some prints. 2023-07-27 16:12:43 -04:00
asagi4
1ea4d84691 Fix timestep ranges when batch_size > 1 2023-07-27 21:14:09 +03:00
comfyanonymous
5379051d16 Fix diffusers VAE loading. 2023-07-26 18:26:39 -04:00
comfyanonymous
727588d076 Fix some new loras. 2023-07-25 16:39:15 -04:00
comfyanonymous
4f9b6f39d1 Fix potential issue with Save Checkpoint. 2023-07-25 00:45:20 -04:00
comfyanonymous
5f75d784a1 Start is now 0.0 and end is now 1.0 for the timestep ranges. 2023-07-24 18:38:17 -04:00
comfyanonymous
7ff14b62f8 ControlNetApplyAdvanced can now define when controlnet gets applied. 2023-07-24 17:50:49 -04:00
comfyanonymous
d191c4f9ed Add a ControlNetApplyAdvanced node. 
The controlnet can be applied to the positive or negative prompt only by
connecting it correctly.
 2023-07-24 13:35:20 -04:00
comfyanonymous
0240946ecf Add a way to set which range of timesteps the cond gets applied to. 2023-07-24 09:25:02 -04:00
comfyanonymous
22f29d66ca Try to fix memory issue with lora. 2023-07-22 21:38:56 -04:00
comfyanonymous
67be7eb81d Nodes can now patch the unet function. 2023-07-22 17:01:12 -04:00
comfyanonymous
12a6e93171 Del the right object when applying lora. 2023-07-22 11:25:49 -04:00
comfyanonymous
78e7958d17 Support controlnet in diffusers format. 2023-07-21 22:58:16 -04:00
comfyanonymous
09386a3697 Fix issue with lora in some cases when combined with model merging. 2023-07-21 21:27:27 -04:00
comfyanonymous
58b2364f58 Properly support SDXL diffusers unet with UNETLoader node. 2023-07-21 14:38:56 -04:00
comfyanonymous
0115018695 Print errors and continue when lora weights are not compatible. 2023-07-20 19:56:22 -04:00
comfyanonymous
4760c29380 Merge branch 'fix-AttributeError-module-'torch'-has-no-attribute-'mps'' of https://github.com/KarryCharon/ComfyUI 2023-07-20 00:34:54 -04:00
comfyanonymous
0b284f650b Fix typo. 2023-07-19 10:20:32 -04:00
comfyanonymous
e032ca6138 Fix ddim issue with older torch versions. 2023-07-19 10:16:00 -04:00
comfyanonymous
18885f803a Add MX450 and MX550 to list of cards with broken fp16. 2023-07-19 03:08:30 -04:00
comfyanonymous
9ba440995a It's actually possible to torch.compile the unet now. 2023-07-18 21:36:35 -04:00
comfyanonymous
51d5477579 Add key to indicate checkpoint is v_prediction when saving. 2023-07-18 00:25:53 -04:00
comfyanonymous
ff6b047a74 Fix device print on old torch version. 2023-07-17 15:18:58 -04:00
comfyanonymous
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
comfyanonymous
55d0fca9fa --windows-standalone-build now enables --cuda-malloc 2023-07-17 14:10:36 -04:00
comfyanonymous
1679abd86d Add a command line argument to enable backend:cudaMallocAsync 2023-07-17 11:00:14 -04:00
comfyanonymous
3a150bad15 Only calculate randn in some samplers when it's actually being used. 2023-07-17 10:11:08 -04:00
comfyanonymous
ee8f8ee07f Fix regression with ddim and uni_pc when batch size > 1. 2023-07-17 09:35:19 -04:00
comfyanonymous
3ded1a3a04 Refactor of sampler code to deal more easily with different model types. 2023-07-17 01:22:12 -04:00
comfyanonymous
5f57362613 Lower lora ram usage when in normal vram mode. 2023-07-16 02:59:04 -04:00
comfyanonymous
490771b7f4 Speed up lora loading a bit. 2023-07-15 13:25:22 -04:00