andreas/ComfyUI
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
306 Commits 1 Branch 0 Tags
83f23f82b8a4ac041dd8262ee12951ac6826162f
Commit Graph
100 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
comfyanonymous 83f23f82b8 Add pytorch attention support to VAE. 2023-03-13 12:45:54 -04:00
comfyanonymous a256a2abde --disable-xformers should not even try to import xformers. 2023-03-13 11:36:48 -04:00
comfyanonymous ebfa749b7b Readme improvement. 2023-03-13 10:49:03 -04:00
comfyanonymous 010bbb9c5a Readme style adjustments. 2023-03-13 10:44:29 -04:00
comfyanonymous 6fd8377429 Typo. 2023-03-13 10:43:07 -04:00
comfyanonymous dc24ad1554 Add download link of portable build to README. 2023-03-13 10:42:02 -04:00
comfyanonymous 17636d083f Probably safer to manually trigger builds instead of every push. 2023-03-13 02:54:30 -04:00
comfyanonymous f0d8fdc0d6 Add an automatic standalone windows release for nvidia and cpu. 2023-03-13 01:34:09 -04:00
comfyanonymous 0f3ba7482f Xformers is now properly disabled when --cpu used. 
Added --windows-standalone-build option, currently it only opens
makes the code open up comfyui in the browser.
 2023-03-12 15:44:16 -04:00
comfyanonymous 6d6758e9e4 Add WD VAE to colab. 2023-03-11 22:08:00 -05:00
comfyanonymous b64f5e6a27 Indicate in readme that upscale models are now supported. 2023-03-11 19:48:42 -05:00
comfyanonymous c8f1acc4eb Put image upscaling nodes in image/upscaling category. 2023-03-11 18:10:36 -05:00
comfyanonymous e33dc2b33b Add a VAEEncodeTiled node. 2023-03-11 15:28:15 -05:00
comfyanonymous 1de86851b1 Try to fix memory issue. 2023-03-11 15:15:13 -05:00
comfyanonymous 2b1fce2943 Make tiled_scale work for downscaling. 2023-03-11 14:58:55 -05:00
comfyanonymous 9db2e97b47 Tiled upscaling with the upscale models. 2023-03-11 14:04:13 -05:00
comfyanonymous 905857edd8 Take some code from chainner to implement ESRGAN and other upscale models. 2023-03-11 13:09:28 -05:00
comfyanonymous 8c4ccb55d1 Small refactor of custom node loading code. 2023-03-11 12:49:41 -05:00
comfyanonymous 1f717903bc Prevent potential int overflow in SaveImage 2023-03-11 12:48:28 -05:00
comfyanonymous 44294a446e Link to lora example. 2023-03-10 14:27:37 -05:00
comfyanonymous c759801a52 Update some links in colab notebook. 2023-03-10 11:01:33 -05:00
comfyanonymous 4e3ee3bd8b Notebook update to fix links. 2023-03-09 21:55:57 -05:00
comfyanonymous cd64111c83 Add locon support. 2023-03-09 21:41:24 -05:00
comfyanonymous 99eb777f5d Make the LoadImage node output the alpha as a mask. 2023-03-09 14:07:55 -05:00
comfyanonymous b94ed02aae Merge branch 'uploadimages' of https://github.com/pythongosssss/ComfyUI 2023-03-09 13:30:19 -05:00
comfyanonymous 9ce300ab59 I confirmed CPU only inference works fine on a pytorch without cuda. 2023-03-09 11:50:00 -05:00
comfyanonymous c70f0ac64b SD2.x controlnets now work. 2023-03-08 01:13:38 -05:00
comfyanonymous 5ea597710f Merge branch 'socketsession' of https://github.com/pythongosssss/ComfyUI 2023-03-07 23:05:52 -05:00
comfyanonymous 19415c3ace Relative imports to test something. 2023-03-07 11:00:35 -05:00
comfyanonymous 0a0c769d6d Try to fix import issue. 2023-03-06 14:41:42 -05:00
comfyanonymous 235ba852d9 Style. 2023-03-06 14:09:23 -05:00
comfyanonymous 25941aeef9 This isn't needed anymore. 2023-03-06 12:02:02 -05:00
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 799f510d0c Add some links to notebook for the t2i styles model. 2023-03-06 02:07:58 -05:00
comfyanonymous 8515d96328 It's more logical for the StyleModelApply to append it directly. 2023-03-06 01:48:18 -05:00
comfyanonymous 7ec1dd25a2 A tiny bit of reorganizing. 2023-03-06 01:30:17 -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 f9d09c266f Colab notebook update. 2023-03-05 03:05:58 -05:00
comfyanonymous a098dc965c Switch the default workflow to the CheckpointLoaderSimple node. 2023-03-05 03:00:28 -05:00
comfyanonymous c2fa2a18d2 Update readme with link to matrix space. 
Specify which way is the recommended way to run ComfyUI in colab.
 2023-03-04 08:46:39 -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 3ddff339f5 Add commented out command to install the preprocessor nodes to notebook. 2023-03-03 14:52:39 -05:00
comfyanonymous b9e3f52240 stop_at_clip_layer can be set in CLIPSetLastLayer so it can be removed 
from the CLIPLoader node.
 2023-03-03 14:27:55 -05:00
comfyanonymous ebfcf0a9c9 Fix issue. 2023-03-03 13:18:01 -05:00
comfyanonymous 8586515886 Move the CheckpointLoaderSimple to the right section. 2023-03-03 13:09:44 -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 c8ce599a8f Add a button to interrupt processing to the ui. 2023-03-02 15:24:51 -05:00
comfyanonymous 69cc75fbf8 Add a way to interrupt current processing in the backend. 2023-03-02 14:42:03 -05:00
comfyanonymous 1e2c4df972 Add a print to colab. 2023-03-01 10:53:18 -05:00
comfyanonymous 725f7eb2a4 Add some more stuff to colab notebook. 2023-03-01 10:40:26 -05:00
comfyanonymous 3fe162c680 Quick fix modal overflowing at the bottom if error too large. 2023-02-28 19:07:23 -05:00
comfyanonymous 9502ee45c3 Hopefully fix a strange issue with xformers + lowvram. 2023-02-28 13:48:52 -05:00
comfyanonymous 5f0f97634f Only clear cuda cache on CUDA since it causes slowdowns on ROCm. 2023-02-28 13:39:30 -05:00
comfyanonymous b31daadc03 Try to improve memory issues with del. 2023-02-28 12:27:43 -05:00
comfyanonymous cd85f876f2 Try to clear more memory at the end of each prompt execution. 2023-02-28 11:56:33 -05:00
comfyanonymous f3103d7b60 I confirmed the notebook works on paperspace. 2023-02-28 02:49:53 -05:00
comfyanonymous b28dcd7684 Install xformers at the same time as requirements in notebook to fix issues. 2023-02-27 20:22:46 -05:00
comfyanonymous a29bd63e7a --highvram should be autodetected in colab/etc.. now. 2023-02-27 20:06:44 -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 49d2e5bb5a Move some stuff from main.py to execution.py 2023-02-27 19:44:58 -05:00
comfyanonymous f30a2deb3f Switch the CLIPTextEncode div to a textarea. 2023-02-27 16:13:09 -05:00
comfyanonymous d826a0971c Outpainting actually works now. 2023-02-27 12:02:23 -05:00
comfyanonymous 75fa162531 Remove sample_ from some sampler names. 
Old workflows will still work.
 2023-02-27 01:43:06 -05:00
comfyanonymous 666337bff4 Merge branch 'batchimagepreview' of https://github.com/pythongosssss/ComfyUI into pythongosssss-batchimagepreview 2023-02-26 17:29:51 -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 8f75047d9c Small Readme change. 2023-02-26 03:37:57 -05:00
comfyanonymous 678ba05a28 Add some commented out wget commands to the colab notebook. 2023-02-26 01:54:17 -05:00
comfyanonymous 1561edcd98 Colab notebook. 2023-02-25 23:23:24 -05:00
comfyanonymous d31d161ee6 Fix. 2023-02-25 23:00:31 -05:00
comfyanonymous 3263a2bf0e Colab notebook improvements. 2023-02-25 22:57:22 -05:00
comfyanonymous c0fb0c848f Update colab notebook. 2023-02-25 22:49:22 -05:00
comfyanonymous dfb397e034 Fix multiple controlnets not working. 2023-02-25 22:12:22 -05:00
comfyanonymous 6de6246dd4 Fix some potential issues related to threads. 2023-02-25 18:36:29 -05:00
comfyanonymous 8074a58a1a Merge branch 'master' into pythongosssss-socketrework 2023-02-25 16:02:36 -05:00
comfyanonymous af3cc1b5fb Fixed issue when batched image was used as a controlnet input. 2023-02-25 14:57:28 -05:00
comfyanonymous d6ed202679 Add xformers install command to readme and colab notebook. 2023-02-25 14:00:24 -05:00
comfyanonymous d2da346b0b Fix missing variable. 2023-02-25 12:19:03 -05:00
comfyanonymous 1144ed5792 Add to the Readme that T2I-Adapter is now supported. 2023-02-25 01:38:34 -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 5796705cc6 Add some cells to run with localtunnel in colab notebook. 2023-02-23 10:16:30 -05:00
comfyanonymous 62df8dd62a Add a node to load diff controlnets. 2023-02-22 23:22:03 -05:00
comfyanonymous 3ae61a2bca Add a node to invert the colours of images. 
Might be useful for controlnets.
 2023-02-22 21:57:56 -05:00
comfyanonymous f04dc2c2f4 Implement DDIM sampler. 2023-02-22 21:10:19 -05:00
comfyanonymous 218f64315d Add some text to colab to help people troubleshoot issues. 2023-02-22 17:15:10 -05:00
comfyanonymous a37b41e84c Don't send the "Random seed after every gen" field in the prompt. 2023-02-22 12:48:27 -05:00
comfyanonymous 8c692c91d2 Add a basic example for how to use the ComfyUI api. 2023-02-22 12:34:27 -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