andreas/ComfyUI
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
1,738 Commits 1 Branch 0 Tags
34eccd863bb41f48346de178a55be308dc36e5e5
Commit Graph
100 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
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 5b37270d3a Add a lora loader node for models with no CLIP. 2023-11-25 02:26:50 -05:00
comfyanonymous 5d6dfce548 Fix importing diffusers unets. 2023-11-24 20:35:29 -05:00
comfyanonymous e020ab61f9 Fix output APNG not working with ffmpeg. 2023-11-24 18:24:19 -05:00
comfyanonymous 8ad5d494d5 Fix APNG not working in ffmpeg. 2023-11-24 18:14:17 -05:00
comfyanonymous 916e9c998c Use same default fps as webp node. 2023-11-24 11:19:23 -05:00
comfyanonymous eff24ea6aa Add a node to save animated PNG files. These work in ffpmeg unlike webp. 2023-11-24 11:12:10 -05:00
comfyanonymous 3e5ea74ad3 Make buggy xformers fall back on pytorch attention. 2023-11-24 03:55:35 -05:00
comfyanonymous 982338b9bb Fix issue loading webp files in UI. 2023-11-24 02:08:08 -05:00
comfyanonymous c782cf3ea9 Add to Readme that Stable Video Diffusion is supported. 2023-11-24 00:27:08 -05:00
comfyanonymous 02ffbb2de3 Fix typo. 2023-11-23 23:20:07 -05:00
comfyanonymous 42dfae6331 Nodes to properly use the SDV img2vid checkpoint. 
The img2vid model is conditioned on clip vision output only which means
there's no CLIP model which is why I added a ImageOnlyCheckpointLoader to
load it. Note that the unClipCheckpointLoader can also load it because it
also has a CLIP_VISION output.

SDV_img2vid_Conditioning is the node used to pass the right conditioning
to the img2vid model.

VideoLinearCFGGuidance applies a linearly decreasing CFG scale to each
video frame from the cfg set in the sampler node to min_cfg.

SDV_img2vid_Conditioning can be found in conditioning->video_models
ImageOnlyCheckpointLoader can be found in loaders->video_models
VideoLinearCFGGuidance can be found in sampling->video_models
 2023-11-23 19:48:49 -05:00
comfyanonymous 871cc20e13 Support SVD img2vid model. 2023-11-23 19:41:33 -05:00
comfyanonymous 022033a0e7 Fix SaveAnimatedWEBP not working when metadata is disabled. 2023-11-23 15:39:35 -05:00
comfyanonymous a657f96c5c Add a node to save animated webp. 2023-11-23 14:28:41 -05:00
comfyanonymous 87031a1945 Update readme with link to LCM example page. 2023-11-23 11:59:11 -05:00
comfyanonymous d03d8aa2e3 Fix loading groups. 2023-11-23 01:09:15 -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 1ca4802e8c Merge branch 'hide-if-collapsed' of https://github.com/pythongosssss/ComfyUI 2023-11-22 11:46:21 -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 d66b631d74 Merge branch 'fix-collapsed-clip' of https://github.com/pythongosssss/ComfyUI 2023-11-21 13:26:26 -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 2dd5b4dd78 Only show last 200 elements in the UI history tab. 2023-11-20 16:56:29 -05:00
comfyanonymous a03dde190e Cap maximum history size at 10000. Delete oldest entry when reached. 2023-11-20 16:38:39 -05:00
comfyanonymous 31c5ea7b2c Add LatentInterpolate to interpolate between latents. 2023-11-20 03:55:51 -05:00
comfyanonymous dba4f3b4fc Add a RepeatImageBatch node. 2023-11-19 06:09:01 -05:00
comfyanonymous d9d8702d8d percent_to_sigma now returns a float instead of a tensor. 2023-11-18 23:20:29 -05:00
comfyanonymous 8a451234b3 Add ImageCrop node. 2023-11-18 04:44:17 -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 bd07ad1861 Add PatchModelAddDownscale (Kohya Deep Shrink) node. 
By adding a downscale to the unet in the first timesteps this node lets
you generate images at higher resolutions with less consistency issues.
 2023-11-16 13:25:46 -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 7114cfec0e Always clone graph data when loading to fix some load issues. 2023-11-15 15:55:02 -05:00
comfyanonymous 629e4c552c Merge branch 'master' of https://github.com/42lux/ComfyUI 2023-11-15 01:47:21 -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
comfyanonymous 94cc718e9c Add a way to add patches to the input block. 2023-11-14 00:08:12 -05:00
comfyanonymous 8509bd58b4 Reorganize custom_sampling nodes. 2023-11-13 21:45:23 -05:00
comfyanonymous 61112c81b9 Add a node to flip the sigmas for unsampling. 2023-11-13 21:45:08 -05:00
comfyanonymous eb0407e806 Update litegraph to latest. 2023-11-13 16:26:28 -05:00
comfyanonymous 7339479b10 Disable xformers when it can't load properly. 2023-11-13 12:31:10 -05:00
comfyanonymous f12ec55983 Allow boolean widgets to have no options dict. 2023-11-13 00:42:34 -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 ca2812bae0 Fix RescaleCFG for batch size > 1. 2023-11-10 22:05:25 -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 ca71e542d2 Lower cfg step to 0.1 in sampler nodes. 2023-11-09 17:35:17 -05:00
comfyanonymous cd6df8b323 Fix sanitize node name removing the "/" character. 2023-11-09 13:10:19 -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 d07cd44272 Merge branch 'master' of https://github.com/cubiq/ComfyUI 2023-11-07 01:52:13 -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
comfyanonymous a6c83b3cd0 Merge branch 'fix_unet_wrapper_function_name' of https://github.com/gameltb/ComfyUI 2023-11-05 12:41:38 -05:00
comfyanonymous 02f062b5b7 Sanitize unknown node types on load to prevent XSS. 2023-11-05 12:29:28 -05:00
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 ee74ef5c9e Increase maximum batch size in LatentRebatch. 2023-11-02 13:07:41 -04:00
comfyanonymous dd116abfc4 Merge branch 'quantize-dither' of https://github.com/tsone/ComfyUI 2023-11-02 00:57:00 -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 45a3df1cde Merge branch 'filter-widgets-crash-fix' of https://github.com/Jantolick/ComfyUI 2023-11-01 20:17:25 -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 aac8fc99d6 Cleanup webp import code a bit. 2023-10-28 12:24:50 -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