qnloft
/
ComfyUI
mirror of https://github.com/comfyanonymous/ComfyUI.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
1,843 Commits 6 Branches 26 Tags 116 MiB
Commit Graph

289 Commits

Author SHA1 Message Date
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
Hari 574363a8a6 Implement Perp-Neg 2023-12-16 00:28:16 +05:30
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 9ac0b487ac Make --gpu-only put intermediate values in GPU memory instead of cpu. 2023-12-08 02:35:45 -05:00
comfyanonymous d19de2753e Merge branch 'fix_folders_handling' of https://github.com/fazo96/ComfyUI 2023-11-29 14:10:30 -05:00
comfyanonymous 798a34d009 Lower compress level for image preview. 2023-11-28 04:57:59 -05:00
comfyanonymous 5b37270d3a Add a lora loader node for models with no CLIP. 2023-11-25 02:26:50 -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
Enrico Fasoli 1964bf1e78 fix: folder handling issues 2023-11-23 22:24:58 +01:00
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 8a451234b3 Add ImageCrop node. 2023-11-18 04:44:17 -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 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 ca71e542d2 Lower cfg step to 0.1 in sampler nodes. 2023-11-09 17:35:17 -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 1443caf373 HyperTile node, can be found in: _for_testing->HyperTile 2023-10-21 05:16:38 -04:00
comfyanonymous d44a2de49f Make VAE code closer to sgm. 2023-10-17 15:18:51 -04:00
comfyanonymous 7e09e889e3 Make clear that the old CheckpointLoader is deprecated. 2023-10-15 02:22:22 -04:00
comfyanonymous 20d3852aa1 Pull some small changes from the other repo. 2023-10-11 20:38:48 -04:00
comfyanonymous 9212bea87c Change a few things in #1578. 2023-10-04 15:43:41 -04:00
MoonRide303 ece69bf28c Change channel type to MASK (reduced redundancy, increased usability) 2023-10-04 19:04:52 +02:00
MoonRide303 d06cd2805d Added support for Porter-Duff image compositing 2023-10-04 19:04:48 +02:00
comfyanonymous ec454c771b Refactor with code from comment of #1588 2023-10-02 17:26:59 -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 9546a798fb Make LoadImage and LoadImageMask return masks in batch format. 2023-09-26 02:56:40 -04:00
comfyanonymous ba7dfd60f2 Merge branch 'proportional-scale' of https://github.com/jn-jairo/ComfyUI 2023-09-25 12:39:53 -04:00
comfyanonymous 2381d36e6d 1024 wasn't enough. 2023-09-25 01:46:44 -04:00
comfyanonymous 42f6d1ebe2 Increase maximum batch sizes of empty image nodes. 2023-09-25 01:22:37 -04:00
comfyanonymous 77c124c5a1 Fix typo. 2023-09-24 13:27:57 -04:00
Jairo Correa 593b7069e7 Proportional scale latent and image 2023-09-24 12:08:54 -03:00
comfyanonymous fd93c759e2 Implement FreeU: Free Lunch in Diffusion U-Net node. 
_for_testing->FreeU
 2023-09-23 00:56:09 -04:00
comfyanonymous 422d16c027 Add some nodes to add, subtract and multiply latents. 2023-09-21 22:23:01 -04:00
comfyanonymous 1122df1a20 Increase range of lora strengths. 2023-09-20 17:58:54 -04:00
MoonRide303 2b6b178173 Added support for lanczos scaling 2023-09-19 10:40:38 +02:00
comfyanonymous 0109431626 Lower the minimum resolution of EmptyLatentImage. 2023-09-18 16:20:03 -04:00
comfyanonymous db63aa7e53 Nodes can now control the rounding in the UI. 2023-09-17 12:49:06 -04:00
comfyanonymous f88f7f413a Add a ConditioningSetAreaPercentage node. 2023-09-06 03:28:27 -04:00
comfyanonymous 36ea8784a8 Only return tuple of 3 args in CheckpointLoaderSimple. 2023-09-02 03:34:57 -04:00
comfyanonymous 57beace324 Fix VAEDecodeTiled minimum. 2023-08-31 14:26:16 -04:00
comfyanonymous 7e941f9f24 Clean up DiffusersLoader node. 2023-08-30 12:57:07 -04:00
comfyanonymous 8ddd081b09 Use the same units for tile size in VAEDecodeTiled and VAEEncodeTiled. 2023-08-29 01:51:35 -04:00
BVH d86b222fe9
Reduce min tile size for encode 2023-08-28 22:39:09 +05:30
BVH 9196588088
Make tile size in Tiled VAE encode/decode user configurable 2023-08-28 19:57:22 +05:30
comfyanonymous c77f02e1c6 Move controlnet code to comfy/controlnet.py 2023-08-25 17:33:04 -04:00
comfyanonymous d7b3b0f8c1 Don't hardcode node names for image upload widget. 2023-08-22 19:41:49 -04:00
pythongosssss 9b1d5a587c Allow loading js extensions without copying to /web folder 2023-08-20 19:55:48 +01:00
comfyanonymous 27b87c25a1 Add an EmptyImage node. 
TODO: implement color picker in the frontend.
 2023-08-15 17:53:10 -04:00
comfyanonymous e7d88855f4 Add node to batch images together. 2023-08-14 20:23:38 -04:00
comfyanonymous 9cc12c833d CLIPVisionEncode can now encode multiple images. 2023-08-14 16:54:05 -04:00