ComfyUI

Author	SHA1	Message	Date
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	11 months ago
comfyanonymous	9ac0b487ac	Make --gpu-only put intermediate values in GPU memory instead of cpu.	12 months ago
comfyanonymous	798a34d009	Lower compress level for image preview.	12 months ago
comfyanonymous	5b37270d3a	Add a lora loader node for models with no CLIP.	12 months ago
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	12 months ago
Enrico Fasoli	1964bf1e78	fix: folder handling issues	1 year ago
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.	1 year ago
comfyanonymous	8a451234b3	Add ImageCrop node.	1 year ago
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.	1 year ago
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.	1 year ago
comfyanonymous	ca71e542d2	Lower cfg step to 0.1 in sampler nodes.	1 year ago
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.	1 year ago
comfyanonymous	1443caf373	HyperTile node, can be found in: _for_testing->HyperTile	1 year ago
comfyanonymous	d44a2de49f	Make VAE code closer to sgm.	1 year ago
comfyanonymous	7e09e889e3	Make clear that the old CheckpointLoader is deprecated.	1 year ago
comfyanonymous	20d3852aa1	Pull some small changes from the other repo.	1 year ago
comfyanonymous	9212bea87c	Change a few things in #1578 .	1 year ago
MoonRide303	ece69bf28c	Change channel type to MASK (reduced redundancy, increased usability)	1 year ago
MoonRide303	d06cd2805d	Added support for Porter-Duff image compositing	1 year ago
comfyanonymous	ec454c771b	Refactor with code from comment of #1588	1 year ago
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.	1 year ago
comfyanonymous	bf3fc2f1b7	Refactor sampling related code.	1 year ago
comfyanonymous	9546a798fb	Make LoadImage and LoadImageMask return masks in batch format.	1 year ago
comfyanonymous	2381d36e6d	1024 wasn't enough.	1 year ago
comfyanonymous	42f6d1ebe2	Increase maximum batch sizes of empty image nodes.	1 year ago
comfyanonymous	77c124c5a1	Fix typo.	1 year ago
Jairo Correa	593b7069e7	Proportional scale latent and image	1 year ago
comfyanonymous	fd93c759e2	Implement FreeU: Free Lunch in Diffusion U-Net node. _for_testing->FreeU	1 year ago
comfyanonymous	422d16c027	Add some nodes to add, subtract and multiply latents.	1 year ago
comfyanonymous	1122df1a20	Increase range of lora strengths.	1 year ago
MoonRide303	2b6b178173	Added support for lanczos scaling	1 year ago
comfyanonymous	0109431626	Lower the minimum resolution of EmptyLatentImage.	1 year ago
comfyanonymous	db63aa7e53	Nodes can now control the rounding in the UI.	1 year ago
comfyanonymous	f88f7f413a	Add a ConditioningSetAreaPercentage node.	1 year ago
comfyanonymous	36ea8784a8	Only return tuple of 3 args in CheckpointLoaderSimple.	1 year ago
comfyanonymous	57beace324	Fix VAEDecodeTiled minimum.	1 year ago
comfyanonymous	7e941f9f24	Clean up DiffusersLoader node.	1 year ago
comfyanonymous	8ddd081b09	Use the same units for tile size in VAEDecodeTiled and VAEEncodeTiled.	1 year ago
BVH	d86b222fe9	Reduce min tile size for encode	1 year ago
BVH	9196588088	Make tile size in Tiled VAE encode/decode user configurable	1 year ago
comfyanonymous	c77f02e1c6	Move controlnet code to comfy/controlnet.py	1 year ago
comfyanonymous	d7b3b0f8c1	Don't hardcode node names for image upload widget.	1 year ago
pythongosssss	9b1d5a587c	Allow loading js extensions without copying to /web folder	1 year ago
comfyanonymous	27b87c25a1	Add an EmptyImage node. TODO: implement color picker in the frontend.	1 year ago
comfyanonymous	e7d88855f4	Add node to batch images together.	1 year ago
comfyanonymous	9cc12c833d	CLIPVisionEncode can now encode multiple images.	1 year ago
comfyanonymous	fa962e86c1	Make LatentBlend more consistent with other nodes.	1 year ago
FuamiCake	d712193885	Add LatentBlend node, allowing for blending between two Latent inputs.	1 year ago
FuamiCake	3dcad78fe1	SaveLatent reports its outputs so they are visible to API	1 year ago
comfyanonymous	1141029a4a	Add --disable-metadata argument to disable saving metadata in files.	1 year ago

1 2 3 4 5 ...

287 Commits (a5056cfb1f41f1f9e6fcd523ef8091e6e7cd6e3b)