ComfyUI

Author	SHA1	Message	Date
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.	1 year ago
comfyanonymous	fff491b032	Model patches can now know which batch is positive and negative.	1 year ago
comfyanonymous	afa2399f79	Add a way to set output block patches to modify the h and hsp.	1 year ago
comfyanonymous	1938f5c5fe	Add a force argument to soft_empty_cache to force a cache empty.	1 year ago
Simon Lui	2da73b7073	Revert changes in comfy/ldm/modules/diffusionmodules/util.py, which is unused.	1 year ago
Simon Lui	4a0c4ce4ef	Some fixes to generalize CUDA specific functionality to Intel or other GPUs.	1 year ago
comfyanonymous	0e3b641172	Remove xformers related print.	1 year ago
comfyanonymous	bed116a1f9	Remove optimization that caused border.	1 year ago
comfyanonymous	1c794a2161	Fallback to slice attention if xformers doesn't support the operation.	1 year ago
comfyanonymous	d935ba50c4	Make --bf16-vae work on torch 2.0	1 year ago
comfyanonymous	cf5ae46928	Controlnet/t2iadapter cleanup.	1 year ago
comfyanonymous	b80c3276dc	Fix issue with gligen.	1 year ago
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.	1 year ago
comfyanonymous	2b13939044	Remove some useless code.	1 year ago
comfyanonymous	95d796fc85	Faster VAE loading.	1 year ago
comfyanonymous	4b957a0010	Initialize the unet directly on the target device.	1 year ago
comfyanonymous	9ba440995a	It's actually possible to torch.compile the unet now.	1 year ago
comfyanonymous	ddc6f12ad5	Disable autocast in unet for increased speed.	1 year ago
comfyanonymous	103c487a89	Cleanup.	1 year ago
comfyanonymous	78d8035f73	Fix bug with controlnet.	1 year ago
comfyanonymous	05676942b7	Add some more transformer hooks and move tomesd to comfy_extras. Tomesd now uses q instead of x to decide which tokens to merge because it seems to give better results.	1 year ago
comfyanonymous	fa28d7334b	Remove useless code.	1 year ago
comfyanonymous	f87ec10a97	Support base SDXL and SDXL refiner models. Large refactor of the model detection and loading code.	1 year ago
comfyanonymous	9fccf4aa03	Add original_shape parameter to transformer patch extra_options.	1 year ago
comfyanonymous	8883cb0f67	Add a way to set patches that modify the attn2 output. Change the transformer patches function format to be more future proof.	1 year ago
comfyanonymous	ae43f09ef7	All the unet weights should now be initialized with the right dtype.	1 year ago
comfyanonymous	7bf89ba923	Initialize more unet weights as the right dtype.	1 year ago
comfyanonymous	e21d9ad445	Initialize transformer unet block weights in right dtype at the start.	1 year ago
comfyanonymous	21f04fe632	Disable default weight values in unet conv2d for faster loading.	1 year ago
comfyanonymous	9d54066ebc	This isn't needed for inference.	1 year ago
comfyanonymous	6971646b8b	Speed up model loading a bit. Default pytorch Linear initializes the weights which is useless and slow.	1 year ago
comfyanonymous	274dff3257	Remove more useless files.	1 year ago
comfyanonymous	f0a2b81cd0	Cleanup: Remove a bunch of useless files.	1 year ago
comfyanonymous	b8636a44aa	Make scaled_dot_product switch to sliced attention on OOM.	2 years ago
comfyanonymous	797c4e8d3b	Simplify and improve some vae attention code.	2 years ago
BlenderNeko	d9e088ddfd	minor changes for tiled sampler	2 years ago
comfyanonymous	cb1551b819	Lowvram mode for gligen and fix some lowvram issues.	2 years ago
comfyanonymous	bae4fb4a9d	Fix imports.	2 years ago
comfyanonymous	ba8a4c3667	Change latent resolution step to 8.	2 years ago
comfyanonymous	66c8aa5c3e	Make unet work with any input shape.	2 years ago
comfyanonymous	5282f56434	Implement Linear hypernetworks. Add a HypernetworkLoader node to use hypernetworks.	2 years ago
comfyanonymous	6908f9c949	This makes pytorch2.0 attention perform a bit faster.	2 years ago
comfyanonymous	3696d1699a	Add support for GLIGEN textbox model.	2 years ago
comfyanonymous	73c3e11e83	Fix model_management import so it doesn't get executed twice.	2 years ago
EllangoK	e5e587b1c0	seperates out arg parser and imports args	2 years ago
comfyanonymous	e46b1c3034	Disable xformers in VAE when xformers == 0.0.18	2 years ago
comfyanonymous	539ff487a8	Pull latest tomesd code from upstream.	2 years ago
comfyanonymous	809bcc8ceb	Add support for unCLIP SD2.x models. See _for_testing/unclip in the UI for the new nodes. unCLIPCheckpointLoader is used to load them. unCLIPConditioning is used to add the image cond and takes as input a CLIPVisionEncode output which has been moved to the conditioning section.	2 years ago
comfyanonymous	0d972b85e6	This seems to give better quality in tome.	2 years ago
comfyanonymous	18a6c1db33	Add a TomePatchModel node to the _for_testing section. Tome increases sampling speed at the expense of quality.	2 years ago

1 2 3

130 Commits (72508a8d19121e2814ea4dfbce8a5311f37dcd61)