ComfyUI

Author	SHA1	Message	Date
comfyanonymous	448d9263a2	Fix control loras breaking.	8 months ago
comfyanonymous	db8b59ecff	Lower memory usage for loras in lowvram mode at the cost of perf.	8 months ago
comfyanonymous	667c92814e	Stable Cascade Stage B.	9 months ago
comfyanonymous	78a70fda87	Remove useless import.	10 months ago
comfyanonymous	36a7953142	Greatly improve lowvram sampling speed by getting rid of accelerate. Let me know if this breaks anything.	11 months ago
comfyanonymous	77755ab8db	Refactor comfy.ops comfy.ops -> comfy.ops.disable_weight_init This should make it more clear what they actually do. Some unused code has also been removed.	11 months ago
comfyanonymous	ba07cb748e	Use faster manual cast for fp8 in unet.	11 months ago
comfyanonymous	57926635e8	Switch text encoder to manual cast. Use fp16 text encoder weights for CPU inference to lower memory usage.	11 months ago
comfyanonymous	af365e4dd1	All the unet ops with weights are now handled by comfy.ops	12 months ago
comfyanonymous	412d3ff57d	Refactor.	1 year ago
comfyanonymous	00c0b2c507	Initialize text encoder to target dtype.	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	bb1f45d6e8	Properly disable weight initialization in clip models.	1 year ago
comfyanonymous	21f04fe632	Disable default weight values in unet conv2d for faster loading.	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

15 Commits (f2fe635c9f56a8e78866f59b3f110585e75b42f4)