ComfyUI

Author	SHA1	Message	Date
comfyanonymous	4871a36458	Cleanup some unused imports.	10 months ago
comfyanonymous	d76a04b6ea	Add unfinished ImageOnlyCheckpointSave node to save a SVD checkpoint. This node is unfinished, SVD checkpoints saved with this node will work with ComfyUI but not with anything else.	10 months ago
comfyanonymous	2395ae740a	Make unclip more deterministic. Pass a seed argument note that this might make old unclip images different.	10 months ago
comfyanonymous	10f2609fdd	Add InpaintModelConditioning node. This is an alternative to VAE Encode for inpaint that should work with lower denoise. This is a different take on #2501	10 months ago
comfyanonymous	8c6493578b	Implement noise augmentation for SD 4X upscale model.	11 months ago
comfyanonymous	a7874d1a8b	Add support for the stable diffusion x4 upscaling model. This is an old model. Load the checkpoint like a regular one and use the new SD_4XUpscale_Conditioning node.	11 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	8cf1daa108	Fix SDXL area composition sometimes not using the right pooled output.	11 months ago
comfyanonymous	2258f85159	Support stable zero 123 model. To use it use the ImageOnlyCheckpointLoader to load the checkpoint and the new Stable_Zero123 node.	11 months ago
comfyanonymous	3152023fbc	Use inference dtype for unet memory usage estimation.	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	31b0f6f3d8	UNET weights can now be stored in fp8. --fp8_e4m3fn-unet and --fp8_e5m2-unet are the two different formats supported by pytorch.	12 months ago
comfyanonymous	61a123a1e0	A different way of handling multiple images passed to SVD. Previously when a list of 3 images [0, 1, 2] was used for a 6 frame video they were concated like this: [0, 1, 2, 0, 1, 2] now they are concated like this: [0, 0, 1, 1, 2, 2]	12 months ago
comfyanonymous	13fdee6abf	Try to free memory for both cond+uncond before inference.	12 months ago
comfyanonymous	be71bb5e13	Tweak memory inference calculations a bit.	12 months ago
comfyanonymous	871cc20e13	Support SVD img2vid model.	1 year ago
comfyanonymous	ce67dcbcda	Make it easy for models to process the unet state dict on load.	1 year ago
comfyanonymous	4781819a85	Make memory estimation aware of model dtype.	1 year ago
comfyanonymous	dd4ba68b6e	Allow different models to estimate memory usage differently.	1 year ago
comfyanonymous	064d7583eb	Add a CONDConstant for passing non tensor conds to unet.	1 year ago
comfyanonymous	1ffa8858e7	Move model sampling code to comfy/model_sampling.py	1 year ago
comfyanonymous	ecb80abb58	Allow ModelSamplingDiscrete to be instantiated without a model config.	1 year ago
comfyanonymous	111f1b5255	Fix some issues with sampling precision.	1 year ago
comfyanonymous	7c0f255de1	Clean up percent start/end and make controlnets work with sigmas.	1 year ago
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.	1 year ago
comfyanonymous	d1d2fea806	Pass extra conds directly to unet.	1 year ago
comfyanonymous	036f88c621	Refactor to make it easier to add custom conds to models.	1 year ago
comfyanonymous	e6962120c6	Make sure cond_concat is on the right device.	1 year ago
comfyanonymous	782a24fce6	Refactor cond_concat into model object.	1 year ago
comfyanonymous	492db2de8d	Allow having a different pooled output for each image in a batch.	1 year ago
comfyanonymous	7931ff0fd9	Support SDXL inpaint models.	1 year ago
comfyanonymous	1c012d69af	It doesn't make sense for c_crossattn and c_concat to be lists.	1 year ago
comfyanonymous	15adc3699f	Move beta_schedule to model_config and allow disabling unet creation.	1 year ago
comfyanonymous	a57b0c797b	Fix lowvram model merging.	1 year ago
comfyanonymous	39ac856a33	ReVision support: unclip nodes can now be used with SDXL.	1 year ago
comfyanonymous	a2ce9655ca	Refactor unclip code.	1 year ago
comfyanonymous	9cc12c833d	CLIPVisionEncode can now encode multiple images.	1 year ago
comfyanonymous	4b957a0010	Initialize the unet directly on the target device.	1 year ago
comfyanonymous	68be24eead	Remove some prints.	1 year ago
comfyanonymous	51d5477579	Add key to indicate checkpoint is v_prediction when saving.	1 year ago
comfyanonymous	3ded1a3a04	Refactor of sampler code to deal more easily with different model types.	1 year ago
comfyanonymous	ddc6f12ad5	Disable autocast in unet for increased speed.	1 year ago
comfyanonymous	fcef47f06e	Fix bug.	1 year ago
comfyanonymous	9b93b920be	Add CheckpointSave node to save checkpoints. The created checkpoints contain workflow metadata that can be loaded by dragging them on top of the UI or loading them with the "Load" button. Checkpoints will be saved in fp16 or fp32 depending on the format ComfyUI is using for inference on your hardware. To force fp32 use: --force-fp32 Anything that patches the model weights like merging or loras will be saved. The output directory is currently set to: output/checkpoints but that might change in the future.	1 year ago
comfyanonymous	8607c2d42d	Move latent scale factor from VAE to model.	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	c64ca8c0b2	Refactor unCLIP noise augment out of samplers.py	1 year ago
comfyanonymous	de142eaad5	Simpler base model code.	1 year ago

49 Commits (508d286b8fbd4cfa0281ee6c0d25aab95a7c014c)