ComfyUI

Author	SHA1	Message	Date
comfyanonymous	e7bee85df8	Add arguments to run the VAE in fp16 or bf16 for testing.	1 year ago
comfyanonymous	608fcc2591	Fix bug with weights when prompt is long.	1 year ago
comfyanonymous	ddc6f12ad5	Disable autocast in unet for increased speed.	1 year ago
comfyanonymous	603f02d613	Fix loras not working when loading checkpoint with config.	1 year ago
comfyanonymous	af7a49916b	Support loading unet files in diffusers format.	1 year ago
comfyanonymous	e57cba4c61	Add gpu variations of the sde samplers that are less deterministic but faster.	1 year ago
comfyanonymous	f81b192944	Add logit scale parameter so it's present when saving the checkpoint.	1 year ago
comfyanonymous	acf95191ff	Properly support SDXL diffusers loras for unet.	1 year ago
mara	c61a95f9f7	Fix size check for conditioning mask The wrong dimensions were being checked, [1] and [2] are the image size. not [2] and [3]. This results in an out-of-bounds error if one of them actually matches.	1 year ago
comfyanonymous	8d694cc450	Fix issue with OSX.	1 year ago
comfyanonymous	c3e96e637d	Pass device to CLIP model.	1 year ago
comfyanonymous	5e6bc824aa	Allow passing custom path to clip-g and clip-h.	1 year ago
comfyanonymous	dc9d1f31c8	Improvements for OSX.	1 year ago
comfyanonymous	103c487a89	Cleanup.	1 year ago
comfyanonymous	2c4e0b49b7	Switch to fp16 on some cards when the model is too big.	1 year ago
comfyanonymous	6f3d9f52db	Add a --force-fp16 argument to force fp16 for testing.	1 year ago
comfyanonymous	1c1b0e7299	--gpu-only now keeps the VAE on the device.	1 year ago
comfyanonymous	ce35d8c659	Lower latency by batching some text encoder inputs.	1 year ago
comfyanonymous	3b6fe51c1d	Leave text_encoder on the CPU when it can handle it.	1 year ago
comfyanonymous	b6a60fa696	Try to keep text encoders loaded and patched to increase speed. load_model_gpu() is now used with the text encoder models instead of just the unet.	1 year ago
comfyanonymous	97ee230682	Make highvram and normalvram shift the text encoders to vram and back. This is faster on big text encoder models than running it on the CPU.	1 year ago
comfyanonymous	5a9ddf94eb	LoraLoader node now caches the lora file between executions.	1 year ago
comfyanonymous	9920367d3c	Fix embeddings not working with --gpu-only	1 year ago
comfyanonymous	62db11683b	Move unet to device right after loading on highvram mode.	1 year ago
comfyanonymous	4376b125eb	Remove useless code.	1 year ago
comfyanonymous	89120f1fbe	This is unused but it should be 1280.	1 year ago
comfyanonymous	2c7c14de56	Support for SDXL text encoder lora.	1 year ago
comfyanonymous	fcef47f06e	Fix bug.	1 year ago
comfyanonymous	8248babd44	Use pytorch attention by default on nvidia when xformers isn't present. Add a new argument --use-quad-cross-attention	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	b72a7a835a	Support loras based on the stability unet implementation.	1 year ago
comfyanonymous	c71a7e6b20	Fix ddim + inpainting not working.	1 year ago
comfyanonymous	4eab00e14b	Set the seed in the SDE samplers to make them more reproducible.	1 year ago
comfyanonymous	cef6aa62b2	Add support for TAESD decoder for SDXL.	1 year ago
comfyanonymous	20f579d91d	Add DualClipLoader to load clip models for SDXL. Update LoadClip to load clip models for SDXL refiner.	1 year ago
comfyanonymous	b7933960bb	Fix CLIPLoader node.	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	8607c2d42d	Move latent scale factor from VAE to model.	1 year ago
comfyanonymous	30a3861946	Fix bug when yaml config has no clip params.	1 year ago
comfyanonymous	9e37f4c7d5	Fix error with ClipVision loader node.	1 year ago
comfyanonymous	9f83b098c9	Don't merge weights when shapes don't match and print a warning.	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	51581dbfa9	Fix last commits causing an issue with the text encoder lora.	1 year ago
comfyanonymous	8125b51a62	Keep a set of model_keys for faster add_patches.	1 year ago
comfyanonymous	45beebd33c	Add a type of model patch useful for model merging.	1 year ago
comfyanonymous	036a22077c	Fix k_diffusion math being off by a tiny bit during txt2img.	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

... 5 6 7 8 9 ...

633 Commits (e45d920ae392c608b9cfcb1f863cfc8688ebb518)