128 Commits

Author	SHA1	Message	Date
Denis	e71ae285ef	Merge branch 'kijai:main' into main	2024-10-28 15:19:56 +03:00
kijai	c17750ea0a	remove print	2024-10-26 02:35:29 +03:00
kijai	dcca095743	make torch compile work better	2024-10-26 02:33:29 +03:00
kijai	25f16462aa	torch compile maybe	2024-10-25 22:50:13 +03:00
kijai	249e8d54d1	Add cogvideox-5b-controlnet-canny-v1	2024-10-25 22:46:37 +03:00
denk	47a79dae4e	add cogvideox-2b-img2vid	2024-10-24 22:42:09 +03:00
kijai	ccddf0b271	Update nodes.py	2024-10-23 18:30:28 +03:00
Jukka Seppänen	5a024a0973	possibly fix for diffusers 0.31.0	2024-10-22 22:12:49 +03:00
kijai	2cc521062f	correct Tora fuser dtype ... I think...	2024-10-22 18:40:31 +03:00
kijai	15bf8f51ab	Update nodes.py	2024-10-22 15:34:42 +03:00
kijai	45c3f06d0a	Update nodes.py	2024-10-22 13:52:27 +03:00
kijai	35cb4fde94	bugfixes	2024-10-22 00:52:58 +03:00
kijai	a654821515	testing Tora for I2V	2024-10-21 22:53:36 +03:00
kijai	adfc560ad6	Add ToraEncodeOpticalFlow -node ... For using custom optical flows as input for the Tora model	2024-10-21 18:19:15 +03:00
kijai	4c3fcd7b01	Support multiple LoRAs	2024-10-21 13:24:21 +03:00
kijai	01bce7dfff	Add Tora GGUF	2024-10-21 03:49:29 +03:00
kijai	256a638ee4	cleanup, bugfixes	2024-10-21 03:24:53 +03:00
kijai	7e8a3e4f2a	Update nodes.py	2024-10-21 00:50:04 +03:00
kijai	b33a127dc7	Update nodes.py	2024-10-21 00:49:07 +03:00
kijai	47f028e0bd	Update nodes.py	2024-10-21 00:29:44 +03:00
kijai	e8bc2fd052	Initial Tora implementation ... https://github.com/alibaba/Tora	2024-10-21 00:11:39 +03:00
kijai	8f9fa07455	Add GGUF for the interpolation model	2024-10-19 13:17:11 +03:00
kijai	4f8f3aa74f	Support CogVideoX-Interpolation -model ... https://github.com/feizc/CogvideX-Interpolation	2024-10-17 13:41:23 +03:00
kijai	09ed641575	fix LoRA for I2V model when using fp8	2024-10-14 01:05:35 +03:00
kijai	0f5d67a9a9	Update nodes.py	2024-10-13 23:05:50 +03:00
kijai	42c46b76e1	Error on too long prompts.	2024-10-13 15:38:06 +03:00
kijai	a995247624	possibly fix LoRA scaling	2024-10-12 22:23:54 +03:00
kijai	276b3b86d9	possible fix for NaNs when using LoRA and fp8	2024-10-12 02:24:53 +03:00
kijai	bf0f6888c2	fix fp8 with controlnet	2024-10-08 18:05:28 +03:00
kijai	d76229c49b	controlnet support ... https://huggingface.co/TheDenk/cogvideox-2b-controlnet-hed-v1 https://huggingface.co/TheDenk/cogvideox-2b-controlnet-canny-v1	2024-10-08 16:22:07 +03:00
kijai	d83f64aa3e	don't break MZ loader for no reason	2024-10-08 14:53:19 +03:00
kijai	e1a784d92b	error out if trying to use I2V model with other frame counts than 49	2024-10-07 22:15:06 +03:00
Jukka Seppänen	f657e0d56e	allow tiny resolutions (it actually works with fun models)	2024-10-07 01:06:22 +03:00
Jukka Seppänen	49451c4a22	support sageattn ... https://github.com/thu-ml/SageAttention	2024-10-06 20:26:03 +03:00
kijai	502ebab83f	support extra_model_paths	2024-10-06 12:39:57 +03:00
kijai	af2a568c8e	Update nodes.py	2024-10-06 11:54:47 +03:00
kijai	fc7e7d7c62	peft	2024-10-06 11:53:38 +03:00
kijai	d8a9f31de9	lora loading	2024-10-06 02:48:39 +03:00
kijai	5fde34468e	update workflows	2024-10-06 02:22:35 +03:00
kijai	00d38f9a22	context schedule and all samplers for the non-Fun sampler as well	2024-10-06 01:28:20 +03:00
kijai	1801c65e97	FreeNoise noise shuffling for context windows	2024-10-05 19:29:09 +03:00
kijai	6e82eb1618	Update nodes.py	2024-10-05 16:16:44 +03:00
kijai	453ee1606e	Add context schedules for the control pipeline	2024-10-05 16:15:34 +03:00
kijai	033ec61d86	Update nodes.py	2024-10-04 13:19:13 +03:00
kijai	7af6666c67	latent input for the control sampler, allows vid2vid along with pose input	2024-10-04 13:14:54 +03:00
kijai	3c8183ac65	Support lora loading with fp8, noise augment for control input	2024-10-04 12:48:32 +03:00
kijai	3efe90ba35	Support CogVideoX-Fun lora loading	2024-10-04 01:53:40 +03:00
kijai	f9f06d595e	temporal tiling for the control pipe	2024-10-02 20:14:45 +03:00
kijai	bb6ea6b3a4	Update nodes.py	2024-10-02 18:39:15 +03:00
kijai	627af9341c	separate control image encoder and add tiled encode support for it ... tiled encoding code thanks to MinusZoneML: https://github.com/MinusZoneAI/ComfyUI-CogVideoX-MZ/blob/main/mz_enable_vae_encode_tiling.py	2024-10-02 18:08:11 +03:00