255 commits

Author	SHA1	Message	Date
Frank Lee	93ba7719ec	[checkpoint] adapted inference to hf pretrained weights (#143)	2024-06-17 11:27:24 +08:00
Frank Lee	a887f54711	added sp for stdit3 (#131)	2024-06-14 11:10:43 +08:00
zhengzangw	a50bec768f	[feat] complete training with feature	2024-05-21 07:20:14 +00:00
zhengzangw	80f9ecbde3	[feat] generate feature	2024-05-21 04:05:02 +00:00
zhengzangw	bdc67a3933	[wip] debug extract feat	2024-05-20 09:40:28 +00:00
zhengzangw	a016325a8e	[feat] enable freezing y_embedder	2024-05-17 06:40:44 +00:00
zhengzangw	9fd4554f55	[fix] vae dtype	2024-05-16 08:50:24 +00:00
zhengzangw	137d0ac223	[fix] t5 dtype	2024-05-16 08:33:01 +00:00
zhengzangw	bb3c23577c	[wip] eval loss and search bs	2024-05-15 12:21:07 +00:00
zhengzangw	e1e379d898	[feat] update inference config	2024-05-14 05:40:17 +00:00
zhengzangw	3a01cb440d	[feat] inference for rf	2024-05-13 11:39:16 +00:00
Shen Chenhui	b8d99d7a8b	fixed (#98) ... Co-authored-by: Shen-Chenhui <shen_chenhui@u.nus.edu>	2024-05-13 11:58:06 +08:00
zhengzangw	1db24970d5	updated	2024-05-10 03:19:38 +00:00
Shen Chenhui	89a90e6b3d	Hotfix/latent size calc std (#96) ... * save progress * format * clean config --------- Co-authored-by: Shen-Chenhui <shen_chenhui@u.nus.edu>	2024-05-09 14:12:29 +08:00
Frank Lee	82f15b30f9	fixed checkpoint (#92)	2024-05-07 18:34:22 +08:00
Zangwei Zheng	8564074229	[exp]	2024-05-07 15:41:52 +08:00
Frank Lee	06693a8187	fixed v3 train config (#89)	2024-05-07 15:13:20 +08:00
Zangwei Zheng	917643d5bd	[wip]	2024-05-07 14:51:11 +08:00
Shen-Chenhui	8e37e7d76e	Merge branch 'vae-clean-new' into dev/v1.2	2024-05-07 06:39:57 +00:00
FrankLeeeee	ec88d2d54e	resolved conflicts	2024-05-07 03:08:41 +00:00
Frank Lee	d599fd75b3	adapted pretrained model to training (#371)	2024-05-07 10:37:06 +08:00
Shen-Chenhui	1522f683b8	fix padding	2024-05-06 07:49:56 +00:00
Shen-Chenhui	041b14f138	fix padding error;add chunck inference script	2024-05-06 07:47:12 +00:00
Zangwei Zheng	eefb351333	[exp] update config bucket	2024-05-06 14:32:28 +08:00
Frank Lee	19911b99b8	converted model to hf format (#366)	2024-05-06 14:15:04 +08:00
Zangwei Zheng	5f6c9bfceb	[exp] update config	2024-05-06 10:29:21 +08:00
zhengzangw	f77370fff6	[feat] vae micro frame	2024-05-05 15:25:17 +00:00
Zangwei Zheng	c4f17b41fc	[exp] update config	2024-05-05 20:26:26 +08:00
Zheng Zangwei (Alex Zheng)	f941fa95dc	Merge branch 'dev/v1.2' into vae-clean-new	2024-05-04 20:26:42 +08:00
Zangwei Zheng	d07003b0cd	[fix] rf inference scale	2024-05-04 20:23:32 +08:00
Shen-Chenhui	d8fab103f4	added disc	2024-05-02 09:48:30 +00:00
Shen-Chenhui	bcb997502e	enable disc	2024-05-02 17:28:45 +08:00
Shen-Chenhui	b35b933841	add disc	2024-05-02 16:32:19 +08:00
Zangwei Zheng	00e21e9fed	[wip] adapt multi-res	2024-05-02 15:27:03 +08:00
zhengzangw	02904b4f29	updated	2024-05-02 03:46:01 +00:00
zhengzangw	f7a4fcfc3f	updated	2024-04-30 09:46:27 +00:00
zhengzangw	b89c072eb5	[fix] micro batch size not for training	2024-04-30 09:20:08 +00:00
zhengzangw	ace37cf7c7	refactor	2024-04-30 08:13:20 +00:00
zhengzangw	41e276f5ef	updated	2024-04-30 06:19:40 +00:00
周钰坤	bf633f3e68	Update pixart.py	2024-04-30 13:53:17 +08:00
周钰坤	34711b7bd2	update	2024-04-30 13:37:25 +08:00
周钰坤	59591d8afc	update	2024-04-30 13:36:41 +08:00
zhengzangw	b2f302b379	[wip] try vae	2024-04-29 17:02:22 +00:00
Shen-Chenhui	e3b84247c1	disable t-conv for t=1	2024-04-29 20:06:18 +08:00
Shen-Chenhui	c59b499085	Merge branch 'vae-clean-new' of https://github.com/hpcaitech/Open-Sora-dev into vae-clean-new	2024-04-29 18:10:03 +08:00
Shen-Chenhui	c631358bbf	add z nll loss	2024-04-29 18:09:42 +08:00
zhengzangw	9632b5bcf8	merged	2024-04-29 10:07:09 +00:00
zhengzangw	5c8139521a	update	2024-04-29 10:02:42 +00:00
Shen-Chenhui	b78b469420	fix merge	2024-04-29 17:58:59 +08:00
Shen-Chenhui	f81d8648cf	move out losses to different file	2024-04-29 17:53:03 +08:00