973 Commits

Author	SHA1	Message	Date
rockerBOO	f974c6b257	change order to match upstream	2025-03-19 14:27:43 -04:00
rockerBOO	5d5a7d2acf	Fix IP noise calculation	2025-03-19 13:50:04 -04:00
rockerBOO	1eddac26b0	Separate random to a variable, and make sure on device	2025-03-19 00:49:42 -04:00
rockerBOO	8e6817b0c2	Remove double noise	2025-03-19 00:45:13 -04:00
rockerBOO	d93ad90a71	Add perturbation on noisy_model_input if needed	2025-03-19 00:37:27 -04:00
rockerBOO	7197266703	Perturbed noise should be separate of input noise	2025-03-19 00:25:51 -04:00
rockerBOO	b81bcd0b01	Move IP noise gamma to noise creation to remove complexity and align noise for target loss	2025-03-18 21:36:55 -04:00
rockerBOO	6f4d365775	zeros_like because we are adding	2025-03-18 18:53:34 -04:00
rockerBOO	a4f3a9fc1a	Use ones_like	2025-03-18 18:44:21 -04:00
rockerBOO	b425466e7b	Fix IP noise gamma to use random values	2025-03-18 18:42:35 -04:00
rockerBOO	c8be141ae0	Apply IP gamma to noise fix	2025-03-18 15:42:18 -04:00
rockerBOO	0b25a05e3c	Add IP noise gamma for Flux	2025-03-18 15:40:40 -04:00
Disty0	620a06f517	Check for uppercase file extension too	2025-03-17 17:44:29 +03:00
Disty0	564ec5fb7f	use extend instead of +=	2025-03-17 17:41:03 +03:00
Disty0	7e90cdd47a	use bytearray and add typing hints	2025-03-17 17:26:08 +03:00
rockerBOO	1f22a94cfe	Update embedder_dims, add more flexible caption extension	2025-03-04 02:25:50 -05:00
青龍聖者@bdsqlsz	09c4710d1e	Merge pull request #22 from rockerBOO/sage_attn ... Add Sage Attention for Lumina	2025-03-03 10:26:02 +08:00
青龍聖者@bdsqlsz	dfe1ab6c50	Merge pull request #21 from rockerBOO/lumina-torch-dynamo-gemma2 ... fix torch compile/dynamo for Gemma2	2025-03-02 18:31:13 +08:00
青龍聖者@bdsqlsz	b6e4194ea5	Merge pull request #20 from rockerBOO/lumina-system-prompt-special-token ... Lumina system prompt special token	2025-03-02 18:30:49 +08:00
青龍聖者@bdsqlsz	b5d1f1caea	Merge pull request #19 from rockerBOO/lumina-block-swap ... Lumina block swap	2025-03-02 18:30:37 +08:00
rockerBOO	a69884a209	Add Sage Attention for Lumina	2025-03-01 20:37:45 -05:00
rockerBOO	cad182d29a	fix torch compile/dynamo for Gemma2	2025-02-28 18:35:19 -05:00
rockerBOO	a2daa87007	Add block swap for uncond (neg) for sample images	2025-02-28 14:22:47 -05:00
rockerBOO	1bba7acd9a	Add block swap in sample image timestep loop	2025-02-28 14:12:13 -05:00
rockerBOO	d6f7e2e20c	Fix block swap for sample images	2025-02-28 14:08:27 -05:00
Kohya S	272f4c3775	Merge branch 'sd3' into sd3_safetensors_merge	2025-02-28 23:52:36 +09:00
rockerBOO	9647f1e324	Fix validation block swap. Add custom offloading tests	2025-02-27 20:36:36 -05:00
rockerBOO	42fe22f5a2	Enable block swap for Lumina	2025-02-27 03:21:24 -05:00
rockerBOO	ce2610d29b	Change system prompt to inject Prompt Start special token	2025-02-27 02:47:04 -05:00
rockerBOO	0886d976f1	Add block swap	2025-02-27 02:31:50 -05:00
rockerBOO	542f980443	Fix sample norms in batches	2025-02-27 00:00:20 -05:00
rockerBOO	70403f6977	fix cache text encoder outputs if not using disk. small cleanup/alignment	2025-02-26 23:33:50 -05:00
rockerBOO	7b83d50dc0	Merge branch 'sd3' into lumina	2025-02-26 22:13:56 -05:00
Disty0	2f69f4dbdb	fix typo	2025-02-27 00:30:19 +03:00
Disty0	9a415ba965	JPEG XL support	2025-02-27 00:21:57 +03:00
Kohya S	ec350c83eb	Merge branch 'dev' into sd3	2025-02-26 21:17:29 +09:00
Kohya S	1fcac98280	Merge branch 'sd3' into val-loss-improvement	2025-02-26 21:09:10 +09:00
Kohya S	f4a0047865	feat: support metadata loading in MemoryEfficientSafeOpen	2025-02-26 20:50:44 +09:00
sdbds	a1a5627b13	fix shift	2025-02-26 11:35:38 +08:00
sdbds	ce37c08b9a	clean code and add finetune code	2025-02-26 11:20:03 +08:00
Disty0	f68702f71c	Update IPEX libs	2025-02-25 21:27:41 +03:00
sdbds	5f9047c8cf	add truncation when > max_length	2025-02-26 01:00:35 +08:00
Kohya S	67fde015f7	Merge branch 'dev' into sd3	2025-02-24 18:56:15 +09:00
Kohya S.	386b7332c6	Merge pull request #1918 from tsukimiya/fix_vperd_warning ... Remove v-pred warning.	2025-02-24 18:55:25 +09:00
Kohya S	905f081798	Merge branch 'dev' into sd3	2025-02-24 18:54:28 +09:00
sdbds	fc772affbe	1、Implement cfg_trunc calculation directly using timesteps, without intermediate steps. ... 2、Deprecate and remove the guidance_scale parameter because it used in inference not train 3、Add inference command-line arguments --ct for cfg_trunc_ratio and --rc for renorm_cfg to control CFG truncation and renormalization during inference.	2025-02-24 14:10:24 +08:00
rockerBOO	2c94d17f05	Fix typo	2025-02-23 20:21:06 -05:00
rockerBOO	48e7da2d4a	Add sample batch size for Lumina	2025-02-23 20:19:24 -05:00
rockerBOO	ba725a84e9	Set default discrete_flow_shift to 6.0. Remove default system prompt.	2025-02-23 18:01:09 -05:00
rockerBOO	42a801514c	Fix system prompt in datasets	2025-02-23 13:48:37 -05:00