5380 Commits

Author	SHA1	Message	Date
Vladimir Mandic	d0905a86cb	update notes	2024-08-29 07:35:30 -04:00
Vladimir Mandic	8cf959047b	flux add safetensors unet load	2024-08-28 21:53:09 -04:00
Vladimir Mandic	01fc706433	fix nvml gpu monitor	2024-08-28 20:05:12 -04:00
Vladimir Mandic	73efa761d8	add taesd flux	2024-08-28 19:24:05 -04:00
Vladimir Mandic	5503a3bf09	fix invalid resize mode	2024-08-28 13:51:03 -04:00
Vladimir Mandic	81d9af7331	control tab include all scripts	2024-08-28 13:42:58 -04:00
Vladimir Mandic	bb7f84b99b	better api defaults	2024-08-28 10:58:54 -04:00
Vladimir Mandic	65c137abf1	update	2024-08-28 10:22:46 -04:00
Vladimir Mandic	35565fa47c	offload disabled controlnets	2024-08-28 10:10:17 -04:00
Vladimir Mandic	b39abdd18f	control allow resizing overrides to match input	2024-08-28 09:53:50 -04:00
Vladimir Mandic	277d84cdbe	fix control api	2024-08-28 09:11:21 -04:00
Vladimir Mandic	707fc1de79	flux prompt attention	2024-08-28 08:34:42 -04:00
Vladimir Mandic	ed52624bef	Merge branch 'dev' into xhinker	2024-08-28 08:11:52 -04:00
Vladimir Mandic	5ed58ac7cc	end-to-end update flux, see changelog and wiki	2024-08-28 08:04:24 -04:00
Seunghoon Lee	a5d1c65948	update zluda (hip sdk 5, 6)	2024-08-26 20:35:51 +09:00
AI-Casanova	1de7716495	Remove print commands	2024-08-25 18:27:30 -05:00
AI-Casanova	517ee93e96	xhinker parser implementation	2024-08-25 18:23:45 -05:00
Seunghoon Lee	ab9a4d37cc	update zluda	2024-08-24 21:00:45 +09:00
Disty0	c1285c6de6	Cascade re-add empty embed provider	2024-08-23 07:09:05 +03:00
Disty0	02d6b674c6	Cascade decide atten mask value from the model name	2024-08-23 02:53:39 +03:00
Disty0	35d70b35ce	Flux change no-half-vae check order	2024-08-22 03:01:48 +03:00
Disty0	3165bbc4f8	Flux quant loding detect dtype from state_dict	2024-08-22 01:29:35 +03:00
Disty0	3a97db1f8a	Fix setting no-half-vae	2024-08-22 00:16:00 +03:00
Disty0	3c4d9f313d	Change vae cast order	2024-08-21 23:46:54 +03:00
Disty0	963940b9ae	Fix no half vae	2024-08-21 22:45:02 +03:00
Disty0	b706083541	Quanto Activations fix Diffuser's model offload bug	2024-08-21 20:48:32 +03:00
Disty0	e40e13a330	Quanto fix Flux activations	2024-08-21 20:04:05 +03:00
Disty0	2caf52a546	Update Quanto settings names	2024-08-21 19:25:38 +03:00
Disty0	c3ff21c15e	Quanto freeze the model before calibration	2024-08-21 19:18:57 +03:00
Disty0	694d25c161	Fix quanto	2024-08-21 19:17:04 +03:00
Disty0	16d6c03d45	Optimum Quanto activations support	2024-08-21 17:30:45 +03:00
Disty0	6a58d5210b	Make eval use apply_compile_to_model	2024-08-19 20:06:51 +03:00
Disty0	b025d1dab1	Round memory size in settings	2024-08-19 18:56:28 +03:00
Disty0	cc89ed84f9	Rename cpu offload to model offload	2024-08-19 18:48:09 +03:00
Disty0	2586a18218	Don't add 0.1 to the GPU memory	2024-08-18 13:18:24 +03:00
Disty0	5e1da44bba	IPEX fix custom_fwd x2	2024-08-18 05:22:11 +03:00
Disty0	b862400ea2	IPEX fix AMP custom_fwd	2024-08-18 05:11:00 +03:00
Disty0	0734c75ef4	Add Heun FlowMatch	2024-08-18 02:17:55 +03:00
Disty0	a3f26c9df0	Convert Dynamic Attention SDP to a global SDP option	2024-08-18 01:44:27 +03:00
Disty0	5c857e8aaf	Add check for Flux attention processor	2024-08-18 00:35:10 +03:00
Disty0	bce3c7eabf	Fix --Xvram flags not activating offload	2024-08-18 00:23:15 +03:00
Disty0	5a75b120ae	Fix Lora with Balanced Offlaod	2024-08-16 21:22:41 +03:00
Disty0	3f5c3ba0d8	Add warning to Quanto with balanced and sequential offload	2024-08-16 02:58:43 +03:00
Disty0	7a6b45b410	Balanced offload move device map calcs	2024-08-16 02:49:42 +03:00
Disty0	80be079130	Flux load quant model to cpu	2024-08-15 22:17:41 +03:00
Disty0	f3f721e39a	Quanto disable gemm kernels	2024-08-14 20:26:46 +03:00
Disty0	237cab2aa1	Add offload check to cascade's vqgan	2024-08-14 17:42:49 +03:00
Disty0	8699e0cacb	Add gc to balanced offload	2024-08-14 17:37:07 +03:00
Disty0	119c37212d	More offload checks	2024-08-14 17:27:10 +03:00
Disty0	7edc864014	Add module name to disk offload path	2024-08-14 12:21:54 +03:00