582 commits

Author	SHA1	Message	Date
Wagner Bruna	5c40f07d4a	sd: sync to 0752cc9 (master-507-b314d80 +1) (#1999) ... * sd: sync to 0752cc9 (master-507-b314d80 +1) * sd: add flow-shift support to gendefaults	2026-02-28 12:22:32 +08:00
Concedo	d643d945f5	clamp music inference steps to 100 max	2026-02-28 12:12:50 +08:00
Concedo	14d82bb38e	allow music llm and diffusion gen models to be loaded independently	2026-02-27 21:56:48 +08:00
Concedo	19eb78844c	audio codes working	2026-02-27 21:23:00 +08:00
Concedo	ba42f22fc8	stereo is working	2026-02-27 20:36:44 +08:00
Concedo	5a57ed8ca4	revert to 8 step	2026-02-26 22:07:01 +08:00
Concedo	173702d1a4	music lowvram indicator	2026-02-26 21:30:47 +08:00
Concedo	adebf63877	ace converter	2026-02-26 19:53:02 +08:00
Concedo	ac8f12f259	still a bit wonky	2026-02-26 17:50:49 +08:00
Concedo	81fb4d773c	swap resampling function	2026-02-26 17:37:53 +08:00
Concedo	fb3f7d92bc	reenable cfg	2026-02-26 14:51:15 +08:00
Concedo	b7d2fe68e7	adjust	2026-02-26 14:46:41 +08:00
Concedo	edbc4fe592	music lm finally working	2026-02-26 14:00:58 +08:00
Concedo	cf042af701	Revert "still not working" ... This reverts commit a1305ffff9.	2026-02-26 10:55:55 +08:00
Concedo	a1305ffff9	still not working	2026-02-26 10:48:21 +08:00
Concedo	d8746a851f	still bugged	2026-02-26 00:07:04 +08:00
Concedo	8a3ccfcba5	some fixes but some issues	2026-02-25 23:41:32 +08:00
Concedo	0eafc3cf2d	ace step lowvram mode done, improved	2026-02-24 23:12:26 +08:00
Concedo	11a85d62fc	lowvram for music lm	2026-02-24 22:21:17 +08:00
Concedo	aa58d1ed3b	all working, but needs to optimize vram	2026-02-24 21:55:57 +08:00
Concedo	488c431331	not yet working	2026-02-24 17:47:50 +08:00
Concedo	0fd7d2c0e5	ace step diffusion loading	2026-02-24 15:24:15 +08:00
Concedo	749536f464	fixed wav header wrong size	2026-02-24 01:13:44 +08:00
Concedo	5311997581	updated ace step cpp	2026-02-23 23:01:10 +08:00
Concedo	2e713cfff5	fixed compile issue, trying out 8bit pcm	2026-02-23 21:19:03 +08:00
Wagner Bruna	a6c0a224b2	sd: sync to master-506-c9cd497 (#1991)	2026-02-23 17:35:59 +08:00
Concedo	c2b0cb26a8	ace step codes api	2026-02-23 14:04:45 +08:00
Concedo	4be93db21c	ace step codes generation now working	2026-02-23 00:27:26 +08:00
Concedo	13db5aee9e	stub files for loading ace step	2026-02-22 23:15:08 +08:00
Concedo	37ae068dee	set default to GPU test	2026-02-22 17:03:43 +08:00
Concedo	fdf868f397	add ace step cpp license info	2026-02-22 13:24:28 +08:00
Concedo	5cd6e50eab	initial files for ace step	2026-02-22 13:22:24 +08:00
Wagner Bruna	19588f18ea	sd: relax size restrictions for DiT models (#1986) ... Round image dimensions to the specific multiple required by each DiT model, which range from 32 (certain Wan models) to 1 (Chroma Radiance), with most requiring multiples of 8 or 16. Unet models keep being rounded to multiples of 64. Current sd.cpp rounds the sizes internally; but it always rounds up, so we still need to round on our side to apply image size restrictions, and to trigger VAE tiling correctly. Also, remove a legacy test that could abort a generation with unsupported image sizes: it'd never run, because it was applied after the image side adjustements.	2026-02-22 11:00:10 +08:00
Concedo	78b4b87e54	fixed compile issue for tts on ci (+1 squashed commits) ... Squashed commits: [d6f778499] fixed compile issue for tts on ci	2026-02-22 02:28:11 +08:00
Concedo	7068a74998	tts upstream bugfix	2026-02-22 00:46:03 +08:00
Concedo	313d37a602	cache used voices	2026-02-22 00:43:57 +08:00
Concedo	5536fb29f2	add some default voices for qwen3tts	2026-02-21 23:45:15 +08:00
Concedo	2db018a1d7	qwen3tts support reference audio	2026-02-21 17:30:21 +08:00
Concedo	72219fdbf5	basic qwen3 tts working	2026-02-21 12:03:53 +08:00
Concedo	1af7095cb5	add qwen3 tts repo files	2026-02-21 10:54:55 +08:00
Concedo	81065fd801	fix ci build error	2026-02-20 21:32:07 +08:00
Concedo	4115f1c54d	fixed tts for outetts	2026-02-20 14:27:36 +08:00
Concedo	bf3f2e1ba8	support loading multiple sd loras (up to 4 at once)	2026-02-19 13:57:58 +08:00
Concedo	83f905919b	flash attention is broken on qwen image edit. disabled conditioner to fix (+1 squashed commits) ... Squashed commits: [1b705cb6e] flash attention is broken on qwen image edit. disabled conditioner to fix	2026-02-14 11:59:03 +08:00
Wagner Bruna	ae5183be10	sd: sync to master-504-636d3cb (#1969) ... * sd: sync to master-504-636d3cb * sd: fix and simplify limit calculation - restore the "arbitrarily high" 8192 limit, since it's used to turn off the img_hard_limit (and if each side was always limited by 2048, we wouldn't need hard_megapixel_res_limit) - avoid changing the config cfg_square_limit during a generation - apply the hard_megapixel_res_limit only in the configuration-changed path, since the default path uses constants - clean up comments The calculation itself remains the same: - default area limit: 832² for SD1.5/SD2, 1024² otherwise - configured limit always between 64 and 2048	2026-02-14 08:12:08 +08:00
Concedo	5b54fee042	fixed compile issue	2026-02-13 12:22:26 +08:00
Concedo	58ebff4c74	adjust soft clamp	2026-02-12 21:31:45 +08:00
Concedo	cb5755bc96	reworked soft limit default restrictions for sd image gen	2026-02-12 17:53:04 +08:00
Wagner Bruna	c2d96328fe	sd: sync to master-493-65891d7 (#1960)	2026-02-05 22:11:47 +08:00
Wagner Bruna	d9ac52a01a	sd: sync to master-492-f957fa3 (#1957) ... * sd: sync to master-492-f957fa3 * add Res Multistep and Res 2s samplers * make sdflashattention control flash_attn too	2026-02-04 16:12:39 +08:00