296 Commits

Author	SHA1	Message	Date
leejet	2540a4fc25	feat: use backend-native FP8 matmul when supported (#1916)	2026-08-30 20:19:56 +08:00
jk212h20	dc4000d9f8	fix: correct MiniMax H3 audio Euler steps (#1908)	2026-08-30 20:19:28 +08:00
jk212h20	c797899732	fix: correct MiniMax H3 reference audio encoding (#1886)	2026-08-30 19:33:59 +08:00
Piotr Wilkin (ilintar)	afd5306d88	feat: add LTX-2.5 support (#1893) ... Co-authored-by: leejet <leejet714@gmail.com>	2026-08-30 19:13:06 +08:00
leejet	2c929495ab	fix: match exact weights in LLM config detection (#1923)	2026-08-30 17:43:41 +08:00
leejet	be0e34480d	feat: load scaled FP8 weights without upfront conversion (#1913)	2026-08-27 20:50:47 +08:00
leejet	50d6405683	feat: support standard Qwen3-VL weights for MiniMax-H3 (#1910)	2026-08-26 00:13:33 +08:00
vmobilis	12ee60dc02	fix: use sd_get_preview_interval() (#1907)	2026-08-26 00:05:46 +08:00
leejet	97d2990807	chore: format code	2026-08-19 23:06:07 +08:00
vmobilis	16304cc3fd	fix: guard against missing sampler/scheduler names (#1887)	2026-08-19 22:31:19 +08:00
vmobilis	760717a060	fix: make max_order of lms sampler configurable (#1885)	2026-08-19 22:29:29 +08:00
Wagner Bruna	88b044be7f	fix: mark graph cuts with both a prefix and a suffix (#1883)	2026-08-19 22:27:48 +08:00
fszontagh	1706b32813	fix: re-clamp streaming VRAM budget to currently free memory (#1878)	2026-08-19 22:21:21 +08:00
fszontagh	58b6cb6b0c	fix: prevent gallocr hash overflow in tiny graph-cut segments (#1880)	2026-08-19 22:20:21 +08:00
stduhpf	6100d8339b	feat: add taeh3 support (#1874)	2026-08-19 22:18:19 +08:00
LostRuins Concedo	06c359f17a	fix: replace free_compute_buffer with runner_done in vae (#1872)	2026-08-12 23:39:57 +08:00
leejet	bcc7e29568	feat: support INT8 ConvRot safetensors (#1857)	2026-08-11 23:45:02 +08:00
Daniel Han	487de75c96	fix: fail with a message when MiniMax-H3 is run in img_gen mode (#1863)	2026-08-11 23:22:20 +08:00
stduhpf	b4f1fd6d7f	fix: preserve "token_refiner" token for MiniMax H3 LoRAs (#1864)	2026-08-11 22:57:05 +08:00
leejet	c6beeef355	fix: map Qwen3-VL DeepStack GGUF tensor names (#1858)	2026-08-06 01:50:55 +08:00
stduhpf	bfbef5b7e6	feat: trained Minimax VAE Latent2rgb proj (#1856)	2026-08-06 01:39:10 +08:00
leejet	ea7f0c87cf	feat: add minimax-h3 support (#1854)	2026-08-04 23:14:18 +08:00
leejet	db99efdd6d	refactor: extract model loader initialization (#1844)	2026-08-02 17:24:10 +08:00
vmobilis	eb7f35ca49	feat: add linear multi-step sampling method (#1843)	2026-08-02 16:19:47 +08:00
fszontagh	50062a4bba	feat: add IP-Adapter Plus (Resampler image projection) support (#1839)	2026-08-02 16:15:28 +08:00
stduhpf	8457624101	feat: support more LoRA models (Kroma-v0.1 support) (#1842)	2026-08-02 16:08:47 +08:00
stduhpf	10378f42db	fix: lora with split qkv compatibility check at runtime (#1836) ... Co-authored-by: leejet <leejet714@gmail.com>	2026-08-02 16:08:08 +08:00
leejet	e31a86ce91	refactor: centralize CLIP prefix conversion (#1837)	2026-07-30 22:44:31 +08:00
akleine	735a4ef520	fix(PhotoMaker): avoid GGML_ASSERT if trigger word 'img' was not found in prompt (#1835)	2026-07-30 21:26:57 +08:00
Wagner Bruna	af92790ffc	feat: allow customizing the alpha and beta parameters of the beta scheduler (#1834)	2026-07-30 21:24:51 +08:00
leejet	e92e86fb11	fix: prevent torch checkpoint offset overflow (#1832)	2026-07-29 23:16:29 +08:00
vmobilis	9cfe2af8f9	feat: display number of tokens for SD models (#1831)	2026-07-29 22:21:54 +08:00
yzyyzyhhh	2993b7fb43	fix: make parameter loading backend-aware (#1828)	2026-07-29 22:18:44 +08:00
Nicky Mouha	53856e7ec8	fix: null pointer dereference when loading malformed LoHa file (#1826)	2026-07-29 21:53:26 +08:00
leejet	22516991cb	fix: skip incompatible LoRA weights (#1825)	2026-07-28 00:06:46 +08:00
vmobilis	2d0385ba85	fix: add missing sampler names (#1819)	2026-07-26 22:58:05 +08:00
leejet	87a01773be	fix: add frame dimension for Hunyuan IMG2VID encoding (#1816)	2026-07-24 22:37:26 +08:00
leejet	b0f856804c	fix: correct IP-Adapter CFG conditioning and defaults (#1815)	2026-07-24 22:01:54 +08:00
Wagner Bruna	b8bf67615c	fix: correct dangling pointer to empty image reference vector (#1813)	2026-07-24 21:20:33 +08:00
fszontagh	8d377073e3	feat: add IP-Adapter support for SD 1.5 and SDXL (#1803)	2026-07-24 21:19:44 +08:00
fszontagh	5114672c48	fix: detect vision patch size for unsplit (HF-format) Qwen3-VL (#1811)	2026-07-23 22:22:21 +08:00
leejet	8a51eb9284	feat: add Mage-Flow support (#1808)	2026-07-23 01:23:25 +08:00
leejet	35fb21f3e0	fix: avoid structured binding capture in Hunyuan config (#1809)	2026-07-23 01:23:03 +08:00
Wagner Bruna	2961182365	chore: add missing override declarations (#1800)	2026-07-21 22:49:52 +08:00
leejet	ea4e566ccf	feat: add hunyuan video 1.5 support (#1795)	2026-07-18 22:30:10 +08:00
leejet	b290693977	feat: add PiD 1.5 support (#1790)	2026-07-17 01:35:18 +08:00
fszontagh	7717e82c00	feat(animatediff): support img2video via --init-img (#1789)	2026-07-17 01:24:12 +08:00
leejet	a8a91b24cd	feat: add ADetailer support (#1785)	2026-07-14 23:59:11 +08:00
fszontagh	c00a9e956d	feat: AnimateDiff SD 1.5 motion modules (v2 + v3) (#1784)	2026-07-14 23:58:03 +08:00
stduhpf	833369da84	fix: protect cross_attn and output_proj tokens for Anima LoRAs (#1786)	2026-07-14 22:59:07 +08:00