Commit Graph

186 Commits

Author SHA1 Message Date
m00dy
4fcc6fef10 fix: reject a repeated entry with an inconsistent value count in load_imatrix (#1749) (#1750) 2026-07-06 22:11:27 +08:00
fszontagh
9e1055d2e3 fix: SDXL ControlNet (diffusers naming + graph size) (#1752) 2026-07-06 22:06:58 +08:00
fszontagh
e071aa390b feat: move circular padding from context to per-generation params (#1748) 2026-07-06 22:04:20 +08:00
leejet
2abbc773ac fix: use larger image VAE encode tiles (#1744) 2026-07-05 18:27:07 +08:00
Shikaku2
da6db07c5c feat: stream model conversion (#1581) 2026-07-05 17:46:07 +08:00
fszontagh
e9dee542c4 feat: add DPM++ 2M SDE (Brownian tree) sampler (#1743) 2026-07-05 17:32:43 +08:00
stduhpf
c60b36af0f feat: denoise strength as starting noise level (#1738) 2026-07-05 16:24:46 +08:00
fszontagh
38a51f8105 feat: add DPM++ 2M SDE sampler (#1742) 2026-07-05 16:13:25 +08:00
leejet
e790073e1c fix: avoid layer splitting unet block paths (#1741) 2026-07-05 15:43:12 +08:00
Piotr Wilkin (ilintar)
b11c95a41c feat: auto fit tensors across devices to guarantee optimal load (#1736) 2026-07-05 00:48:10 +08:00
Piotr Wilkin (ilintar)
68f3d6df9f feat: support for cross-device row split (#1735) 2026-07-04 16:31:18 +08:00
Piotr Wilkin (ilintar)
7bcd189639 feat: add multi-device layer split (--backend "diffusion=cuda0&cuda1") (#1734) 2026-07-04 16:06:33 +08:00
leejet
2574f59365 fix: fallback when backend rejects flash attention (#1732) 2026-07-03 00:46:51 +08:00
mmandelker-code
7dab3668d0 fix: enable Wan/TAEHV video generation on the Metal backend (#850) (#1731) 2026-07-03 00:38:13 +08:00
leejet
556f04bb3f feat: add qwen image layered support (#1119) 2026-07-03 00:21:22 +08:00
KenForever
3590aa8d62 feat: add MiniT2I support (#1683) 2026-07-02 00:46:51 +08:00
stduhpf
1a13107bac feat: add imatrix support (#633) 2026-07-01 23:26:37 +08:00
Erik Scholz
484baa41e5 feat: add beta scheduler (#811)
Co-authored-by: phil2sat <phil2sat@users.noreply.github.com>
2026-07-01 01:40:22 +08:00
leejet
2bb0389683 refactor: return bool from image and upscale APIs (#1728) 2026-07-01 01:11:56 +08:00
Cyberhan123
ccda89e09c feat: make ffi for same shape (#1635) 2026-07-01 00:30:16 +08:00
leejet
f0271076ad chore: strip UTF-8 BOMs and add cleanup script (#1726) 2026-06-30 22:32:45 +08:00
leejet
3b6c9ca97c feat: add normal alias for discrete scheduler (#1724) 2026-06-30 00:19:21 +08:00
leejet
57e19fa954 feat: add Flux scheduler (#1723) 2026-06-29 23:49:56 +08:00
leejet
61a637bfd5 feat: add Flux2 scheduler (#1722) 2026-06-29 23:17:31 +08:00
stduhpf
3ec374aecc fix: avoid crash and warn when using Qwen 2D VAE for Wan video (#1721) 2026-06-29 21:44:05 +08:00
leejet
9f855c933b chore: silence narrowing conversion warnings (#1717) 2026-06-28 23:14:53 +08:00
stduhpf
7b5f34d93e feat: support Qwen2D VAE (#1714) 2026-06-28 22:50:57 +08:00
stduhpf
d77b8f5ee8 feat: support Qwen-Image/Wan VAE with diffusers naming (#1713) 2026-06-28 22:50:12 +08:00
fszontagh
03e9a22f4d feat: add SeFi-Image support (#1707) 2026-06-28 22:49:24 +08:00
leejet
9956436c92 refactor: consolidate WAN VAE version checks (#1712) 2026-06-27 01:23:37 +08:00
Wagner Bruna
ec4cb8104b fix: correct TAEHV encoding for image models (#1711) 2026-06-27 01:23:18 +08:00
Daniele
3973015ed7 sync: update ggml and revert vulkan workarounds for Anima and Ernie (#1710) 2026-06-27 00:52:32 +08:00
leejet
8caa3f908a feat: add krea2 support (#1705) 2026-06-25 00:25:50 +08:00
stduhpf
2938272d82 feat: add logit-normal scheduler (#1669) 2026-06-25 00:06:11 +08:00
leejet
f440ad9c29 fix: avoid writable mmap for read-only weights (#1698) 2026-06-23 00:39:31 +08:00
stduhpf
41f7acbfb0 feat: support guidance_schedule (#1684) 2026-06-23 00:05:55 +08:00
leejet
b395a6972d refactor: add Flux VAE version helper (#1696) 2026-06-22 22:39:42 +08:00
fszontagh
787d229d84 perf: --eager-load to pre-load params at model-load time (#1687) 2026-06-22 22:10:09 +08:00
leejet
b12098f5d0 feat: add boogu image support (#1688) 2026-06-22 00:36:17 +08:00
Daniele
e9e952462f fix: workaround for Ernie with Vulkan and Flash Attention (#1680) 2026-06-22 00:21:38 +08:00
Wagner Bruna
e8e012eef2 fix: workaround for Anima with Vulkan and Flash Attention (#1678) 2026-06-22 00:20:00 +08:00
leejet
7f0e728b7d fix: normalize CLIP prompts before special-token splitting (#1670) 2026-06-17 00:33:00 +08:00
Wagner Bruna
710bc91c8f fix: correct conversion from sd_type_t to ggml_type (#1519) 2026-06-16 23:54:42 +08:00
Wagner Bruna
5a34bc7f6e feat: support for cancelling generations (#1124)
* feat: support for canceling the ongoing generation

* return partial image batches on cancel

---------

Co-authored-by: leejet <leejet714@gmail.com>
2026-06-16 00:36:38 +08:00
leejet
146b6cc49e fix: simplify PuLID ID extraction setup (#1664) 2026-06-15 23:55:38 +08:00
RapidMark
93527fda74 feat: add PuLID-Flux identity-injection support (#1595) 2026-06-15 23:33:50 +08:00
leejet
6e66a1a4a4 fix: allow oversized Vulkan parameter tensors (#1662) 2026-06-15 23:18:52 +08:00
leejet
bb90bfa00f feat: support backend-specific max-vram budgets 2026-06-14 22:46:32 +08:00
stduhpf
c2df4e1228 feat: add RPC support (#1629) 2026-06-14 17:30:23 +08:00
leejet
9838264c49 refactor: simplify ControlNet output caching (#1655) 2026-06-14 16:58:37 +08:00