stduhpf
138da14cc3
apg: normalize diff_norm calculation by tensor size ( #1620 )
2026-06-08 21:56:15 +08:00
fszontagh
17a2b4a315
perf: cap planner budget when model dwarfs the streaming budget ( #1612 )
2026-06-08 21:53:54 +08:00
leejet
b3d56d0ba1
refactor: split model loader from model definitions ( #1619 )
2026-06-07 23:20:12 +08:00
leejet
2a07540c2a
refactor: move photomaker into generation extension ( #1618 )
2026-06-07 22:40:02 +08:00
Wagner Bruna
81abfb2548
chore: rename and reformat gits_noise.inl ( #1617 )
2026-06-07 22:30:20 +08:00
leejet
f3fd359b58
refactor: reorganize src model layout ( #1615 )
2026-06-07 03:21:12 +08:00
leejet
dfb2390dd4
refactor: extract Wan VAE implementation ( #1614 )
2026-06-07 01:33:49 +08:00
leejet
cfbc19d186
refactor: unify model config detection ( #1613 )
2026-06-07 01:05:12 +08:00
leejet
b9254dda0d
feat: add ideogram4 support ( #1609 )
2026-06-06 16:34:16 +08:00
fszontagh
0648f4426b
perf: ratchet streaming budget so plan stops re-merging every step ( #1611 )
2026-06-06 16:32:03 +08:00
YOSHIDA Keiji
74f513d512
fix: Suppress spurious error output for --help ( #1607 ) ( #1608 )
...
Signed-off-by: kei-g <km.8k6ce+github@gmail.com>
2026-06-06 16:23:44 +08:00
fszontagh
064001b524
perf: allocate CPU-offloaded params from runtime device pinned host buffer ( #1601 )
2026-06-06 16:22:18 +08:00
leejet
1f9ee88e09
fix: zero Wan2.2 TI2V timesteps for fixed frames ( #1604 )
2026-06-03 23:32:31 +08:00
fszontagh
a7f2e03da4
perf: keep chunk-K residency engaged with runtime LoRA ( #1598 )
2026-06-03 23:12:00 +08:00
stduhpf
4513e3fda9
refactor: img-cond->img_uncond ( #1594 )
...
* refactor: img-cond->img_uncond
* align APG and CFG++ with img-uncond CFG
* set default img_cfg to 1.f
---------
Co-authored-by: leejet <leejet714@gmail.com>
2026-06-03 22:57:42 +08:00
leejet
2d40a8b2ad
feat: make Wan2.2 5B FLF2V work ( #1110 )
2026-06-02 23:16:09 +08:00
leejet
9c7f9a20b3
chore: embed server web UI in Docker images ( #1597 )
2026-06-02 22:46:25 +08:00
fszontagh
ed74577c40
feat: --stream-layers for streaming weights from CPU during generation ( #1576 )
2026-06-02 22:35:28 +08:00
RapidMark
7948df8ac1
fix(cmake): build HIP backend with PIC so the static-lib PIE link succeeds ( #1593 )
2026-06-02 00:07:48 +08:00
Wagner Bruna
02f06370a7
refactor: call CPU backend functions dynamically ( #1591 )
...
Co-authored-by: leejet <leejet714@gmail.com>
2026-06-01 23:41:21 +08:00
stduhpf
f8935d6f25
feat: support img-cfg for edit models ( #929 )
...
Co-authored-by: leejet <leejet714@gmail.com>
2026-06-01 22:54:25 +08:00
stduhpf
be65ac7511
feat: add support for APG (adaptive projected guidance) + unconditionnal SLG ( #593 )
2026-06-01 00:55:49 +08:00
leejet
20901f6d8e
fix: remove kv padding from flash attention wrapper ( #1453 )
2026-05-31 23:23:19 +08:00
leejet
0982807139
feat: add PiD support ( #1585 )
2026-05-31 22:38:39 +08:00
leejet
d2797b8667
fix: correct Gemma3 rope settings and vram limit propagation ( #1583 )
2026-05-30 22:23:49 +08:00
leejet
d3b2cb047e
fix: split tokens before normalization ( #1582 )
2026-05-30 18:38:46 +08:00
akleine
b4ba55d8d7
fix: prevent crash in case of a mem alloc error and graceful exit ( #1566 )
2026-05-30 18:34:07 +08:00
Wagner Bruna
b54bd83a3f
fix: explicitly exclude f8, f64 and i64 tensors from mmap ( #1575 )
2026-05-30 18:31:08 +08:00
Wagner Bruna
0e4ee04488
fix: correct tae for models that use the flux2 vae ( #1571 )
2026-05-28 09:13:16 +08:00
leejet
29ab511fc7
fix: resolve LLM norm tensor names by architecture ( #1570 )
2026-05-28 00:36:16 +08:00
leejet
55c2aed52c
refactor: simplify diffusion model runner params ( #1569 )
2026-05-28 00:12:35 +08:00
leejet
8eded497e5
fix: preserve frontend tooling in ROCm CI build ( #1568 )
2026-05-27 21:26:16 +08:00
leejet
92dc7268fc
feat: add microsoft lens support ( #1560 )
2026-05-27 01:04:17 +08:00
schirik
07b2b18e70
fix: skip permission denied errors in recursive_directory_iterator ( #1564 )
...
Co-authored-by: Serge F. Chirik <s.chirik@timbel.info>
2026-05-27 00:56:16 +08:00
leejet
1ceb5bd9df
fix: package ROCm BLAS runtime in Windows artifacts ( #1562 )
2026-05-26 00:57:37 +08:00
leejet
202c6154a2
fix: use flux flow prediction for LTXAV ( #1561 )
2026-05-26 00:23:39 +08:00
stduhpf
a397e03488
feat: add Longcat-Image / Longcat-Image-Edit support ( #1053 )
...
Co-authored-by: leejet <leejet714@gmail.com>
2026-05-24 02:02:02 +08:00
leejet
72e512a0cc
fix: make macOS binaries use relocatable rpaths ( #1552 )
2026-05-23 12:27:06 +08:00
leejet
0baf721215
feat: add LTX temporal latent upscaler support ( #1551 )
2026-05-23 01:35:13 +08:00
leejet
645e6e9089
feat: add LTX rational latent upscaler ( #1549 )
2026-05-23 00:28:15 +08:00
stduhpf
cbf92191c3
fix: strip trailing latent channels for preview decode ( #1548 )
2026-05-23 00:26:40 +08:00
stduhpf
8cf55a3b3b
fix: load TAESD preview-only model correctly ( #1547 )
2026-05-23 00:22:35 +08:00
leejet
3a8788cb7d
refactor: unify extra argument parsing ( #1540 )
2026-05-22 01:00:03 +08:00
leejet
449165caf5
feat: stream LTX VAE temporal tile decoding ( #1539 )
2026-05-22 00:25:04 +08:00
stduhpf
adaa599a3b
Feat: Temporal tile custom size with overlap ( #1510 )
...
* Temporal tile size + overlap
* add --extra-tiling-args support
---------
Co-authored-by: leejet <leejet714@gmail.com>
2026-05-21 23:44:12 +08:00
leejet
2e3514625a
perf: run LTX audio VAE decode in one ggml graph ( #1538 )
2026-05-21 22:43:14 +08:00
stduhpf
47d8198b69
feat: add taeltx2_3_wide support ( #1535 )
2026-05-21 22:34:12 +08:00
leejet
ef92a0027e
feat: add graph cut markers for LTXAV transformer ( #1534 )
2026-05-20 23:22:10 +08:00
leejet
b3374e6a71
feat: add LTX spatial latent upscale hires support ( #1533 )
2026-05-20 22:27:09 +08:00
stduhpf
bdd937f29a
feat: add taeltx2/taeltx2.3 support ( #1531 )
2026-05-20 22:14:05 +08:00
