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
fszontagh
ed74577c40
feat: --stream-layers for streaming weights from CPU during generation ( #1576 )
2026-06-02 22:35:28 +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
92dc7268fc
feat: add microsoft lens support ( #1560 )
2026-05-27 01:04:17 +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
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
stduhpf
c51ec7cad9
fix: always load runtimle lora params on runtime backend ( #1532 )
2026-05-20 22:13:15 +08:00
leejet
5b0267e941
fix: avoid Vulkan f16 repeat in LTX audio VAE ( #1528 )
2026-05-19 23:15:26 +08:00
leejet
b706d682ad
fix: restore singleton dims for LLM outputs ( #1518 )
2026-05-18 23:47:10 +08:00
leejet
b758b7de13
fix: only enable TAE after successful load ( #1517 )
2026-05-18 23:32:03 +08:00
Wagner Bruna
f683c88a28
feat: make negative max_vram control the amount of spare vram ( #1503 )
2026-05-18 23:00:06 +08:00
leejet
baf7eda1e4
refactor: minify vocab files ( #1509 )
2026-05-17 23:06:58 +08:00
Wagner Bruna
e7eb92fd84
feat: add Gradient Estimation sampler ( #1484 )
2026-05-17 22:54:28 +08:00
leejet
50134e51dd
refactor: split guidance composition ( #1506 )
2026-05-17 20:20:16 +08:00
leejet
e43b24cf48
feat: add ltx2.3 flf2v support ( #1505 )
2026-05-17 18:40:14 +08:00
stduhpf
06accf2b39
feat: add ltxav latent2rgb projection matrix ( #1502 )
2026-05-17 17:52:05 +08:00
stduhpf
cde20d5ef0
fix: handle stereo format in sd_audio ( #1489 )
...
Co-authored-by: leejet <leejet714@gmail.com >
2026-05-17 16:55:39 +08:00
leejet
67dda3f897
feat: add ltx2.3 support ( #1463 )
...
* add GemmaTokenizer
* add basic ltx2.3 support
* change vocab file encoding
* fix ci
* fix ubuntu build
* add temporal tiling support
* add ltx audio support
* update ggml submodule url
* fix generate_video
* add i2v support
* minify bundled Gemma tokenizer vocab sources
* pass video fps into temporal rope embeddings
* fix av_ca_timestep_scale_multiplier
* add LTX2Scheduler support
* update docs
* fix ci
2026-05-17 16:46:20 +08:00
leejet
d7ecbe1d01
fix: avoid repeated T5 EOS tokens in Anima prompt weights ( #1501 )
2026-05-16 21:22:46 +08:00
leejet
36330724bd
feat: add module backend assignment support ( #1500 )
...
Co-authored-by: Stéphane du Hamel <stephduh@live.fr >
2026-05-16 20:27:06 +08:00
leejet
38b14adb67
feat: auto-detect max VRAM budget with --max-vram -1 ( #1498 )
2026-05-16 16:14:25 +08:00
Wagner Bruna
fd1a2794f3
refactor: unify Euler, Euler Ancestral and DDIM implementations ( #1474 )
2026-05-16 16:13:28 +08:00
Wagner Bruna
686856edca
chore: do not report the fake VAE "allocation" as an error ( #1494 )
2026-05-16 16:08:31 +08:00
