leejet
|
82e03ef137
|
ci: add inactive pr clean up workflow
|
2026-05-18 00:09:45 +08:00 |
|
leejet
|
baf7eda1e4
|
refactor: minify vocab files (#1509)
master-621-baf7eda
|
2026-05-17 23:06:58 +08:00 |
|
Wagner Bruna
|
e7eb92fd84
|
feat: add Gradient Estimation sampler (#1484)
master-620-e7eb92f
|
2026-05-17 22:54:28 +08:00 |
|
leejet
|
50134e51dd
|
refactor: split guidance composition (#1506)
master-619-50134e5
|
2026-05-17 20:20:16 +08:00 |
|
leejet
|
e43b24cf48
|
feat: add ltx2.3 flf2v support (#1505)
master-618-e43b24c
|
2026-05-17 18:40:14 +08:00 |
|
stduhpf
|
06accf2b39
|
feat: add ltxav latent2rgb projection matrix (#1502)
master-617-06accf2
|
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>
master-616-cde20d5
|
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
master-615-67dda3f
|
2026-05-17 16:46:20 +08:00 |
|
Mario Limonciello
|
3b4d26f3d9
|
ci: update ROCm builds for Windows and Linux to use ROCm 7.13 (#1504)
|
2026-05-17 16:32:19 +08:00 |
|
Taylor
|
bd17f53b73
|
docs: update zit example to 8 steps (#1294)
|
2026-05-16 21:32:03 +08:00 |
|
leejet
|
d7ecbe1d01
|
fix: avoid repeated T5 EOS tokens in Anima prompt weights (#1501)
master-612-d7ecbe1
|
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>
master-611-3633072
|
2026-05-16 20:27:06 +08:00 |
|
Mario Limonciello
|
0c1ca170ca
|
ci: update ROCm Windows builds (#1282)
master-610-0c1ca17
|
2026-05-16 20:25:38 +08:00 |
|
Mario Limonciello
|
839f6a94d2
|
ci: switch over ROCm builds to artifacts both for stable and preview releases (#1281)
|
2026-05-16 20:23:26 +08:00 |
|
leejet
|
38b14adb67
|
feat: auto-detect max VRAM budget with --max-vram -1 (#1498)
master-608-38b14ad
|
2026-05-16 16:14:25 +08:00 |
|
Wagner Bruna
|
fd1a2794f3
|
refactor: unify Euler, Euler Ancestral and DDIM implementations (#1474)
master-607-fd1a279
|
2026-05-16 16:13:28 +08:00 |
|
cphlipot
|
db08b84607
|
fix: Fix broken GCC 16 build (enforce C11/C++17 compile ) (#1478)
master-606-db08b84
|
2026-05-16 16:10:16 +08:00 |
|
Wagner Bruna
|
686856edca
|
chore: do not report the fake VAE "allocation" as an error (#1494)
master-605-686856e
|
2026-05-16 16:08:31 +08:00 |
|
leejet
|
0b8296915c
|
docs: add .github/pull_request_template.md
|
2026-05-15 01:16:21 +08:00 |
|
leejet
|
381e0df50f
|
docs: add CONTRIBUTING.md
|
2026-05-15 01:09:45 +08:00 |
|
leejet
|
0665a7f8bf
|
feat: add hidream o1 image support (#1485)
master-602-0665a7f
|
2026-05-15 00:40:21 +08:00 |
|
Craig Andrews
|
eeac950b44
|
fix: Use PkgConfig for WebP and WebM (#1400)
master-601-eeac950
|
2026-05-15 00:31:10 +08:00 |
|
Wagner Bruna
|
57ff2eb0f4
|
feat: support for memory-mapping model weights (#1414)
Co-authored-by: Piotr Wilkin <piotr.wilkin@syndatis.com>
Co-authored-by: Junmo Kim <me@junmo.kim>
Co-authored-by: leejet <leejet714@gmail.com>
master-600-57ff2eb
|
2026-05-15 00:30:03 +08:00 |
|
Daniele
|
9d683417cb
|
feat: add Euler CFG++ and Euler-A CFG++ samplers (#1354)
master-599-9d68341
|
2026-05-15 00:29:04 +08:00 |
|
l8bloom
|
60477fd50f
|
docs: add new go bindings for stable-diffusion.cpp (#1480)
|
2026-05-14 23:59:06 +08:00 |
|
cphlipot
|
6ee0684d74
|
feat: display server url with "http://" prefix. (#1486)
master-597-6ee0684
|
2026-05-14 23:57:22 +08:00 |
|
leejet
|
90e87bc846
|
feat: add max-vram based segmented param offload (#1476)
master-596-90e87bc
|
2026-05-06 21:56:02 +08:00 |
|
Wagner Bruna
|
586b6f1481
|
feat: adapt res samplers for flow models for eta > 0 (#1436)
master-595-586b6f1
|
2026-05-06 21:49:06 +08:00 |
|
fszontagh
|
9097ce5211
|
fix: skip empty MultiLoraAdapter when no LoRAs target a model (#1469)
master-594-9097ce5
|
2026-05-06 21:45:47 +08:00 |
|
leejet
|
3d6064b37e
|
perf: speed up tensor_to_sd_image conversion (#1466)
master-593-3d6064b
|
2026-04-30 01:13:56 +08:00 |
|
Wagner Bruna
|
b8079e253d
|
feat: transition from compile-time to runtime backend discovery (#1448)
Co-authored-by: Stéphane du Hamel <stephduh@live.fr>
Co-authored-by: Cyberhan123 <255542417@qq.com>
Co-authored-by: leejet <leejet714@gmail.com>
master-592-b8079e2
|
2026-04-29 23:26:57 +08:00 |
|
Wagner Bruna
|
331cfa5387
|
fix: release VAE compute buffer after tiled encoding (#1465)
master-591-331cfa5
|
2026-04-29 22:25:30 +08:00 |
|
Douglas Griffith
|
a81677f59c
|
docs: performance tips markup (#1460)
|
2026-04-27 22:55:30 +08:00 |
|
leejet
|
f40a707d0f
|
feat: add sdcpp-specific generation metadata to image outputs (#1462)
master-589-f40a707
|
2026-04-27 22:43:13 +08:00 |
|
akleine
|
970c4a3312
|
chore: replace some NULL with nullptr + use "%zu" for printing some size_t data (#1457)
master-588-970c4a3
|
2026-04-27 22:42:57 +08:00 |
|
leejet
|
b8bdffc199
|
feat: add more built-in highres upscalers (#1456)
master-587-b8bdffc
|
2026-04-23 22:17:58 +08:00 |
|
leejet
|
c97702e105
|
feat: add sd-webui style Hires. fix support (#1451)
master-586-c97702e
|
2026-04-22 23:51:09 +08:00 |
|
leejet
|
44cca3d626
|
feat: support safetensors export in convert mode (#1444)
master-585-44cca3d
|
2026-04-20 00:22:11 +08:00 |
|
leejet
|
0a7ae07f94
|
feat: add restricted torch legacy checkpoint loading (#1443)
master-584-0a7ae07
|
2026-04-19 23:09:43 +08:00 |
|
leejet
|
66143340b6
|
refactor: move model file IO into dedicated module (#1442)
master-583-6614334
|
2026-04-19 17:52:56 +08:00 |
|
Wagner Bruna
|
7023fc4cfb
|
fix: correct image to image DDIM and TCD (#1410)
master-582-7023fc4
|
2026-04-19 17:51:28 +08:00 |
|
Wagner Bruna
|
e77e4c46bf
|
feat: adapt LCM for flow models (#1413)
master-581-e77e4c4
|
2026-04-19 17:49:46 +08:00 |
|
leejet
|
7d33d4b2dd
|
chore: enable MSVC parallel compilation with /MP (#1438)
master-580-7d33d4b
|
2026-04-18 15:44:43 +08:00 |
|
leejet
|
3c99f700de
|
ci: skip docker image build job on pull requests (#1439)
master-579-3c99f70
|
2026-04-18 15:25:04 +08:00 |
|
leejet
|
4d626d24b2
|
feat(server): implement vid_gen async API and mode-aware capabilities (#1437)
master-578-4d626d2
|
2026-04-18 15:06:36 +08:00 |
|
Wagner Bruna
|
f3f69e2fbe
|
feat: add DPM++ (2S) Ancestral implementation for flow models (#1428)
master-577-f3f69e2
|
2026-04-18 15:05:09 +08:00 |
|
Erik Scholz
|
6a9cb31150
|
fix: tune ernie-image default flow shift (#1433)
master-576-6a9cb31
|
2026-04-18 14:58:00 +08:00 |
|
Wagner Bruna
|
2bcff67480
|
fix: correct dpm++2s_a second model call (#1435)
master-575-2bcff67
|
2026-04-18 14:54:41 +08:00 |
|
leejet
|
a564fdf642
|
refactor: remove is_xl guard wrapper in get_sd_version (#1430)
|
2026-04-17 01:53:58 +08:00 |
|
leejet
|
84fc5446d2
|
fix: skip empty prompt segments around attention range (#1429)
|
2026-04-17 01:42:14 +08:00 |
|