Commit graph

740 commits

Author SHA1 Message Date
Concedo
7a69646196 qwen3tts support languages 2026-07-27 22:45:04 +08:00
Concedo
133411c3fd fixed incorrect line removal 2026-07-25 19:06:56 +08:00
Wagner Bruna
fd44ba2c61
sd: sync with master-795-87a0177 (#2338)
* sd: sync with master-782-b290693

* sd: sync with master-788-8a51eb9

* sd: sync with master-789-5114672

* sd: sync with master-795-87a0177

* sd: expose ref_image_args and make it trigger edit mode
2026-07-25 19:04:50 +08:00
Concedo
49dbdaaab5 Merge branch 'upstream' into concedo_experimental
# Conflicts:
#	AGENTS.md
#	CODEOWNERS
#	CONTRIBUTING.md
#	docs/backend/OPENCL.md
#	docs/development/HOWTO-add-model.md
#	examples/training/finetune.cpp
#	ggml/src/ggml-hexagon/ggml-hexagon.cpp
#	ggml/src/ggml-hexagon/htp-drv.cpp
#	ggml/src/ggml-hexagon/htp/act-ops.c
#	ggml/src/ggml-hexagon/htp/dma-queue.c
#	ggml/src/ggml-hexagon/htp/dma-queue.h
#	ggml/src/ggml-hexagon/htp/flash-attn-ops.c
#	ggml/src/ggml-hexagon/htp/flash-attn-ops.h
#	ggml/src/ggml-hexagon/htp/hmx-mm-kernels-tiled.h
#	ggml/src/ggml-hexagon/htp/htp-ctx.h
#	ggml/src/ggml-hexagon/htp/htp-ops.h
#	ggml/src/ggml-hexagon/htp/htp-tensor.c
#	ggml/src/ggml-hexagon/htp/htp-tensor.h
#	ggml/src/ggml-hexagon/htp/hvx-fa-kernels.h
#	ggml/src/ggml-hexagon/htp/hvx-reduce.h
#	ggml/src/ggml-hexagon/htp/main.c
#	ggml/src/ggml-hexagon/htp/matmul-ops.c
#	ggml/src/ggml-hexagon/htp/matmul-ops.h
#	ggml/src/ggml-hexagon/htp/unary-ops.c
#	ggml/src/ggml-hexagon/htp/unary-ops.h
#	ggml/src/ggml-opencl/CMakeLists.txt
#	ggml/src/ggml-opencl/ggml-opencl.cpp
#	scripts/compare-llama-bench.py
#	scripts/snapdragon/ggml-hexagon-profile.py
#	scripts/snapdragon/ggml-hexagon-trace.py
#	scripts/sync_vendor.py
#	tests/test-arg-parser.cpp
#	tests/test-chat.cpp
#	tests/test-model-load-cancel.cpp
#	tests/test-quantize-stats.cpp
#	tools/cli/README.md
#	tools/completion/README.md
#	tools/llama-bench/llama-bench.cpp
#	tools/server/README.md
#	tools/ui/src/lib/constants/settings-registry.ts
2026-07-25 12:20:51 +08:00
Concedo
68db0dda84 fixed a qwen image edit regression from https://github.com/LostRuins/koboldcpp/pull/2251 2026-07-21 22:20:48 +08:00
Concedo
d7ca5a4d01 use u8 helper 2026-07-19 17:32:43 +08:00
Wagner Bruna
1f9dd9c398
sd: sync with master-775-b5d8120 (#2321)
* sd: expose extra_sample_args parameter

* sd: sync with master-773-1b04283

* sd: sync with master-775-b5d8120
2026-07-13 20:42:22 +08:00
Concedo
d067fc6d28 fixed kcpp sdcpp file location 2026-07-13 20:40:48 +08:00
Concedo
75ada7102f exclude z-image from reference image list 2026-07-13 20:32:58 +08:00
Concedo
b368c874e9 fixed int8 convrot loading 2026-07-13 18:39:32 +08:00
Concedo
60f0e18cb0 added int8 convrot support 2026-07-12 21:43:36 +08:00
Concedo
70a9d58fff fixed sefi loading 2026-07-12 14:25:14 +08:00
Concedo
062a2d0bd3 added support for qwen3tts aliases, replaces https://github.com/LostRuins/koboldcpp/pull/2315 2026-07-12 11:49:33 +08:00
Wagner Bruna
c43c27c838
sd: cancel image generation on client disconnect (#2318) 2026-07-11 12:28:04 +08:00
Wagner Bruna
e11d3ddef0
sd: sync with master-767-885f01a (#2310)
* sd: minor API path handling cleanup

* sd: sync with master-749-b11c95a

* sd: use original API parameters at the internal C++ API

* sd: split_mode and auto_fit backend support

* sd: sync with master-758-c674225

* sd: sync with master-765-bb84971

* sd: sync with master-767-885f01a
2026-07-08 17:08:19 +08:00
Concedo
fd38fec594 save lora info when generating image 2026-07-03 17:32:48 +08:00
Wagner Bruna
6482a596e1
sd: sync with master-746-2574f59 (#2291)
* sd: clean up SD_USE_ defines

* sd: sync with master-721-8caa3f9+5 (9956436)

* sd: simplify taehv selection

* sd: sync with master-731-9f855c9

* sd: sync with master-737-3b6c9ca

* sd: sync with master-741-484baa4

* sd: sync with master-743-3590aa8

* sd: sync with master-746-2574f59

* sd: fix ggml_ext_pad_ext call
2026-07-03 15:28:51 +08:00
Concedo
40e4459147 load sd weights eagerly 2026-06-25 14:22:04 +08:00
Wagner Bruna
afbd83baba
sd: sync with master-721-8caa3f9 (#2284)
* sd: sync with master-714-b12098f

* sd: support for boogu and longcat edit

* sd: remove SD_TYPE_COUNT == GGML_TYPE_COUNT assertion

The current code should be able to deal with an out-of-sync ggml.

* sd: generalize edit mode support

* sd: sync with master-719-f440ad9

* sd: sync with master-721-8caa3f9
2026-06-25 13:49:14 +08:00
Concedo
2fb3406be7 added ideogram 4 support 2026-06-20 00:29:48 +08:00
Concedo
45f49f9bd9 fixed tts mp3 saving 2026-06-18 22:33:30 +08:00
Concedo
1b36e7f606 option to save tts as mp3, currently slightly bugged 2026-06-18 22:16:29 +08:00
Concedo
11cd91658b minor linting 2026-06-17 23:53:06 +08:00
Concedo
eb05dd5fab support audio to video for ltx 2.3 2026-06-17 23:50:08 +08:00
Wagner Bruna
097cc91424
sd: sync with master-707-5a34bc7 (#2274)
* sd: sync with master-692-9b0fceb

* sd: sync with master-694-276025e

* sd: sync with master-697-5db680c

* sd: sync to master-700-c2df4e1

* sd: sync with master-704-6e66a1a

* sd: sync with master-707-5a34bc7
2026-06-17 16:31:16 +08:00
Wagner Bruna
b33042bc18
sd: sync with master-690-3a54597 (#2270)
* sd: sync with master-690-3a54597

* sd: drop Chroma workaround for Flash Attention

Fixed in master-686-1b702a5 .

* sd: skip setting cpu flags (soon to be removed)
2026-06-16 00:33:00 +08:00
Wagner Bruna
fdc9c96124
sd: sync with master-685-19bdfe2 (#2265)
* sd: sync with master-682-b3d56d0

* sd: sync with master-685-19bdfe2

* sd: enable layer streaming
2026-06-13 11:14:44 +08:00
Concedo
40084bb1f8 mtp drafting added (+1 squashed commits)
Squashed commits:

[b0fa1a6de] wip 1
2026-06-11 15:25:49 +08:00
Concedo
0740ce70b7 revert incorrect token count for mtmd 2026-06-09 22:46:17 +08:00
Concedo
f5acccad63 cleanup round 1 2026-06-09 21:13:48 +08:00
Concedo
90a14cecf8 mtmd checkpoint 2 2026-06-09 17:55:17 +08:00
Concedo
794a271cfa upgrade to mtmd checkpoint 1 2026-06-09 16:06:30 +08:00
Wagner Bruna
a53b3f7411
sd: sync with master-679-f3fd359 (#2257) 2026-06-08 20:42:57 +08:00
Wagner Bruna
635beb6891
sd: sync to master-678-dfb2390 (#2251)
* sd: sync to master-666-7948df8

* sd: sync to master-672-1f9ee88

* sd: sync to master-676-b9254dd

* sd: sync to master-678-dfb2390
2026-06-07 22:18:03 +08:00
Wagner Bruna
b1dc6110f0
sd: fix utf-8 prompt handling (#2254) 2026-06-07 13:37:20 +08:00
Concedo
9042af9a2e increase prompt length limit 2026-06-06 09:55:39 +08:00
Concedo
9755b05556 g4ua audio fix 2026-06-05 10:59:24 +08:00
Wagner Bruna
1f14c98d36
sd: fix gemma3 vocab and merge filenames and add functions for gemma2 (#2249)
* sd: simplify vocab and merges loading

* sd: fix gemma3 vocab and merge filenames and add functions for gemma2
2026-06-04 10:31:06 +08:00
Concedo
598b594aa2 Revert "disable temporal tiling"
This reverts commit 241ece07c3.
2026-06-02 19:45:15 +08:00
Concedo
241ece07c3 disable temporal tiling 2026-06-01 18:34:27 +08:00
Concedo
c3246cd392 allow SD to limit max VRAM usage 2026-06-01 16:06:27 +08:00
Concedo
14b7da5e44 allow reversing the reference image 2026-05-31 23:08:58 +08:00
Wagner Bruna
2f100fe3d1
sd: sync to master-660-d2797b8 (#2241)
* sd: sync to master-659-d3b2cb0

* sd: sync to master-660-d2797b8
2026-05-31 14:04:25 +08:00
Concedo
3361ef801c video vae tiling fix 2026-05-30 22:59:15 +08:00
Concedo
d4b513c19d mmap fix from https://github.com/leejet/stable-diffusion.cpp/pull/1575 2026-05-30 16:12:34 +08:00
Concedo
5dc1a89001 support final frame 2026-05-30 09:27:51 +08:00
Concedo
48a6d161a5 add fps controls 2026-05-29 23:18:14 +08:00
Concedo
272c1ee232 increase frame limit to 120 and allow loading tae ltx 2026-05-29 18:50:01 +08:00
Concedo
8ddb4fedb1 add audio support 2026-05-29 13:49:30 +08:00
Concedo
9149e6a96e fix for ltx 2026-05-29 10:49:04 +08:00