Commit graph

379 commits

Author SHA1 Message Date
Concedo
9f4d0f6ccf fixed swa pp bug by retrying smaller batches 2025-07-21 23:34:22 +08:00
Concedo
6d50def409 default kv_unified to true, handle LLAMA_SET_ROWS. 2025-07-21 16:13:20 +08:00
Concedo
15b1034dd6 allow larger img2img 2025-07-20 11:10:03 +08:00
Concedo
f0564f9caf updated lite, added better separators for multimodal chunks (universal) 2025-07-17 00:11:08 +08:00
Concedo
66755c8fe9 switch to miniaudio, support mp3 for whisper 2025-07-13 23:24:07 +08:00
Concedo
dca49de059 fixed qwen2 audio issues, works fine now (+3 squashed commit)
Squashed commit:

[b3053a1ba] updated lite

[5071630d6] fixed mtmd issues, audio works

[06efa5af4] fix mtmd compile
2025-07-12 18:54:41 +08:00
Concedo
e9473305d0 wip2 (+1 squashed commits)
Squashed commits:

[4628777b6] wip
2025-07-12 18:54:40 +08:00
Wagner Bruna
d74c16e6e0
enable flash attention for image generation (#1633) 2025-07-05 11:20:51 +08:00
Concedo
186227fc26 sync with sd.cpp 2025-06-30 00:10:51 +08:00
Concedo
2594be7d4e fixed scaling behavior again 2025-06-29 11:36:38 +08:00
Concedo
2635e4b932 try fix segfault in sdcpp 2025-06-29 02:33:03 +08:00
Concedo
485148b293 fixed sdmain compiling 2025-06-28 23:19:13 +08:00
Concedo
6c92a9f0e1 fixed resizing 2025-06-28 23:10:04 +08:00
Concedo
a1175cf34f merged leejet changes 2025-06-28 22:57:07 +08:00
Concedo
4ec0e0fd21 now accept multiple images for reference images 2025-06-28 17:30:28 +08:00
Concedo
ff2cabc28f fixed kontext and photomaker (+1 squashed commits)
Squashed commits:

[de0ac91dd] photomaker use 1 channel
2025-06-28 12:14:05 +08:00
Concedo
5a6cc38f35 fixed a typo 2025-06-28 11:47:07 +08:00
Concedo
ed289227e5 added support for flux kontext 2025-06-28 11:37:19 +08:00
Concedo
0bd648ffa4 photomaker renamed to extra image to handle future extension 2025-06-28 10:26:06 +08:00
Concedo
39b0699c71 fixed savestates with drafting 2025-06-27 20:35:38 +08:00
Concedo
8ce56bd547 tts more silence at the end 2025-06-23 17:15:35 +08:00
Concedo
6039791adf minor bugfixes 2025-06-21 18:41:28 +08:00
Wagner Bruna
08adfb53c9
Configurable VAE threshold limit (#1601)
* add backend support for changing the VAE tiling threshold

* trigger VAE tiling by image area instead of dimensions

I've tested with GGML_VULKAN_MEMORY_DEBUG all resolutions with
the same 768x768 area (even extremes like 64x9216), and many
below that: all consistently allocate 6656 bytes per image pixel.
As tiling is primarily useful to avoid excessive memory usage, it
seems reasonable to enable VAE tiling based on area rather than
maximum image side.

However, as there is currently no user interface option to change
it back to a lower value, it's best to maintain the default
behavior for now.

* replace the notile option with a configurable threshold

This allows selecting a lower threshold value, reducing the
peak memory usage.

The legacy sdnotile parameter gets automatically converted to
the new parameter, if it's the only one supplied.

* simplify tiling checks, 768 default visible in launcher

---------

Co-authored-by: Concedo <39025047+LostRuins@users.noreply.github.com>
2025-06-21 10:14:57 +08:00
Concedo
caea52407a fix photomaker crash 2025-06-21 10:11:39 +08:00
Concedo
684d71e058 add old convert tool 2025-06-21 08:40:04 +08:00
Concedo
ce58d1253f fixed build and workflow 2025-06-21 00:56:27 +08:00
Concedo
2ba7803b95 replace_instruct_placeholders is now default 2025-06-20 22:11:58 +08:00
Concedo
4e40f2aaf4 added photomaker face cloning 2025-06-20 21:33:36 +08:00
Concedo
21881a861d rename restrict square to sdclampedsoft 2025-06-20 15:39:55 +08:00
Concedo
175c99081e merged https://github.com/leejet/stable-diffusion.cpp/issues/588 to fix vae tiling, ref https://github.com/LostRuins/koboldcpp/issues/1603 2025-06-20 11:13:04 +08:00
Concedo
e35c6b8f9b remove t5 masking sdcpp 2025-06-18 21:05:03 +08:00
Concedo
40443a98f5 show available RAM, fixed SD vae tiling noise 2025-06-18 18:44:50 +08:00
Concedo
bfb47cbcd8 Revert "revert padding change for sd chroma"
This reverts commit 7de88802f9.
2025-06-14 10:10:34 +08:00
Concedo
c494525b33 update deprecated apis 2025-06-13 22:21:15 +08:00
Wagner Bruna
f6d2d1ce5c
configurable resolution limit (#1586)
* refactor image gen configuration screen

* make image size limit configurable

* fix resolution limits and keep dimensions closer to the original ratio

* use 0.0 for the configured default image size limit

This prevents the current default value from being saved into the
config files, in case we later decide to adopt a different value.

* export image model version when loading

* restore model-specific default image size limit

* change the image area restriction to be specified by a square side

* move image resolution limits down to the C++ level

* Revert "export image model version when loading"

This reverts commit fa65b23de3.

* Linting Fixes:
PY:
- Inconsistent var name sd_restrict_square -> sd_restrict_square_var
- GUI swap back to using absolute row numbers for now.
- fstring fix
- size_limit -> side_limit inconsistency
C++:
- roundup_64 standalone function
- refactor sd_fix_resolution variable names for clarity
- move "anti crashing" hard total megapixel limit always to be applied after soft total megapixel limit instead of conditionally only when sd_restrict_square is unset

* allow unsafe resolutions if debugmode is on

---------

Co-authored-by: Concedo <39025047+LostRuins@users.noreply.github.com>
2025-06-13 20:05:20 +08:00
Concedo
7d8aa31f1f fixed embeddings, added new parameter to limit max embeddings context 2025-06-10 01:11:55 +08:00
Concedo
7de88802f9 revert padding change for sd chroma 2025-06-08 23:48:46 +08:00
Concedo
2d4c1aa5a0 chroma support is now usable 2025-06-08 18:53:59 +08:00
Concedo
30cf433ab4 merge base support for chroma, however its not working correctly 2025-06-08 18:06:23 +08:00
Concedo
cfcdfd69bd allow embeddings models to use mmap 2025-06-07 10:14:00 +08:00
Concedo
736030bb9f save and load state upgraded to 3 available states 2025-06-04 22:09:40 +08:00
Concedo
b08dca65ed Merge branch 'upstream' into concedo_experimental
# Conflicts:
#	common/CMakeLists.txt
#	common/arg.cpp
#	common/chat.cpp
#	examples/parallel/README.md
#	examples/parallel/parallel.cpp
#	ggml/cmake/common.cmake
#	ggml/src/CMakeLists.txt
#	ggml/src/ggml-cpu/CMakeLists.txt
#	ggml/src/ggml-sycl/ggml-sycl.cpp
#	ggml/src/ggml-sycl/rope.cpp
#	models/ggml-vocab-bert-bge.gguf.inp
#	models/ggml-vocab-bert-bge.gguf.out
#	models/ggml-vocab-command-r.gguf.inp
#	models/ggml-vocab-command-r.gguf.out
#	models/ggml-vocab-deepseek-coder.gguf.inp
#	models/ggml-vocab-deepseek-coder.gguf.out
#	models/ggml-vocab-deepseek-llm.gguf.inp
#	models/ggml-vocab-deepseek-llm.gguf.out
#	models/ggml-vocab-falcon.gguf.inp
#	models/ggml-vocab-falcon.gguf.out
#	models/ggml-vocab-gpt-2.gguf.inp
#	models/ggml-vocab-gpt-2.gguf.out
#	models/ggml-vocab-llama-bpe.gguf.inp
#	models/ggml-vocab-llama-bpe.gguf.out
#	models/ggml-vocab-llama-spm.gguf.inp
#	models/ggml-vocab-llama-spm.gguf.out
#	models/ggml-vocab-mpt.gguf.inp
#	models/ggml-vocab-mpt.gguf.out
#	models/ggml-vocab-phi-3.gguf.inp
#	models/ggml-vocab-phi-3.gguf.out
#	models/ggml-vocab-qwen2.gguf.inp
#	models/ggml-vocab-qwen2.gguf.out
#	models/ggml-vocab-refact.gguf.inp
#	models/ggml-vocab-refact.gguf.out
#	models/ggml-vocab-starcoder.gguf.inp
#	models/ggml-vocab-starcoder.gguf.out
#	requirements/requirements-gguf_editor_gui.txt
#	tests/CMakeLists.txt
#	tests/test-chat.cpp
#	tests/test-grammar-integration.cpp
#	tests/test-json-schema-to-grammar.cpp
#	tools/mtmd/CMakeLists.txt
#	tools/run/run.cpp
#	tools/server/CMakeLists.txt
2025-05-31 13:04:21 +08:00
Wagner Bruna
12f99ba907
fix: workaround for default clip_skip issues (#1572)
Sets the clip_skip value explicitly to 1 or 2 for all generation
requests, aligning with the tests in the Conditioner objects in
conditioner.hpp.

This should fix #1546 regardless of future changes to the default
behavior of sdcpp. This workaround can be removed once a proper
fix is implemented in sdcpp.
2025-05-31 10:36:30 +08:00
Concedo
fe401ca4c2 fixed a typo 2025-05-30 13:35:42 +08:00
Concedo
a11ab0b08e reverse clip skip fix as it might be breaking some sdxl models 2025-05-30 10:40:03 +08:00
Concedo
e14aec58bc embeds no offload qkv 2025-05-29 00:28:02 +08:00
Concedo
fcc1b43c06 embeddings change to encode 2025-05-28 23:24:33 +08:00
Concedo
26bf5b446d fixed thread count <=0 , fixed clip skip <= 0 2025-05-28 00:38:15 +08:00
Concedo
55cc9acec5 Merge branch 'upstream' into concedo_experimental
# Conflicts:
#	.github/workflows/release.yml
#	README.md
#	ggml/src/ggml-cann/aclnn_ops.cpp
#	ggml/src/ggml-cann/ggml-cann.cpp
#	tools/mtmd/CMakeLists.txt
#	tools/mtmd/clip.cpp
#	tools/mtmd/clip.h
2025-05-24 12:10:36 +08:00
Concedo
499283c63a rename define to match upstream 2025-05-23 17:10:12 +08:00