Concedo
d69db26b44
fix stb multiple impl
2025-12-20 12:05:50 +08:00
Concedo
fb31059f9c
fixed a bug in vision with mrope, mrope is refactored to match upstream, should be more accurate now
2025-12-19 01:23:52 +08:00
Concedo
cefb32df19
track clip img patch nx and ny
2025-12-18 22:58:10 +08:00
Concedo
e88bf41fdc
Merge commit ' 12280ae905' into concedo_experimental
...
# Conflicts:
# .github/workflows/build.yml
# common/CMakeLists.txt
# docs/docker.md
# examples/model-conversion/scripts/causal/compare-logits.py
# ggml/src/ggml-hexagon/htp/rope-ops.c
# tests/test-backend-ops.cpp
# tests/test-barrier.cpp
# tools/server/CMakeLists.txt
# tools/server/README.md
2025-12-16 16:29:01 +08:00
Wagner Bruna
78bbe89956
sd: sync to master-417-43a70e8 ( #1889 )
...
* sd: sync to master-417-43a70e8
* fix sdmain build
* switch to upstream apply_loras()
* refactor u8 path conversions and add it to the gguf reader
2025-12-16 16:16:48 +08:00
Concedo
ab9bc6f2ae
zimage cfg clamp is opt out with remove_limits
2025-12-13 09:20:00 +08:00
Concedo
3fb0f337fe
remove z-image clamping for now
2025-12-11 23:05:00 +08:00
Concedo
8a18e094f5
added smartcaching implementation inspired from Pento95 (+2 squashed commit)
...
Squashed commit:
[fcc498688] wip basic smart caching test
[b6e8b2577] wip basic smart caching test
2025-12-10 18:00:03 +08:00
Concedo
1aab32fe03
fixed safetensors loading for zimage
2025-12-09 18:09:47 +08:00
Wagner Bruna
801840d3bd
sd: sync to master-391-5865b5e ( #1878 )
2025-12-08 19:53:52 +08:00
Concedo
20363dc6e7
z image limit cfg scale to 3.0 max
2025-12-07 16:24:26 +08:00
Wagner Bruna
510508e7da
sd: sync to master-391-5865b5e ( #1872 )
2025-12-04 16:29:38 +08:00
Concedo
7316c24bf6
fixes to load flux2
2025-12-03 18:38:54 +08:00
Wagner Bruna
fbdcc74ae6
adapt kcpp changes for z-image
2025-12-01 19:15:38 -03:00
Wagner Bruna
fcb86f22df
sd: sync to master-387-e4c50f1
2025-12-01 19:15:38 -03:00
Wagner Bruna
e971eaefe3
fix: qwenvl.hpp was renamed to llm.hpp
2025-12-01 19:15:38 -03:00
Wagner Bruna
53407c866d
fix mistral vocab filename and qwen2vl tensor name
2025-12-01 17:31:02 -03:00
Wagner Bruna
07f53a4d84
fix qwen2vl tensor detection
2025-12-01 17:04:56 -03:00
Wagner Bruna
3db48a1536
sd: sync to master-383-20eb674
2025-12-01 17:04:56 -03:00
Concedo
438eae7105
mistral2 vocab for sdcpp
2025-12-01 22:32:58 +08:00
Ruben Garcia
06d39dff73
Fix warnings ( #1864 )
2025-11-29 20:18:38 +08:00
Concedo
9a7f749f7c
minor tweak for sd
2025-11-24 22:31:03 +08:00
Wagner Bruna
717d9c6401
sd: sync to master-377-2034588
2025-11-23 19:29:01 -03:00
Wagner Bruna
703bbf67d8
sd: sync to master-371-5498cc0
2025-11-23 19:29:01 -03:00
Wagner Bruna
8ef66e90c1
sd: sync to master-366-f532972
2025-11-23 19:29:01 -03:00
Wagner Bruna
3a7dd1a97f
sd: sync to master-358-347710f
...
Also adapt Koboldcpp LoRA loading function, and add
backend support for lora_apply_mode.
2025-11-23 19:28:54 -03:00
Wagner Bruna
3318b73c94
sd: sync to master-355-694f0d9
2025-11-23 19:28:34 -03:00
LostRuins Concedo
281542aa0d
add smoothing curve, not tested
2025-11-17 23:07:35 +08:00
LostRuins Concedo
85060da3ce
rename ggml_cumsum for tts
2025-11-16 17:54:58 +08:00
LostRuins Concedo
5751c30790
add vulkan for whisper
2025-11-13 15:37:58 +08:00
LostRuins Concedo
a5cc934f04
cherry pick patch in https://github.com/leejet/stable-diffusion.cpp/pull/957 and https://github.com/leejet/stable-diffusion.cpp/pull/935
2025-11-10 23:05:38 +08:00
Concedo
333e2bb30b
fix for qwen image crashing due to ref images being too big, trial and error shows it happens after 512x512
2025-11-02 01:31:01 +08:00
Concedo
7179e49aef
fix from https://github.com/leejet/stable-diffusion.cpp/pull/926
2025-11-01 23:38:37 +08:00
Concedo
0891b0752d
qwen3vl fixed (+2 squashed commit)
...
Squashed commit:
[89f65ed0c] wip fixing q3vl
[6fa34cff2] wip fixing q3vl
2025-10-31 17:52:33 +08:00
Concedo
c2316353a1
allow usage of flux without some components
2025-10-30 22:32:20 +08:00
Wagner Bruna
96a70033ba
sd: sync to master-343-dd75fc0 ( #1818 )
2025-10-30 13:44:59 +08:00
Wagner Bruna
c652d08f02
sd: sync to master-340-9e28be6 ( #1816 )
2025-10-27 21:47:48 +08:00
Wagner Bruna
2cab657c60
sd: sync to master-336-917f7bf ( #1810 )
2025-10-25 21:19:35 +08:00
tsite
97867f1990
add alt umt5xxl tensor name ( #1813 )
2025-10-25 12:48:08 +08:00
Wagner Bruna
fef73919ea
sd: clean up changes against stable-diffusion.cpp 90ef5f8 ( #1804 )
...
* sd: clean up changes against stable-diffusion.cpp 90ef5f8
Clean up the diff, and include a few missing changes, mainly from
the upscaler and model weight type statistics.
* added line clear again
* remove excess spaces
---------
Co-authored-by: LostRuins Concedo <39025047+LostRuins@users.noreply.github.com>
2025-10-23 22:00:33 +08:00
Concedo
86b94456de
Sync sd.cpp to 90ef5f8
2025-10-20 11:07:42 +08:00
Concedo
fab2ff0687
sync sd.cpp to e370258
2025-10-20 10:45:34 +08:00
Concedo
49535fdfed
rename define
2025-10-20 10:08:39 +08:00
Wagner Bruna
d7da1eb35c
invert KCPP_BAKE_SD_VOCAB logic, move define to sdtype_adapter.cpp ( #1803 )
...
Using KCPP_BAKE_SD_VOCAB to turn off the change to not embed the
vocabulary files makes testing new upstream merges harder, because
we then need to set that macro on the sd.cpp original build.
So, revert the tests, making the define turn the change on. Also,
since model.cpp is always built by Koboldcpp as part of the
sdtype_adapter.cpp, it's enough to set the macro on that file.
2025-10-20 10:07:37 +08:00
Concedo
d9e898afe0
reset scheduler if default otherwise it will persist the old one
2025-10-19 19:53:40 +08:00
Concedo
f6916ba864
updated sdui
2025-10-17 13:56:45 +08:00
Concedo
c18d7991c8
rename tts.cpp ggml_round to ggml_ttsround to avoid conflict
2025-10-16 14:24:44 +08:00
Concedo
5207b8d4be
more sd path fallbacks
2025-10-15 15:22:06 +08:00
Concedo
610ba18971
sdcpp precision fix
2025-10-15 11:08:35 +08:00
Concedo
54db35cd7a
fix t5 scale as well
2025-10-12 20:35:46 +08:00
