Commit graph

75 commits

Author SHA1 Message Date
Wagner Bruna
a6c0a224b2
sd: sync to master-506-c9cd497 (#1991) 2026-02-23 17:35:59 +08:00
Concedo
83f905919b flash attention is broken on qwen image edit. disabled conditioner to fix (+1 squashed commits)
Squashed commits:

[1b705cb6e] flash attention is broken on qwen image edit. disabled conditioner to fix
2026-02-14 11:59:03 +08:00
Wagner Bruna
ae5183be10
sd: sync to master-504-636d3cb (#1969)
* sd: sync to master-504-636d3cb

* sd: fix and simplify limit calculation

- restore the "arbitrarily high" 8192 limit, since it's used to turn
off the img_hard_limit (and if each side was always limited by 2048,
we wouldn't need hard_megapixel_res_limit)
- avoid changing the config cfg_square_limit during a generation
- apply the hard_megapixel_res_limit only in the configuration-changed
path, since the default path uses constants
- clean up comments

The calculation itself remains the same:
- default area limit: 832² for SD1.5/SD2, 1024² otherwise
- configured limit always between 64 and 2048
2026-02-14 08:12:08 +08:00
Wagner Bruna
d9ac52a01a
sd: sync to master-492-f957fa3 (#1957)
* sd: sync to master-492-f957fa3

* add Res Multistep and Res 2s samplers

* make sdflashattention control flash_attn too
2026-02-04 16:12:39 +08:00
Wagner Bruna
715a76ce5f
sd: sync to master-480-b87fe13 (#1932) 2026-01-21 20:49:35 +08:00
Concedo
393791496d flux 2 taesd (+1 squashed commits)
Squashed commits:

[adfc3f3a2] flux 2 taesd
2026-01-19 23:47:16 +08:00
Wagner Bruna
10851f223d
sd: sync to master-473-9565c7f (#1927)
* sd: sync to master-473-9565c7f

* sd: add support for flux2 klein
2026-01-19 01:04:34 +08:00
Wagner Bruna
c91fc850c1
sd: sync to master-467-0e52afc (#1916) 2026-01-15 23:06:51 +08:00
Wagner Bruna
0ef55844d3
sd: sync to master-453-4ff2c8c (#1907) 2026-01-03 15:28:27 +08:00
Concedo
442fa7cd7c support for circular textures in sdcpp 2026-01-01 16:34:09 +08:00
Wagner Bruna
84765f5967
sd: sync to master-447-ccb6b0a (#1898)
* sd: sync to master-438-298b110

* sd: sync to master-440-3e81246

* sd: sync to master-444-a0adcfb

* sd: sync to master-447-ccb6b0a
2025-12-27 16:30:52 +08:00
Concedo
7c82cad72c support ovis, added taehv wan embed, fixed compile error (+1 squashed commits)
Squashed commits:

[ab71f6d33] support ovis, added taehv wan embed
2025-12-22 17:08:09 +08:00
Wagner Bruna
44ce1a80b3
sd: sync to master-431-23fce0b (#1893)
* sd: sync to master-427-78e15bd

* add kl_optimal to the available schedulers list

* more robust workaround to avoid stb linkage issues

* sd: sync to master-431-23fce0b

* add TAEHV support and disable TAE if the model isn't found
2025-12-22 15:07:09 +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
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
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
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
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
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
7179e49aef fix from https://github.com/leejet/stable-diffusion.cpp/pull/926 2025-11-01 23:38:37 +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
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
d9e898afe0 reset scheduler if default otherwise it will persist the old one 2025-10-19 19:53:40 +08:00
Concedo
5207b8d4be more sd path fallbacks 2025-10-15 15:22:06 +08:00
Concedo
80f88eb703 wip qwen image edit. not working yet 2025-10-11 11:24:17 +08:00
Wagner Bruna
bece22f996
fix encoding VAE tiling for Qwen Image (#1785) 2025-10-10 10:07:50 +08:00
Concedo
7447a362d1 hide a debug print 2025-10-03 20:56:57 +08:00
Concedo
f282362414 added qwen image support (+1 squashed commits)
Squashed commits:

[92df28061] added qwen image support (+1 squashed commits)

Squashed commits:

[1485c71ed] wip adding qwen image
2025-10-03 18:58:48 +08:00
Wagner Bruna
ac6be8ab8c
sd: do not force T5 on CPU anymore (#1769)
We now have the clip_cpu config parameter for that. Todo: Will make clip cpu on by default
2025-10-02 10:48:16 +08:00
Concedo
e49ac6b120 allow clip_vision to be loaded via clip_l or clip_g param 2025-10-01 17:57:49 +08:00
Concedo
cbb8a3feb5 taesd disable if not valid model arch 2025-09-27 17:00:30 +08:00
Wagner Bruna
42087c3622
update stable-diffusion.cpp to master-306-2abe945 (#1732)
* update stable-diffusion.cpp to master-52a97b3

* update stable-diffusion.cpp to master-0ebe6fe

* update stable-diffusion.cpp to master-301-fd693ac

* update stable-diffusion.cpp to master-306-2abe945

* fix taesd file selection
2025-09-27 16:52:58 +08:00
Wagner Bruna
5de7ed3d56
WIP: update stable-diffusion.cpp to 5900ef6605c6 (new API) (#1669)
* Update stable-diffusion.cpp to 5900ef6605c6 (new API)

* Clean up pending LoRA code and simplify LoRA changes to upstream

* Move VAE tiling disabling for TAESD to sdtype_adapter.cpp

* Move auxiliary ctx functions to sdtype_adapter.cpp

* Use ref_images parameter for Kontext images

* Drop clip skip workaround (fixed upstream)

* Workaround for flash attention with img2img

leejet/stable-diffusion.cpp#756

* Workaround for Chroma with flash attention, debug prints

* Disable forcing CLIP weights to F32 for reduced memory usage
2025-08-12 23:25:02 +08:00
Concedo
186227fc26 sync with sd.cpp 2025-06-30 00:10:51 +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