Commit graph

155 commits

Author SHA1 Message Date
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
4ec0e0fd21 now accept multiple images for reference images 2025-06-28 17:30:28 +08:00
Concedo
0bd648ffa4 photomaker renamed to extra image to handle future extension 2025-06-28 10:26:06 +08:00
Concedo
65ff041827 added more perf stats 2025-06-21 12:12:28 +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
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
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
1cbe716e45 allow setting maingpu 2025-06-12 17:53:43 +08:00
Concedo
7d8aa31f1f fixed embeddings, added new parameter to limit max embeddings context 2025-06-10 01:11:55 +08:00
Concedo
cfcdfd69bd allow embeddings models to use mmap 2025-06-07 10:14:00 +08:00
Concedo
6ce85c54d6 not working correctly 2025-06-02 22:12:10 +08:00
Concedo
8e1ebc55b5 dropped support for lora base as upstream no longer uses it. If provided it will be silently ignored 2025-06-02 12:49:53 +08:00
Concedo
51dc1cf920 added scale for text lora 2025-06-02 00:13:42 +08:00
Concedo
c4df151298 experimental swa flag 2025-05-23 21:33:26 +08:00
Concedo
38a8778f24 wip cfg scale 2025-05-06 23:06:25 +08:00
Concedo
13cee48740 embed aria2c for windows, add slowness check with highpriority recommendation (+1 squashed commits)
Squashed commits:

[b9b695217] embed aria2c for windows, add slowness check with highpriority recommendation (+1 squashed commits)

Squashed commits:

[90b5d389d] embed aria2c for windows, add slowness check with highpriority recommendation (+1 squashed commits)

Squashed commits:

[fbbaa989f] embed aria2c for windows
2025-05-06 18:56:02 +08:00
Concedo
f59b5eb561 added toggle for guidance 2025-05-05 22:21:46 +08:00
Concedo
9cd6a1add2 allow mmproj to be run on cpu 2025-04-21 21:03:10 +08:00
Concedo
2ed6850c0b added override tensor 2025-04-20 20:56:17 +08:00
Concedo
c67510718e kv override option (+1 squashed commits)
Squashed commits:

[e615fc01] kv override option
2025-04-17 14:22:30 +08:00
Concedo
27f575dc83 inpaining support completed, invert mask added 2025-04-09 23:50:17 +08:00
Concedo
23339ace9b inpainting works in kcpp! 2025-04-09 23:01:05 +08:00
Concedo
e37f27632f clear cpu flag manually for templates, added truncation for embeddings 2025-04-02 00:18:30 +08:00
Concedo
2bdf1dacff embeddings done 2025-03-25 22:41:46 +08:00
Concedo
3992fb79cc wip adding embeddings support 2025-03-24 18:01:23 +08:00
Concedo
c1e58419c7 support for voice cloning is done (+2 squashed commit)
Squashed commit:

[e7301628] support for voice cloning is done

[1653c576] wip adding voice cloning
2025-03-21 22:28:59 +08:00
Concedo
e84596ec1a add config for default gen tokens and bos toggle 2025-03-15 19:53:06 +08:00
Concedo
eb1809c105 add more perf stats 2025-03-12 18:58:27 +08:00
Concedo
f2ac10c014 added nsigma to lite 2025-02-21 15:11:24 +08:00
EquinoxPsychosis
2740af3660
add top n sigma sampler from llama.cpp (#1384)
* Add N Sigma Sampler

* update nsigma sampler chain

* xtc position fix

* remove stray newline

---------

Co-authored-by: CasualAutopsy <casual_autopsy@outlook.com>
2025-02-21 14:31:42 +08:00
Concedo
71016db617 remove tts audio caching 2025-02-12 11:37:43 +08:00
Concedo
70f1d8d746 vision can set max res (+1 squashed commits)
Squashed commits:

[938fc655] vision can set max res
2025-01-30 00:19:49 +08:00
Concedo
558bc5c901 tts can now set a length limit 2025-01-28 22:06:59 +08:00
Concedo
0e45d3bb7a quiet flags now set at load time 2025-01-25 16:46:56 +08:00
Concedo
fa7e661133 various fixes 2025-01-18 23:52:39 +08:00
Concedo
e8570de0e6 improved tts default voices quality and sample rate 2025-01-17 18:45:16 +08:00
Concedo
8e3cad1aa2 added audio caching, as a hacky fix for ST TTS bug 2025-01-16 12:04:58 +08:00
Concedo
b3de1598e7 Fixed some GGUFv1 loading bugs, long overdue cleanup for compiling, integrated TTS
tts is functional (+6 squashed commit)

Squashed commit:

[22396311] wip tts

[3a883027] tts not yet working

[0dcfab0e] fix silly bug

[a378d9ef] some long overdue cleanup

[fc5a6fb5] Wip tts

[39f50497] wip TTS integration
2025-01-13 14:23:25 +08:00
Concedo
91b6e29af3 added multilingual support for whisper 2025-01-09 23:28:52 +08:00
Concedo
0cb599546e increase max supported llava images to 8 2025-01-09 22:12:06 +08:00
Concedo
568e476997 added toggle for vae tiling, use custom memory buffer 2025-01-08 13:12:03 +08:00
Concedo
60cd68a39d draft model sets gpu split instead of id, made mmq default for cli 2024-12-14 23:58:45 +08:00
Concedo
595cc6975f added new flags --moeexperts --failsafe --draftgpulayers and --draftgpuid 2024-12-13 17:11:59 +08:00
Concedo
e9d2332dd8 improved tool calls and whisper 2024-12-06 14:34:31 +08:00
Concedo
32ac3153e4 default speculative set to 8. added more adapter fields 2024-11-30 16:18:27 +08:00
Concedo
e0c59486ee default to 12 tokens drafted 2024-11-30 11:52:07 +08:00
Concedo
b21d0fe3ac customizable speculative size 2024-11-30 11:28:19 +08:00
Concedo
f75bbb945f speculative decoding initial impl completed (+6 squashed commit)
Squashed commit:

[0a6306ca0] draft wip dont use (will be squashed)

[a758a1c9c] wip dont use (will be squashed)

[e1994d3ce] wip dont use

[f59690d68] wip

[77228147d] wip on spec decoding. dont use yet

[2445bca54] wip adding speculative decoding (+1 squashed commits)

Squashed commits:

[50e341bb7] wip adding speculative decoding
2024-11-30 10:41:10 +08:00