Wagner Bruna
f7f05fb185
chore: avoid setting GGML_MAX_NAME when building against external ggml ( #751 )
...
An external ggml will most likely have been built with the default
GGML_MAX_NAME value (64), which would be inconsistent with the value
set by our build (128). That would be an ODR violation, and it could
easily cause memory corruption issues due to the different
sizeof(struct ggml_tensor) values.
For now, when linking against an external ggml, we demand it has been
patched with a bigger GGML_MAX_NAME, since we can't check against a
value defined only at build time.
master-f7f05fb
2025-08-03 01:24:40 +08:00
Seas0
6167e2927a
feat: support build against system installed GGML library ( #749 )
master-6167e29
2025-08-02 11:03:18 +08:00
leejet
f6b9aa1a43
refector: optimize the usage of tensor_types
master-f6b9aa1
2025-07-28 23:18:29 +08:00
Wagner Bruna
7eb30d00e5
feat: add missing models and parameters to image metadata ( #743 )
...
* feat: add new scheduler types, clip skip and vae to image embedded params
- If a non default scheduler is set, include it in the 'Sampler' tag in the data
embedded into the final image.
- If a custom VAE path is set, include the vae name (without path and extension)
in embedded image params under a `VAE:` tag.
- If a custom Clip skip is set, include that Clip skip value in embedded image
params under a `Clip skip:` tag.
* feat: add separate diffusion and text models to metadata
---------
Co-authored-by: one-lithe-rune <skapusniak@lithe-runes.com>
master-7eb30d0
2025-07-28 22:00:27 +08:00
stduhpf
59080d3ce1
feat: change image dimensions requirement for DiT models ( #742 )
master-59080d3
2025-07-28 21:58:17 +08:00
R0CKSTAR
8c3c788f31
feat: upgrade musa sdk to rc4.2.0 ( #732 )
2025-07-28 21:51:11 +08:00
leejet
f54524f620
sync: update ggml
2025-07-28 21:50:12 +08:00
leejet
eed97a5e1d
sync: update ggml
master-eed97a5
2025-07-24 23:04:08 +08:00
Ettore Di Giacinto
fb86bf4cb0
docs: add LocalAI to README's UIs ( #741 )
2025-07-24 22:39:26 +08:00
leejet
bd1eaef93e
fix: convert f64 to f32 and i64 to i32 when loading weights
master-bd1eaef
2025-07-24 00:59:38 +08:00
Erik Scholz
ab835f7d39
fix: correct head dim check and L_k padding of flash attention ( #736 )
master-ab835f7
2025-07-24 00:57:45 +08:00
Daniele
26f3f61d37
docs: add sd.cpp-webui as an available frontend ( #738 )
2025-07-23 23:51:57 +08:00
Oleg Skutte
1896b28ef2
fix: make --taesd work ( #731 )
master-1896b28
2025-07-15 00:45:22 +08:00
leejet
0739361bfe
fix: avoid macOS build failed
master-0739361
2025-07-13 20:18:10 +08:00
leejet
ca0bd9396e
refactor: update c api ( #728 )
2025-07-13 18:48:42 +08:00
stduhpf
a772dca27a
feat: add Instruct-Pix2pix/CosXL-Edit support ( #679 )
...
* Instruct-p2p support
* support 2 conditionings cfg
* Do not re-encode the exact same image twice
* fixes for 2-cfg
* Fix pix2pix latent inputs + improve inpainting a bit + fix naming
* prepare for other pix2pix-like models
* Support sdxl ip2p
* fix reference image embeddings
* Support 2-cond cfg properly in cli
* fix typo in help
* Support masks for ip2p models
* unify code style
* delete unused code
* use edit mode
* add img_cond
* format code
---------
Co-authored-by: leejet <leejet714@gmail.com>
master-a772dca
2025-07-12 15:36:45 +08:00
Wagner Bruna
6d84a30c66
feat: overriding quant types for specific tensors on model conversion ( #724 )
master-6d84a30
2025-07-08 00:11:38 +08:00
stduhpf
dafc32d0dd
feat: add support for f64/i64 and clip_g diffusers model ( #681 )
master-dafc32d
2025-07-06 23:24:55 +08:00
idostyle
225162f270
fix: mark encoder.embed_tokens.weight as unused tensor ( #721 )
master-225162f
2025-07-06 23:10:10 +08:00
leejet
b9e4718fac
fix: correct --chroma-enable-t5-mask argument
master-b9e4718
2025-07-06 11:11:47 +08:00
leejet
1ce1c1adca
feat: make lora graph size variable
master-1ce1c1a
2025-07-05 22:44:22 +08:00
stduhpf
19fbfd8639
feat: override text encoders for unet models ( #682 )
master-19fbfd8
2025-07-04 22:19:47 +08:00
Wagner Bruna
76c72628b1
fix: fix a few typos on cli help and error messages ( #714 )
master-76c7262
2025-07-04 22:15:41 +08:00
vmobilis
3bae667f3d
fix: break the line after skipping tensors in VAE ( #591 )
master-3bae667
2025-07-03 22:50:42 +08:00
stduhpf
8d0819c548
fix: actually use embeddings with SDXL ( #657 )
master-8d0819c
2025-07-03 22:39:57 +08:00
Binozo
7a8ff2e819
docs: add golang cgo bindings to README ( #635 )
2025-07-02 23:19:49 +08:00
rmatif
0927e8e322
docs: add Android app to README ( #647 )
2025-07-02 23:18:16 +08:00
stduhpf
83ef4e44ce
feat: add T5 with llama.cpp naming convention support ( #654 )
master-83ef4e4
2025-07-02 23:13:00 +08:00
leejet
7dac89ad75
refector: reuse some code
master-7dac89a
2025-07-01 23:33:50 +08:00
stduhpf
9251756086
feat: add CosXL support ( #683 )
master-9251756
2025-07-01 23:13:04 +08:00
leejet
ecf5db97ae
chore: fix windows build and release
master-ecf5db9
2025-07-01 23:05:48 +08:00
stduhpf
ea46fd6948
fix: force zero-initialize output of tiling ( #703 )
2025-07-01 23:01:29 +08:00
leejet
23de7fc44a
chore: avoid warnings when building on linux
master-23de7fc
2025-06-30 23:49:52 +08:00
rmatif
d42fd59464
feat: add OpenCL backend support ( #680 )
master-d42fd59
2025-06-30 23:32:23 +08:00
Wagner Bruna
0d8b39f0ba
fix: avoid crash on sdxl loras ( #658 )
...
Some SDXL LoRAs (eg. PCM) can exceed 12k nodes.
master-0d8b39f
2025-06-30 23:29:32 +08:00
R0CKSTAR
539b5b9374
fix: fix musa docker build ( #662 )
...
Signed-off-by: Xiaodong Ye <xiaodong.ye@mthreads.com>
2025-06-30 23:27:40 +08:00
Wagner Bruna
b1fc16b504
fix: allow resetting clip_skip to its default value ( #697 )
master-b1fc16b
2025-06-30 23:23:21 +08:00
leejet
d6c87dce5c
docs: add chroma doc
2025-06-29 23:58:15 +08:00
leejet
a28d04dd81
fix: fix the issue in parsing --chroma-disable-dit-mask
master-a28d04d
2025-06-29 23:52:36 +08:00
leejet
45d0ebb30c
style: format code
master-45d0ebb
2025-06-29 23:40:55 +08:00
stduhpf
b1cc40c35c
feat: add Chroma support ( #696 )
...
---------
Co-authored-by: Green Sky <Green-Sky@users.noreply.github.com>
Co-authored-by: leejet <leejet714@gmail.com>
master-b1cc40c
2025-06-29 23:36:42 +08:00
leejet
884e23eeeb
docs: add kontext doc
2025-06-29 10:35:31 +08:00
stduhpf
c9b5735116
feat: add FLUX.1 Kontext dev support ( #707 )
...
* Kontext support
* add edit mode
---------
Co-authored-by: leejet <leejet714@gmail.com>
master-c9b5735
2025-06-29 10:08:53 +08:00
vmobilis
10c6501bd0
fix missing argument in prototype of stbi_write_jpg ( #613 )
master-10c6501
2025-03-09 12:30:10 +08:00
vmobilis
10feacf031
fix: correct img2img time ( #616 )
master-10feacf
2025-03-09 12:29:08 +08:00
vmobilis
655f8a5169
fix: clang complains about needless braces ( #618 )
2025-03-09 12:26:41 +08:00
idostyle
d7c7a34712
fix: ModelLoader::load_tensors duplicated check ( #623 )
...
Introduced in 2b6ec97fe244d03c40aa8d70131d40bb086099b0
master-d7c7a34
2025-03-09 12:23:23 +08:00
vmobilis
81556f3136
chore: silence some warnings about precision loss ( #620 )
master-81556f3
2025-03-09 12:22:39 +08:00
stduhpf
3fb275a67b
fix: suport sdxl embedddings ( #621 )
master-3fb275a
2025-03-09 12:21:23 +08:00
leejet
30b3ac8e62
fix: avoid potential dangling pointer problem
master-30b3ac8
2025-03-01 16:58:26 +08:00