leejet
ee89afc878
fix: resolve issue with pmid ( #957 )
2025-11-09 22:47:53 +08:00
leejet
c2d8ffc22c
fix: compatibility for models with modified tensor shapes ( #951 )
2025-11-07 23:04:41 +08:00
leejet
8f6c5c217b
refactor: simplify the model loading logic ( #933 )
...
* remove String2GGMLType
* remove preprocess_tensor
* fix clip init
* simplify the logic for reading weights
2025-11-03 21:21:34 +08:00
leejet
6103d86e2c
refactor: introduce GGMLRunnerContext ( #928 )
...
* introduce GGMLRunnerContext
* add Flash Attention enable control through GGMLRunnerContext
* add conv2d_direct enable control through GGMLRunnerContext
2025-11-02 02:11:04 +08:00
leejet
dd75fc081c
refactor: unify the naming style of ggml extension functions ( #921 )
2025-10-28 23:26:48 +08:00
leejet
9e28be6479
feat: add chroma radiance support ( #910 )
...
* add chroma radiance support
* fix ci
* simply generate_init_latent
* workaround: avoid ggml cuda error
* format code
* add chroma radiance doc
2025-10-25 23:56:14 +08:00
leejet
69b9511ce9
sync: update ggml
2025-10-24 00:32:45 +08:00
leejet
48e0a28ddf
feat: add shift factor support ( #903 )
2025-10-23 01:20:29 +08:00
leejet
d05e46ca5e
chore: add .clang-tidy configuration and apply modernize checks ( #902 )
2025-10-18 23:23:40 +08:00
leejet
0723ee51c9
refactor: optimize option printing ( #900 )
2025-10-18 17:50:30 +08:00
leejet
90ef5f8246
feat: add auto-resize support for reference images (was Qwen-Image-Edit only) ( #898 )
2025-10-18 16:37:09 +08:00
leejet
db6f4791b4
feat: add wtype stat ( #899 )
2025-10-17 23:40:32 +08:00
leejet
b25785bc10
sync: update ggml
2025-10-17 21:46:39 +08:00
leejet
0585e2609d
docs: split README sections (build, performance, etc.) into separate docs
2025-10-16 23:22:06 +08:00
leejet
683d6d08a8
chore: add github issue template
2025-10-16 21:04:41 +08:00
leejet
40a6a8710e
fix: resolve precision issues in SDXL VAE under fp16 ( #888 )
...
* fix: resolve precision issues in SDXL VAE under fp16
* add --force-sdxl-vae-conv-scale option
* update docs
2025-10-15 23:01:00 +08:00
leejet
2e9242e37f
feat: add Qwen Image Edit support ( #877 )
...
* add ref latent support for qwen image
* optimize clip_preprocess and fix get_first_stage_encoding
* add qwen2vl vit support
* add qwen image edit support
* fix qwen image edit pipeline
* add mmproj file support
* support dynamic number of Qwen image transformer blocks
* set prompt_template_encode_start_idx every time
* to_add_out precision fix
* to_out.0 precision fix
* update docs
2025-10-13 23:17:18 +08:00
leejet
1c32fa03bc
fix: avoid generating black images when running T5 on the GPU ( #882 )
2025-10-13 00:01:06 +08:00
leejet
beb99a2de2
feat: add Qwen Image support ( #851 )
...
* add qwen tokenizer
* add qwen2.5 vl support
* mv qwen.hpp -> qwenvl.hpp
* add qwen image model
* add qwen image t2i pipeline
* fix qwen image flash attn
* add qwen image i2i pipline
* change encoding of vocab_qwen.hpp to utf8
* fix get_first_stage_encoding
* apply jeffbolz f32 patch
https://github.com/leejet/stable-diffusion.cpp/pull/851#issuecomment-3335515302
* fix the issue that occurs when using CUDA with k-quants weights
* optimize the handling of the FeedForward precision fix
* to_add_out precision fix
* update docs
2025-10-12 23:23:19 +08:00
leejet
02af48a97f
chore: fix vulkan ci ( #878 )
2025-10-11 00:40:57 +08:00
leejet
e12d5e0aaf
fix: ensure directory iteration results are sorted by filename ( #858 )
2025-10-11 00:18:39 +08:00
leejet
35843c77ea
fix: optimize the handling of embedding weight ( #859 )
2025-09-25 23:09:59 +08:00
leejet
6ad46bb700
sync: update ggml
2025-09-25 21:57:43 +08:00
leejet
1ba30ce005
sync: update ggml
2025-09-25 00:38:38 +08:00
leejet
2abe9451c4
fix: optimize the handling of CLIP embedding weight ( #840 )
2025-09-25 00:28:20 +08:00
leejet
fd693ac6a2
refactor: remove unused --normalize-input parameter ( #835 )
2025-09-18 00:12:53 +08:00
leejet
567f9f14f0
fix: avoid multithreading issues in the model loader
2025-09-18 00:00:15 +08:00
leejet
1e5f207006
chore: fix workflow ( #836 )
2025-09-17 22:11:55 +08:00
leejet
79426d578e
chore: set release tag by commit count
2025-09-16 23:24:36 +08:00
leejet
0ebe6fe118
refactor: simplify the logic of pm id image loading ( #827 )
2025-09-14 22:50:21 +08:00
leejet
52a97b3ac1
feat: add vace support ( #819 )
...
* add wan vace t2v support
* add --vace-strength option
* add vace i2v support
* fix the processing of vace_context
* add vace v2v support
* update docs
2025-09-14 16:57:33 +08:00
leejet
288e2d63c0
docs: update docs
2025-09-14 14:24:24 +08:00
leejet
dc46993b55
feat: increase work_ctx memory buffer size ( #814 )
2025-09-14 13:19:20 +08:00
leejet
fce6afcc6a
feat: add sd3 flash attn support ( #815 )
2025-09-11 23:24:29 +08:00
leejet
b017918106
chore: remove sd3 flash attention warn ( #812 )
2025-09-10 22:21:02 +08:00
leejet
c648001030
feat: add detailed tensor loading time stat ( #793 )
2025-09-07 22:51:44 +08:00
leejet
f8fe4e7db9
fix: add flash attn support check ( #803 )
2025-09-07 21:29:06 +08:00
leejet
1c07fb6fb1
docs: update docs/wan.md
2025-09-07 12:07:20 +08:00
leejet
675208dcb6
chore: update to c++17
2025-09-07 12:04:17 +08:00
leejet
d7f430cd69
docs: update docs and help message
2025-09-07 02:26:44 +08:00
leejet
cb1d975e96
feat: add wan2.1/2.2 support ( #778 )
...
* add wan vae suppport
* add wan model support
* add umt5 support
* add wan2.1 t2i support
* make flash attn work with wan
* make wan a little faster
* add wan2.1 t2v support
* add wan gguf support
* add offload params to cpu support
* add wan2.1 i2v support
* crop image before resize
* set default fps to 16
* add diff lora support
* fix wan2.1 i2v
* introduce sd_sample_params_t
* add wan2.2 t2v support
* add wan2.2 14B i2v support
* add wan2.2 ti2v support
* add high noise lora support
* sync: update ggml submodule url
* avoid build failure on linux
* avoid build failure
* update ggml
* update ggml
* fix sd_version_is_wan
* update ggml, fix cpu im2col_3d
* fix ggml_nn_attention_ext mask
* add cache support to ggml runner
* fix the issue of illegal memory access
* unify image loading processing
* add wan2.1/2.2 FLF2V support
* fix end_image mask
* update to latest ggml
* add GGUFReader
* update docs
2025-09-06 18:08:03 +08:00
leejet
5900ef6605
sync: update ggml, make cuda im2col a little faster
2025-08-03 01:29:40 +08:00
leejet
f6b9aa1a43
refector: optimize the usage of tensor_types
2025-07-28 23:18:29 +08:00
leejet
f54524f620
sync: update ggml
2025-07-28 21:50:12 +08:00
leejet
eed97a5e1d
sync: update ggml
2025-07-24 23:04:08 +08:00
leejet
bd1eaef93e
fix: convert f64 to f32 and i64 to i32 when loading weights
2025-07-24 00:59:38 +08:00
leejet
0739361bfe
fix: avoid macOS build failed
2025-07-13 20:18:10 +08:00
leejet
ca0bd9396e
refactor: update c api ( #728 )
2025-07-13 18:48:42 +08:00
leejet
b9e4718fac
fix: correct --chroma-enable-t5-mask argument
2025-07-06 11:11:47 +08:00
leejet
1ce1c1adca
feat: make lora graph size variable
2025-07-05 22:44:22 +08:00
leejet
7dac89ad75
refector: reuse some code
2025-07-01 23:33:50 +08:00
leejet
ecf5db97ae
chore: fix windows build and release
2025-07-01 23:05:48 +08:00
leejet
23de7fc44a
chore: avoid warnings when building on linux
2025-06-30 23:49:52 +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
2025-06-29 23:52:36 +08:00
leejet
45d0ebb30c
style: format code
2025-06-29 23:40:55 +08:00
leejet
884e23eeeb
docs: add kontext doc
2025-06-29 10:35:31 +08:00
leejet
30b3ac8e62
fix: avoid potential dangling pointer problem
2025-03-01 16:58:26 +08:00
leejet
195d170136
sync: update ggml
2025-03-01 12:09:55 +08:00
leejet
dcf91f9e0f
chore: change SD_CUBLAS/SD_USE_CUBLAS to SD_CUDA/SD_USE_CUDA
2024-12-28 13:27:51 +08:00
leejet
9578fdcc46
chore: remove rocm5.5 build temporarily
2024-11-30 14:26:29 +08:00
leejet
4570715727
fix: use ggml_nn_attention in vae
2024-11-24 18:21:31 +08:00
leejet
c3eeb669cd
sync: update ggml
2024-11-23 13:29:32 +08:00
leejet
b5f4932696
refactor: add some sd vesion helper functions
2024-11-23 13:02:44 +08:00
leejet
ac54e00760
feat: add sd3.5 support ( #445 )
2024-10-24 21:58:03 +08:00
leejet
58d54738e2
docs: add star history
2024-08-28 00:27:54 +08:00
leejet
4f87b232c2
docs: add Vulkan build command
2024-08-28 00:25:31 +08:00
leejet
8847114abf
fix: fix issue when applying lora
2024-08-25 22:39:39 +08:00
leejet
5c561eab31
feat: do not convert more flux tensors
2024-08-25 16:01:36 +08:00
leejet
f5997a1951
fix: do not force using f32 for some flux layers
...
This sometimes leads to worse result
2024-08-25 14:07:22 +08:00
leejet
1bdc767aaf
feat: force using f32 for some layers
2024-08-25 13:53:16 +08:00
leejet
79c9fe9556
feat: do not convert some tensors
2024-08-25 13:37:37 +08:00
leejet
28a614769a
docs: update docs/flux.md
2024-08-25 13:11:34 +08:00
leejet
c837c5d9cc
style: format code
2024-08-25 00:19:37 +08:00
leejet
d08d7fa632
docs: update README.md
2024-08-24 14:38:44 +08:00
leejet and Erik Scholz
64d231f384
feat: add flux support ( #356 )
...
* add flux support
* avoid build failures in non-CUDA environments
* fix schnell support
* add k quants support
* add support for applying lora to quantized tensors
* add inplace conversion support for f8_e4m3 (#359 )
in the same way it is done for bf16
like how bf16 converts losslessly to fp32,
f8_e4m3 converts losslessly to fp16
* add xlabs flux comfy converted lora support
* update docs
---------
Co-authored-by: Erik Scholz <Green-Sky@users.noreply.github.com >
2024-08-24 14:29:52 +08:00
leejet
5b8d16aa68
docs: reorganize README.md
2024-08-03 12:06:34 +08:00
leejet
3d854f7917
sync: update ggml submodule url
2024-08-03 11:42:12 +08:00
leejet
4a6e36edc5
sync: update ggml
2024-07-28 18:30:35 +08:00
leejet
73c2176648
feat: add sd3 support ( #298 )
2024-07-28 15:44:08 +08:00
leejet
f9f0d4685b
fix: sample_k_diffusion should be static
2024-06-10 23:04:02 +08:00
leejet
8d2050a5cf
sync: update ggml
2024-06-10 22:59:36 +08:00
leejet
08f5b41956
refector: make the sampling module more independent
2024-06-10 22:42:15 +08:00
leejet
be6cd1a4bf
sync: update ggml
2024-06-01 13:44:09 +08:00
leejet
1d2af5ca3f
fix: set n_dims of tensor storage to 1 when it's 0
2024-05-14 23:06:52 +08:00
leejet
036ba9e6d8
feat: enable controlnet and photo maker for img2img mode
2024-04-14 16:36:08 +08:00
leejet
ec82d5279a
refector: remove some useless code
2024-04-14 14:04:52 +08:00
leejet
3ac48ea1a7
fix: use static implementation of stb_image_resize
2024-04-06 16:37:08 +08:00
leejet
61980171a1
sync: update ggml
2024-03-10 17:23:11 +08:00
leejet
a65c410463
sync: update ggml
2024-03-02 19:49:41 +08:00
leejet
a17ae7b7d2
sync: update ggml
2024-03-02 19:23:11 +08:00
leejet
e1b37b4ef6
fix: update ggml submodule url
2024-03-02 17:34:08 +08:00
leejet
ef5c3f7401
feat: add support for prompt longer than 77
2024-03-02 17:13:18 +08:00
leejet
4a8190405a
fix: fix the issue with dynamic linking
2024-02-25 21:39:01 +08:00
leejet
730585d515
sync: update ggml ( #180 )
2024-02-25 21:11:01 +08:00
leejet
b6368868d9
feat: introduce GGMLBlock and implement SVD(Broken) ( #159 )
...
* introduce GGMLBlock and implement SVD(Broken)
* add sdxl vae warning
2024-02-24 20:06:39 +08:00
leejet
349439f239
style: format code
2024-01-29 23:05:18 +08:00
leejet
5c614e4bc2
feat: add convert api ( #142 )
2024-01-14 11:43:24 +08:00
leejet
2b6ec97fe2
sync: update ggml ( #134 )
2024-01-05 23:18:41 +08:00
leejet
db382348cc
fix: change GGML_MAX_NAME to 128
2024-01-03 22:42:42 +08:00
leejet