leejet
885e62ea82
refactor: replace ggml_ext_attention with ggml_ext_attention_ext ( #1185 )
2026-01-11 16:34:13 +08:00
leejet
27b5f17401
ci: only push Docker images on master or release
2026-01-08 23:03:32 +08:00
leejet
9be0b91927
docs: fix safetensors file extension notation
2026-01-06 23:31:03 +08:00
leejet
05006cd6e1
chore: use CMAKE_BUILD_TYPE ( #1175 )
2026-01-05 23:29:22 +08:00
leejet
b90b1ee9cf
chore: eliminate compilation warnings under MSVC ( #1170 )
2026-01-04 22:26:57 +08:00
leejet
2cef4badb8
chore: use Release build for windows-latest-cmake
2026-01-04 22:26:09 +08:00
leejet
4ff2c8c74b
refactor: simplify logic for saving results ( #1149 )
2025-12-28 23:27:27 +08:00
leejet
51bd9c8004
chore: reformat named cache params description into single line
2025-12-28 22:53:07 +08:00
leejet
a2d83dd0c8
refactor: move pmid condition logic into get_pmid_condition ( #1148 )
2025-12-27 16:48:15 +08:00
leejet
37c9860b79
fix: handle redirected UTF-8 output correctly on Windows ( #1147 )
2025-12-27 15:43:19 +08:00
leejet
ccb6b0ac9d
feat: add __index_timestep_zero__ support ( #1146 )
2025-12-26 22:07:40 +08:00
leejet
860a78e248
fix: avoid crash when using taesd for preview only ( #1141 )
2025-12-24 23:30:12 +08:00
leejet
a0adcfb148
feat: add support for qwen image edit 2511 ( #1096 )
2025-12-24 23:00:08 +08:00
leejet
3d5fdd7b37
feat: add support for more underline loras ( #1135 )
2025-12-24 22:59:23 +08:00
leejet
3e812460cf
fix: correct ggml_pad_ext ( #1133 )
2025-12-23 21:37:07 +08:00
leejet
98916e8256
docs: update README.md
2025-12-22 23:58:28 +08:00
leejet
30a91138f8
fix: add the missing }
2025-12-21 21:53:38 +08:00
leejet
c6937ba44a
fix: correct the parsing of --convert-name opotion
2025-12-21 21:47:50 +08:00
leejet
ca5b1969a8
feat: do not convert tensor names by default in convert mode ( #1122 )
2025-12-21 18:40:10 +08:00
leejet
88ec9d30b1
feat: add scale_rope support ( #1121 )
2025-12-21 15:40:21 +08:00
leejet
8e9f3a4d9e
feat: add support for underline style lora of flux ( #1103 )
...
* feat: add support for underline style lora of flux
* add support for underline style lora of t5
* add more protected tokens
2025-12-18 21:44:16 +08:00
leejet
bda7fab9f2
chore: remove unused debug code
2025-12-17 23:43:37 +08:00
leejet
c2e18c86e8
fix: make flash attn work with high noise diffusion model ( #1111 )
2025-12-17 23:28:59 +08:00
leejet
c3ad6a13e1
refactor: optimize the printing of version log ( #1102 )
2025-12-16 23:11:27 +08:00
leejet
ebe9d26a72
feat: supports correct UTF-8 printing on windows ( #1101 )
2025-12-16 23:00:41 +08:00
leejet
43a70e819b
fix: add lora info to image metadata ( #1086 )
2025-12-14 01:24:15 +08:00
leejet
15d0f82760
feat(server): do not parse lora fromt client-side prompts ( #1083 )
2025-12-13 14:27:47 +08:00
leejet
2aecdd57ca
feat: simple openai image generation api compatiple server ( #1037 )
2025-12-13 13:53:21 +08:00
leejet
11ab095230
fix: resolve embedding loading issue when calling generate_image multiple times ( #1078 )
2025-12-12 23:08:12 +08:00
leejet
8823dc48bc
feat: align the spatial size to the corresponding multiple ( #1073 )
2025-12-10 23:15:08 +08:00
leejet
d939f6e86a
refactor: optimize the handling of LoRA models ( #1070 )
2025-12-10 00:26:07 +08:00
leejet
96c3e64057
refactor: optimize the handling of embedding ( #1068 )
...
* optimize the handling of embedding
* support case-insensitive embedding names
2025-12-08 23:59:04 +08:00
leejet
bf1a388b44
docs: update logo
2025-12-07 15:09:32 +08:00
leejet
c9005337a8
docs: update logo
2025-12-07 14:56:21 +08:00
leejet
2f0bd31a84
feat: add ovis image support ( #1057 )
2025-12-07 12:32:56 +08:00
leejet
bfbb929790
feat: do not convert bf16 to f32 ( #1055 )
2025-12-06 23:55:51 +08:00
leejet
689e44c9a8
fix: correct ggml_ext_silu_act ( #1056 )
2025-12-06 23:55:28 +08:00
leejet
985aedda32
refactor: optimize the handling of pred type ( #1048 )
2025-12-04 23:31:55 +08:00
leejet
3f3610b5cd
chore: optimize lora log ( #1047 )
2025-12-04 22:44:58 +08:00
leejet
5865b5e703
refactor: split SDParams to SDCliParams/SDContextParams/SDGenerationParams ( #1032 )
2025-12-03 22:31:46 +08:00
leejet
710169df5c
docs: update news
2025-12-01 22:46:15 +08:00
leejet
34a6fd4e60
feat: add z-image support ( #1020 )
...
* add z-image support
* use flux_latent_rgb_proj for z-image
* fix qwen3 rope type
* add support for qwen3 4b gguf
* add support for diffusers format lora
* fix nan issue that occurs when using CUDA with k-quants weights
* add z-image docs
2025-12-01 22:39:43 +08:00
leejet
3c1187ce83
docs: correct the time of adding flux2 support
2025-11-30 12:40:56 +08:00
leejet
20eb674100
fix: avoid crash when the lora file is not found using immediately mode ( #1022 )
2025-11-30 12:19:37 +08:00
leejet
bc80225336
fix: make the immediate LoRA apply mode work better when using Vulkan ( #1021 )
2025-11-30 12:08:25 +08:00
leejet
ab7e8d285e
docs: update news
2025-11-30 11:51:23 +08:00
leejet
52b67c538b
feat: add flux2 support ( #1016 )
...
* add flux2 support
* rename qwenvl to llm
* add Flux2FlowDenoiser
* update docs
2025-11-30 11:32:56 +08:00
leejet
20345888a3
refactor: optimize the handling of sample method ( #999 )
2025-11-22 14:00:25 +08:00
leejet
869d023416
refactor: optimize the handling of scheduler ( #998 )
2025-11-22 12:48:53 +08:00
leejet
5498cc0d67
feat: add Wan2.1-I2V-1.3B(SkyReels) support ( #988 )
2025-11-19 23:56:46 +08:00
leejet
28ffb6c13d
fix: resolve issue with concat multiple LoRA output diffs at runtime ( #985 )
2025-11-17 22:56:07 +08:00
leejet
b88cc32346
fix: avoid using same type but diff instances for rng and sampler_rng ( #982 )
2025-11-16 23:37:14 +08:00
leejet
f532972d60
fix: avoid precision issues on vulkan backend ( #980 )
2025-11-16 20:57:08 +08:00
leejet
d5b05f70c6
feat: support independent sampler rng ( #978 )
2025-11-16 17:11:02 +08:00
leejet
742a7333c3
feat: add cpu rng ( #977 )
2025-11-16 14:48:15 +08:00
leejet
347710f68f
feat: support applying LoRA at runtime ( #969 )
2025-11-13 21:48:44 +08:00
leejet
694f0d9235
refactor: optimize the logic for name conversion and the processing of the LoRA model ( #955 )
2025-11-10 00:12:20 +08:00
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