Commit Graph
100 Commits
Author SHA1 Message Date
leejet 2570565dfa update to latest ggml 2025-09-06 15:13:26 +08:00
leejet 00b0a0053d fix end_image mask 2025-09-01 01:10:20 +08:00
leejet e2a3a406b6 add wan2.1/2.2 FLF2V support 2025-08-31 23:49:47 +08:00
leejet 33ff442c1d unify image loading processing 2025-08-31 18:40:04 +08:00
leejet 50f921119e fix the issue of illegal memory access 2025-08-31 12:41:16 +08:00
leejet fed78a3f1a add cache support to ggml runner 2025-08-30 23:53:51 +08:00
leejet aa5566f005 fix ggml_nn_attention_ext mask 2025-08-30 14:21:42 +08:00
leejet 48d4c1cd0b update ggml, fix cpu im2col_3d 2025-08-30 11:22:13 +08:00
leejet 797d2f9c51 fix sd_version_is_wan 2025-08-30 04:02:51 +08:00
leejet dab62afb9b update ggml 2025-08-30 02:35:17 +08:00
leejet 68eaff08b6 update ggml 2025-08-30 01:29:28 +08:00
leejet 08f4b18ed3 avoid build failure 2025-08-29 23:33:08 +08:00
leejet b05b2b29a3 Merge branch 'master' into wan 2025-08-29 23:08:32 +08:00
leejet 2410ce3dee avoid build failure on linux 2025-08-29 22:20:16 +08:00
leejet 27a2cfe1d9 sync: update ggml submodule url 2025-08-29 22:07:25 +08:00
leejet eb3fed8b52 add high noise lora support 2025-08-29 01:36:03 +08:00
leejet 6de680a94c add wan2.2 ti2v support 2025-08-29 00:08:42 +08:00
leejet 815e9fd6e1 add wan2.2 14B i2v support 2025-08-25 23:13:38 +08:00
leejet 079b393b6e add wan2.2 t2v support 2025-08-25 00:10:16 +08:00
leejet afef8cef9e introduce sd_sample_params_t 2025-08-24 17:20:41 +08:00
leejet cf48441345 fix wan2.1 i2v 2025-08-24 14:07:38 +08:00
leejet 9fcc85688d add diff lora support 2025-08-23 19:06:45 +08:00
leejet e69195d22f set default fps to 16 2025-08-23 14:41:14 +08:00
leejet 459fd4dbbc crop image before resize 2025-08-23 13:59:05 +08:00
leejet d83867b8e9 add wan2.1 i2v support 2025-08-23 12:37:15 +08:00
leejet 9b29de27a8 add offload params to cpu support 2025-08-17 03:13:16 +08:00
leejet b0833eb4d8 add wan gguf support 2025-08-16 00:46:49 +08:00
leejet 3a2840f9fb add wan2.1 t2v support 2025-08-15 00:37:30 +08:00
leejet 73f76e6d96 make wan a little faster 2025-08-10 18:29:30 +08:00
leejet 00f790d0e9 make flash attn work with wan 2025-08-10 17:52:59 +08:00
leejet 1d9ccea41a add wan2.1 t2i support 2025-08-10 17:07:17 +08:00
leejet bace0a08c4 add umt5 support 2025-08-09 16:07:04 +08:00
leejet 5f7d98884c add wan model support 2025-08-06 00:29:53 +08:00
leejet 5900ef6605 sync: update ggml, make cuda im2col a little faster 2025-08-03 01:29:40 +08:00
leejet e3f9366857 add wan vae suppport 2025-08-02 11:00:33 +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
leejetandErik 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 7cb41b190f fix: avoid encountering 'std::set undefined' in some environments 2024-01-02 22:37:01 +08:00
leejet 7fb8a51318 chore: make SD_BUILD_DLL visible only to SD_LIB 2024-01-02 22:31:40 +08:00
leejet 2c5f3fc53a chore: add support for building shared library 2024-01-02 21:05:44 +08:00
leejet 2e79a82f85 refactor: reorganize code and use c api (#133) 2024-01-01 16:22:18 +08:00
leejet b139434b57 docs: update README.md 2023-12-31 11:48:41 +08:00
leejet 14da17a923 fix: initialize some pointers to NULL 2023-12-30 14:24:45 +08:00
leejet 78ad76f3f4 feat: add SDXL support (#117)
* add SDXL support

* fix the issue with generating large images
2023-12-29 00:16:10 +08:00