leejet
98d6e71492
fix the issue that occurs when using CUDA with k-quants weights
2025-10-12 15:41:40 +08:00
leejet
6ea2a75929
apply jeffbolz f32 patch
...
https://github.com/leejet/stable-diffusion.cpp/pull/851#issuecomment-3335515302
2025-10-11 01:04:14 +08:00
leejet
d19d4a5903
Merge branch 'master' into qwen_image
2025-10-11 00:52:20 +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
Serkan Sahin
940a2018e1
chore: fix dockerfile libgomp1 dependency + improvements ( #852 )
2025-10-11 00:17:45 +08:00
Sharuzzaman Ahmat Raslan
b451728b2f
docs: update README.md ( #866 )
2025-10-11 00:11:10 +08:00
stduhpf
11f436c483
feat: add support for Flux Controls and Flex.2 ( #692 )
2025-10-11 00:06:57 +08:00
leejet
94f4f295c1
Merge branch 'master' into qwen_image
2025-09-25 23:13:00 +08:00
leejet
35843c77ea
fix: optimize the handling of embedding weight ( #859 )
2025-09-25 23:09:59 +08:00
leejet
178a415d89
Merge branch 'master' into qwen_image
2025-09-25 22:01:08 +08:00
leejet
6ad46bb700
sync: update ggml
2025-09-25 21:57:43 +08:00
leejet
a3a2b2d721
fix get_first_stage_encoding
2025-09-25 00:41:56 +08:00
leejet
a8d3aa0415
Merge branch 'master' into qwen_image
2025-09-25 00:39:57 +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
Wagner Bruna
f3140eadbb
fix: tensor loading thread count ( #854 )
2025-09-25 00:26:38 +08:00
Stefan-Olt
98ba155fc6
docs: HipBLAS / ROCm build instruction fix ( #843 )
2025-09-25 00:03:05 +08:00
Wagner Bruna
513f36d495
docs: include Vulkan compatibility for LoRA quants ( #845 )
2025-09-25 00:01:10 +08:00
rmatif
1e0d2821bb
fix: correct tensor deduplication logic ( #844 )
2025-09-24 23:22:40 +08:00
leejet
5af0bb0aee
change encoding of vocab_qwen.hpp to utf8
2025-09-22 23:57:59 +08:00
leejet
feb027958f
add qwen image i2i pipline
2025-09-22 23:45:29 +08:00
leejet
477911fb20
fix qwen image flash attn
2025-09-22 22:19:03 +08:00
leejet
cf19c6e759
add qwen image t2i pipeline
2025-09-22 21:18:28 +08:00
leejet
d232509b6e
add qwen image model
2025-09-21 23:37:13 +08:00
leejet
d8d4c268dc
mv qwen.hpp -> qwenvl.hpp
2025-09-21 17:21:56 +08:00
leejet
fe4e73156f
add qwen2.5 vl support
2025-09-21 00:31:48 +08:00
leejet
f88daa5114
add qwen tokenizer
2025-09-20 14:05:42 +08:00
leejet
fd693ac6a2
refactor: remove unused --normalize-input parameter ( #835 )
2025-09-18 00:12:53 +08:00
Wagner Bruna
171b2222a5
fix: avoid segfault for pix2pix models without reference images ( #766 )
...
* fix: avoid segfault for pix2pix models with no reference images
* fix: default to empty reference on pix2pix models to avoid segfault
* use resize instead of reserve
* format code
---------
Co-authored-by: leejet <leejet714@gmail.com>
2025-09-18 00:11:38 +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
vmobilis
97ad3e7ff9
refactor: simplify DPM++ (2S) Ancestral ( #667 )
2025-09-16 23:05:25 +08:00
Erik Scholz
8909523e92
refactor: move tiling cacl and debug print into the tiling code branch ( #833 )
2025-09-16 22:46:56 +08:00
rmatif
8376dfba2a
feat: add sgm_uniform scheduler, simple scheduler, and support for NitroFusion ( #675 )
...
* feat: Add timestep shift and two new schedulers
* update readme
* fix spaces
* format code
* simplify SGMUniformSchedule
* simplify shifted_timestep logic
* avoid conflict
---------
Co-authored-by: leejet <leejet714@gmail.com>
2025-09-16 22:42:09 +08:00
leejet
0ebe6fe118
refactor: simplify the logic of pm id image loading ( #827 )
2025-09-14 22:50:21 +08:00
rmatif
55c2e05d98
feat: optimize tensor loading time ( #790 )
...
* opt tensor loading
* fix build failure
* revert the changes
* allow the use of n_threads
* fix lora loading
* optimize lora loading
* add mutex
* use atomic
* fix build
* fix potential duplicate issue
* avoid duplicate lookup of lora tensor
* fix progeress bar
* remove unused remove_duplicates
---------
Co-authored-by: leejet <leejet714@gmail.com>
2025-09-14 22:48:35 +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
stduhpf
2c9b1e2594
feat: add VAE encoding tiling support and adaptive overlap ( #484 )
...
* implement tiling vae encode support
* Tiling (vae/upscale): adaptative overlap
* Tiling: fix edge case
* Tiling: fix crash when less than 2 tiles per dim
* remove extra dot
* Tiling: fix edge cases for adaptative overlap
* tiling: fix edge case
* set vae tile size via env var
* vae tiling: refactor again, base on smaller buffer for alignment
* Use bigger tiles for encode (to match compute buffer size)
* Fix edge case when tile is bigger than latent
* non-square VAE tiling (#3 )
* refactor tile number calculation
* support non-square tiles
* add env var to change tile overlap
* add safeguards and better error messages for SD_TILE_OVERLAP
* add safeguards and include overlapping factor for SD_TILE_SIZE
* avoid rounding issues when specifying SD_TILE_SIZE as a factor
* lower SD_TILE_OVERLAP limit
* zero-init empty output buffer
* Fix decode latent size
* fix encode
* tile size params instead of env
* Tiled vae parameter validation (#6 )
* avoid crash with invalid tile sizes, use 0 for default
* refactor default tile size, limit overlap factor
* remove explicit parameter for relative tile size
* limit encoding tile to latent size
* unify code style and format code
* update docs
* fix get_tile_sizes in decode_first_stage
---------
Co-authored-by: Wagner Bruna <wbruna@users.noreply.github.com>
Co-authored-by: leejet <leejet714@gmail.com>
2025-09-14 16:00:29 +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
Richard Palethorpe
a6a8569ea0
feat: Add SYCL Dockerfile ( #651 )
2025-09-14 13:02:59 +08:00
Erik Scholz
9e7befa320
fix: harden for large files ( #643 )
2025-09-14 12:44:19 +08:00
Wagner Bruna
c607fc3ed4
feat: use Euler sampling by default for SD3 and Flux ( #753 )
...
Thank you for your contribution.
2025-09-14 12:34:41 +08:00
Wagner Bruna
b54bec3f18
fix: do not force VAE type to f32 on SDXL ( #716 )
...
This seems to be a leftover from the initial SDXL support: it's
not enough to avoid NaN issues, and it's not not needed for the
fixed sdxl-vae-fp16-fix .
2025-09-14 12:19:59 +08:00
Wagner Bruna
5869987fe4
fix: make weight override more robust against ggml changes ( #760 )
2025-09-14 12:15:53 +08:00
Wagner Bruna
48956ffb87
feat: reduce CLIP memory usage with no embeddings ( #768 )
2025-09-14 12:08:00 +08:00
Wagner Bruna
ddc4a18b92
fix: make tiled VAE reuse the compute buffer ( #821 )
2025-09-14 11:41:50 +08:00
leejet
fce6afcc6a
feat: add sd3 flash attn support ( #815 )
2025-09-11 23:24:29 +08:00
