DarthAffe/stable-diffusion.cpp
1
0 Fork 0
mirror of https://github.com/leejet/stable-diffusion.cpp.git synced 2026-11-11 11:26:34 +00:00
Code Issues Packages Projects Releases Wiki Activity
603 Commits 3 Branches 824 Tags
381e0df50fd0c58b7ea0b662a7c48ee603400736
Commit Graph
75 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
Wagner BrunaPiotr WilkinJunmo Kimleejet
 		57ff2eb0f4 feat: support for memory-mapping model weights (#1414) 
Co-authored-by: Piotr Wilkin <piotr.wilkin@syndatis.com>
Co-authored-by: Junmo Kim <me@junmo.kim>
Co-authored-by: leejet <leejet714@gmail.com>
 2026-05-15 00:30:03 +08:00
Wagner Bruna 586b6f1481 feat: adapt res samplers for flow models for eta > 0 (#1436) 2026-05-06 21:49:06 +08:00
Wagner BrunaStéphane du HamelCyberhan123leejet
 		b8079e253d feat: transition from compile-time to runtime backend discovery (#1448) 
Co-authored-by: Stéphane du Hamel <stephduh@live.fr>
Co-authored-by: Cyberhan123 <255542417@qq.com>
Co-authored-by: leejet <leejet714@gmail.com>
 2026-04-29 23:26:57 +08:00
Wagner Bruna 331cfa5387 fix: release VAE compute buffer after tiled encoding (#1465) 2026-04-29 22:25:30 +08:00
Wagner Bruna 7023fc4cfb fix: correct image to image DDIM and TCD (#1410) 2026-04-19 17:51:28 +08:00
Wagner Bruna e77e4c46bf feat: adapt LCM for flow models (#1413) 2026-04-19 17:49:46 +08:00
Wagner Bruna f3f69e2fbe feat: add DPM++ (2S) Ancestral implementation for flow models (#1428) 2026-04-18 15:05:09 +08:00
Wagner Bruna 2bcff67480 fix: correct dpm++2s_a second model call (#1435) 2026-04-18 14:54:41 +08:00
Wagner Bruna ee5bf956b0 chore: allow building the embedded UI header separately (#1415) 2026-04-15 22:07:31 +08:00
Wagner Brunaandprofessor-moody 118489eb5c chore: harden safetensors and gguf loading code (#1404) 
Co-authored-by: professor-moody <keys@nimbus.lan>
 2026-04-11 17:19:57 +08:00
Wagner Bruna be9f51b25c refactor: simplify DiscreteFlowDenoiser (#1405) 2026-04-11 17:18:23 +08:00
Wagner Bruna dd753729cc fix: correct double increment on flow denoisers sigma calculations (#1372) 2026-04-08 23:13:05 +08:00
Wagner Brunaandleejet 687a81f251 chore: make libwebp optional and support system libwebp (#1387) 
Co-authored-by: leejet <leejet714@gmail.com>
 2026-04-05 23:52:05 +08:00
Wagner Brunaandleejet 99c1de379b feat: ancestral sampler implementations for flow models (#1374) 
* feat: add support for the eta parameter to ancestral samplers

* feat: Euler Ancestral sampler implementation for flow models

* refine flow ancestral sampling and normalize eta defaults

---------

Co-authored-by: leejet <leejet714@gmail.com>
 2026-04-02 01:35:29 +08:00
Wagner Bruna 4fe7a35939 feat(server): add generation metadata to png images (#1217) 2026-03-31 23:06:27 +08:00
Wagner Bruna 02dd5e5dd2 refactor: move VAE tiling parameters to SDGenerationParams (#1261) 2026-03-30 23:09:38 +08:00
Wagner Bruna 6293ab5aaf docs: update Spectrum info about DiT models (#1360) 2026-03-30 00:12:57 +08:00
Wagner Bruna 630ee03f23 refactor: move all cache parameter defaults to the library (#1327) 2026-03-15 16:43:46 +08:00
Wagner Bruna f6968bc589 chore: remove SD_FAST_SOFTMAX build flag (#1338) 2026-03-15 16:42:47 +08:00
Wagner Bruna 39d54702a6 feat: accept legacy image parameter on v1/images/edits (#1270) 2026-03-01 22:00:50 +08:00
Wagner Bruna 60889bc9a1 fix: correct sdapi LoRA file handling (#1276) 2026-03-01 21:57:06 +08:00
Wagner Brunaandleejet b314d80ad0 feat: turn flow_shift into a generation parameter (#1289) 
* feat: turn flow_shift into a generation parameter

* format code

* simplify set_shift/set_parameters

* fix sd_sample_params_to_str

* remove unused variable

* update docs

---------

Co-authored-by: leejet <leejet714@gmail.com>
 2026-02-26 00:26:04 +08:00
Wagner Bruna adea272225 feat(server): use image and command-line dimensions by default on server (#1262) 2026-02-11 00:42:50 +08:00
Wagner Bruna c7ccafbd6f fix: correct sdapi handling of cfg_scale and steps (#1260) 2026-02-09 23:34:19 +08:00
Wagner Bruna 329571131d chore: clarify warning about missing model files (#1219) 2026-01-21 22:34:11 +08:00
Wagner Brunaandleejet 61659ef299 feat: add basic sdapi support to sd-server (#1197) 
* feat: add basic sdapi support to sd-server

Compatible with AUTOMATIC1111 / Forge.

* fix img2img with no mask

* add more parameter validation

* eliminate MSVC warnings

---------

Co-authored-by: leejet <leejet714@gmail.com>
 2026-01-19 00:21:11 +08:00
Wagner Bruna fbce16e02d fix: avoid undefined behavior on image mask allocation failure (#1198) 2026-01-18 01:14:56 +08:00
Wagner Bruna 48d3161a8d feat: add sd-server API support for steps, sampler and scheduler (#1173) 2026-01-14 00:34:27 +08:00
Wagner Bruna c5602a676c feat: prioritize gguf and safetensors formats for embeddings and LoRAs (#1169) 2026-01-05 23:58:09 +08:00
Wagner Bruna d0d836ae74 feat: support mmap for model loading (#1059) 2025-12-28 22:38:29 +08:00
Wagner Bruna cc107714d7 fix: consistently pass 2nd-order samplers half steps as negatives (#1095) 2025-12-27 15:54:18 +08:00
Wagner Bruna 7c88c4765c chore: give feedback about cfg values smaller than 1 (#1088) 2025-12-19 23:41:52 +08:00
Wagner Brunaandleejet 78e15bd4af feat: default to LCM scheduler for LCM sampling (#1109) 
* feat: default to LCM scheduler for LCM sampling

* fix bug and attempt to get default scheduler for vid_gen when none is set

---------

Co-authored-by: leejet <leejet714@gmail.com>
 2025-12-18 21:43:39 +08:00
Wagner Bruna e687913bf1 chore: remove lora_model_dir parameter (#1100) 2025-12-16 22:37:45 +08:00
Wagner Bruna 200cb6f2ca fix: avoid crash with VAE tiling and certain image sizes (#1090) 2025-12-15 23:51:40 +08:00
Wagner Bruna a3a88fc9b2 fix: avoid crash loading LoRAs with bf16 weights (#1077) 2025-12-12 22:36:54 +08:00
Wagner Bruna e72aea796e feat: embed version string and git commit hash (#1008) 2025-12-09 22:38:54 +08:00
Wagner Bruna 118683de8a fix: correct preview method selection (#1038) 2025-12-04 22:43:16 +08:00
Wagner Bruna 99e17232a4 fix: prevent NaN issues with Z-Image on certain ROCm setups (#1034) 2025-12-03 22:19:34 +08:00
Wagner Bruna e4c50f1de5 chore: add sd_ prefix to a few functions (#967) 2025-12-01 22:43:52 +08:00
Wagner Bruna 673dbdda17 fix: add missing line cleanup for s/it progress display (#891) 2025-11-30 11:45:30 +08:00
Wagner Bruna 0249509a30 refactor: add user data pointer to the image preview callback (#1001) 2025-11-30 11:34:17 +08:00
Wagner Bruna 45c46779af feat: add LCM scheduler (#983) 2025-11-22 13:53:31 +08:00
Wagner Brunaandmasamaru-san b542894fb9 fix: avoid crash on default video preview path (#997) 
Co-authored-by: masamaru-san
 2025-11-22 12:46:27 +08:00
Wagner Bruna 199e675cc7 feat: support for --tensor-type-rules on generation modes (#932) 2025-11-16 17:07:32 +08:00
Wagner Bruna e8eb3791c8 fix: typo in --lora-apply-mode help (#972) 2025-11-16 14:48:00 +08:00
Wagner Bruna aa44e06890 fix: avoid crash with LoRAs and type override (#974) 2025-11-16 14:47:36 +08:00
Wagner Bruna 945d9a9ee3 docs: add Koboldcpp as an available UI (#930) 2025-11-02 02:03:01 +08:00
Wagner Bruna 353e708844 docs: update ggml and llama.cpp URLs (#931) 2025-11-02 02:02:44 +08:00
Wagner Bruna 8a45d0ff7f chore: clean up stb includes (#919) 2025-10-28 23:25:45 +08:00
Wagner Bruna 64a7698347 chore: report number of Qwen layers as info (#901) 2025-10-18 23:22:01 +08:00
Wagner Bruna c64994dc1d fix: better progress display for second-order samplers (#834) 2025-10-13 22:12:48 +08:00
Wagner Bruna 5436f6b814 fix: correct canny preprocessor (#861) 2025-10-13 22:02:35 +08:00
Wagner Bruna 9727c6bb98 fix: resolve VAE tiling problem in Qwen Image (#873) 2025-10-12 23:45:53 +08:00
Wagner Bruna aa68b875b9 refactor: deal with default img-cfg-scale at the library level (#869) 2025-10-12 23:17:52 +08:00
Wagner Brunaandleejet 5b261b9cee feat: add a stand-alone upscale mode (#865) 
* feat: add a stand-alone upscale mode

* fix prompt option check

* format code

* update README.md

---------

Co-authored-by: leejet <leejet714@gmail.com>
 2025-10-12 23:10:02 +08:00
Wagner Bruna f3140eadbb fix: tensor loading thread count (#854) 2025-09-25 00:26:38 +08:00
Wagner Bruna 513f36d495 docs: include Vulkan compatibility for LoRA quants (#845) 2025-09-25 00:01:10 +08:00
Wagner Brunaandleejet 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
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
Wagner Bruna ac5a215998 fix: use {} for params init instead of memset (#781) 2025-09-10 21:49:29 +08:00
Wagner Bruna abb36d66b5 chore: update flash attention warnings (#805) 2025-09-10 21:38:21 +08:00
Wagner Bruna ff4fdbb88d fix: accept NULL in sd_img_gen_params_t::input_id_images_path (#809) 2025-09-10 21:22:55 +08:00
Wagner Bruna 2eb3845df5 fix: typo in the verbose long flag (#783) 2025-09-04 00:49:01 +08:00
Wagner Bruna eea77cbad9 feat: throttle model loading progress updates (#782) 
Some terminals have slow display latency, so frequent output
during model loading can actually slow down the process.

Also, since tensor loading times can vary a lot, the progress
display now shows the average across past iterations instead
of just the last one.
 2025-09-01 21:32:01 +08:00
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.
 2025-08-03 01:24:40 +08:00
Wagner Brunaandone-lithe-rune 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>
 2025-07-28 22:00:27 +08:00
Wagner Bruna 6d84a30c66 feat: overriding quant types for specific tensors on model conversion (#724) 2025-07-08 00:11:38 +08:00
Wagner Bruna 76c72628b1 fix: fix a few typos on cli help and error messages (#714) 2025-07-04 22:15:41 +08:00
Wagner Bruna 0d8b39f0ba fix: avoid crash on sdxl loras (#658) 
Some SDXL LoRAs (eg. PCM) can exceed 12k nodes.
 2025-06-30 23:29:32 +08:00
Wagner Bruna b1fc16b504 fix: allow resetting clip_skip to its default value (#697) 2025-06-30 23:23:21 +08:00