Mario Limonciello (AMD)
e212912bbf
Switch over ROCm builds to artifacts both for stable and preview releases
...
AMD is in the process of moving over to a brand new build system (TheRock).
They have a preview release stream for it, and it includes some significant
performance uplifts.
To let people experiment with both stacks generate artifacts both for the
stable (7.2) and preview (7.11) stacks.
In both cases - ROCm must be installed first to use this artifact.
It's intentionally not bundled because so many ISAs are included and the
size of the artifact balloons to an untenable size.
master-505-e212912
2026-02-13 23:50:50 -06:00
leejet
636d3cb6ff
refactor: reorganize the vocab file structure ( #1271 )
2026-02-11 00:44:17 +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
Mario Limonciello
45ce78a3ae
ci: correct rocm artifact of linux ( #1269 )
2026-02-10 23:19:28 +08:00
leejet
28ef93c0e1
refactor: reorganize the file structure ( #1266 )
2026-02-10 23:13:35 +08:00
leejet
3296545090
feat: add extra_c_crossattns support for llm embedder ( #1265 )
2026-02-10 00:00:17 +08:00
akleine
d60fb27560
fix: avoid unwanted file extension changes ( #1257 )
2026-02-09 23:59:43 +08:00
Wagner Bruna
c7ccafbd6f
fix: correct sdapi handling of cfg_scale and steps ( #1260 )
2026-02-09 23:34:19 +08:00
stduhpf
aa0b899397
fix: improve handling of VAE decode failures ( #1222 )
2026-02-09 23:29:41 +08:00
Mario Limonciello
5e264372ce
ci: add a github action to generate a Linux ROCm artifact ( #1258 )
2026-02-09 23:23:06 +08:00
leejet
f0f641a142
feat(server): add lora support to sdapi ( #1256 )
2026-02-08 00:11:16 +08:00
stduhpf
9f56833e14
feat: optimize LoKr at runtime ( #1233 )
2026-02-08 00:08:09 +08:00
Roj234
65891d74cc
fix: avoid the issue of NaN for qwen-image on certain devices ( #1249 )
2026-02-04 23:49:05 +08:00
leejet
f957fa3d2a
feat: add --fa option ( #1242 )
2026-02-01 21:44:54 +08:00
leejet
c252e03c6b
sync: update ggml
2026-02-01 20:54:23 +08:00
rmatif
e63daba33d
feat: add res_multistep, res_2s sampler and bong tangent scheduler ( #1234 )
2026-02-01 20:05:27 +08:00
stduhpf
3959109281
fix: improve LoCon support with other naming conventions ( #1239 )
2026-02-01 20:00:16 +08:00
leejet
e411520407
docs: add z-image-base example
2026-01-28 21:47:36 +08:00
leejet
43e829f219
refactor: unify the processing of attention mask ( #1230 )
2026-01-26 00:33:34 +08:00
leejet
7837232631
perf: make dit faster ( #1228 )
2026-01-25 22:50:10 +08:00
Equious
4ccce027b2
fix: correct mask and control image loading in cli ( #1229 )
2026-01-25 22:47:52 +08:00
leejet
fa61ea744d
fix: set default lora_model_dir to . ( #1224 )
2026-01-23 22:13:59 +08:00
leejet
5e4579c11d
feat: use image width and height when not explicitly set ( #1206 )
2026-01-22 23:54:41 +08:00
Wagner Bruna
329571131d
chore: clarify warning about missing model files ( #1219 )
2026-01-21 22:34:11 +08:00
leejet
a48b4a3ade
docs: add FLUX.2-klein support to news
2026-01-19 23:56:50 +08:00
stduhpf
b87fe13afd
feat: support new chroma radiance "x0_x32_proto" ( #1209 )
2026-01-19 23:51:26 +08:00
Oleg Skutte
e50e1f253d
feat: add taef2 support ( #1211 )
2026-01-19 23:39:36 +08:00
leejet
c6206fb351
fix: set VAE conv scale for all SDXL variants
2026-01-19 23:21:48 +08:00
akleine
639091fbe9
feat: add support for Segmind's Vega model ( #1195 )
2026-01-19 23:15:47 +08:00
leejet
9293016c9d
docs: update esrgan.md
2026-01-19 23:00:50 +08:00
leejet
2efd19978d
fix: use Unix timestamp for field instead of ISO string ( #1205 )
2026-01-19 00:21:29 +08:00
Wagner Bruna and leejet
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 <[email protected] >
2026-01-19 00:21:11 +08:00
leejet
9565c7f6bd
add support for flux2 klein ( #1193 )
...
* add support for flux2 klein 4b
* add support for flux2 klein 8b
* use attention_mask in Flux.2 klein LLMEmbedder
* update docs
2026-01-18 01:17:33 +08:00
Wagner Bruna
fbce16e02d
fix: avoid undefined behavior on image mask allocation failure ( #1198 )
2026-01-18 01:14:56 +08:00
akleine and leejet
7010bb4dff
feat: support for SDXS-512 model ( #1180 )
...
* feat: add U-Net specials of SDXS
* docs: update distilled_sd.md for SDXS-512
* feat: for SDXS use AutoencoderTiny as the primary VAE
* docs: update distilled_sd.md for SDXS-512
* fix: SDXS code cleaning after review by stduhpf
* format code
* fix sdxs with --taesd-preview-only
---------
Co-authored-by: leejet <[email protected] >
2026-01-14 01:14:57 +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
Weiqi Gao
271b594e74
sync: update ggml ( #1187 )
2026-01-14 00:28:55 +08:00
leejet
885e62ea82
refactor: replace ggml_ext_attention with ggml_ext_attention_ext ( #1185 )
2026-01-11 16:34:13 +08:00
rmatif and leejet
0e52afc651
feat: enable vae tiling for vid gen ( #1152 )
...
* enable vae tiling for vid gen
* format code
* eliminate compilation warning
---------
Co-authored-by: leejet <[email protected] >
2026-01-08 23:23:05 +08:00
leejet
27b5f17401
ci: only push Docker images on master or release
2026-01-08 23:03:32 +08:00
Flavio Bizzarri
dfe6d6c664
fix: missing newline after seed in sd_img_gen_params_to_str ( #1183 )
2026-01-08 22:52:22 +08:00
leejet
9be0b91927
docs: fix safetensors file extension notation
2026-01-06 23:31:03 +08:00
evanreichard
e7e83ed4d1
fix(server): use has_file for mask multipart detection ( #1178 )
2026-01-06 23:16:05 +08:00
Wagner Bruna
c5602a676c
feat: prioritize gguf and safetensors formats for embeddings and LoRAs ( #1169 )
2026-01-05 23:58:09 +08:00
Nuno
c34730d9b4
chore: downgrade ubuntu base image in musa container image ( #1176 )
...
Signed-off-by: rare-magma <[email protected] >
2026-01-05 23:56:34 +08:00
Nuno and leejet
fdcacc1ebb
ci: cancel old github action runs ( #1172 )
...
* ci: cancel old github action runs
Signed-off-by: rare-magma <[email protected] >
* ci: adjust concurrency to avoid canceling non-PR workflows
---------
Signed-off-by: rare-magma <[email protected] >
Co-authored-by: leejet <[email protected] >
2026-01-05 23:52:34 +08:00
Nuno
496ec9421e
chore: add Linux Vulkan build and Docker image workflows ( #1164 )
2026-01-05 23:42:12 +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