bssrdf
d41f5fff69
perf: improved flux attention qkv unpacking ( #1306 )
2026-03-04 00:36:32 +08:00
Korsar13
810ef0cf76
fix: reset weight adapter for models if no loras in request ( #1307 )
2026-03-04 00:34:07 +08:00
leejet
5792c66879
feat: support some non-standard Anima weight names ( #1305 )
2026-03-01 22:01:29 +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
leejet
e64baa3611
refactor: reuse DiT's patchify/unpatchify functions ( #1304 )
2026-03-01 21:44:51 +08:00
leejet
cec4aedcfd
docs: add anima docs
2026-03-01 15:32:25 +08:00
rmatif
4cdfff5ff2
feat: add Anima support ( #1296 )
2026-03-01 15:23:18 +08:00
leejet
0752cc9d3a
fix: resolve image quality degradation issue ( #1297 )
2026-02-26 00:26:21 +08:00
Wagner Bruna
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
leejet
c9cd49701a
fix: safely handle whitespace and consecutive newlines ( #1288 )
2026-02-19 20:54:42 +08:00
akleine
c5eb1e4137
fix: avoid black images if using an invalid VAE (for SDXL) ( #1273 )
2026-02-19 20:54:18 +08:00
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
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
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
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 <leejet714@gmail.com>
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
0e52afc651
feat: enable vae tiling for vid gen ( #1152 )
...
* enable vae tiling for vid gen
* format code
* eliminate compilation warning
---------
Co-authored-by: leejet <leejet714@gmail.com>
2026-01-08 23:23:05 +08:00
