master-480-b87fe13

feat: support new chroma radiance "x0_x32_proto" (#1209)

master-479-e50e1f2

feat: add taef2 support (#1211)

master-478-c6206fb

fix: set VAE conv scale for all SDXL variants

master-477-639091f

feat: add support for Segmind's Vega model (#1195)

master-475-2efd199

fix: use Unix timestamp for  field instead of ISO string (#1205)

master-474-61659ef

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>

master-473-9565c7f

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

master-472-fbce16e

fix: avoid undefined behavior on image mask allocation failure (#1198)

master-471-7010bb4

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>

master-470-48d3161

feat: add sd-server API support for steps, sampler and scheduler (#1173)