steve a213c18263 fix(llamaswap): use A1111 /sdapi/v1/txt2img so seed is honored ...

The OpenAI /v1/images/generations endpoint ignores `seed` on our
stable-diffusion.cpp build — every render of a given prompt comes back
byte-identical, so a drawbot batch of N collapsed to one image. Switch the
image provider to sd-server's A1111 /sdapi/v1/txt2img endpoint, which honors
`seed` (verified live: distinct seeds -> distinct images on SDXL and
Qwen-Image). Size is split into width/height; llama-swap still routes by the
`model` field. Tests + ADR-0016 updated.

2026-06-28 22:56:25 -04:00

..

image.go

fix(llamaswap): use A1111 /sdapi/v1/txt2img so seed is honored

2026-06-28 22:56:25 -04:00

llamaswap_test.go

fix(llamaswap): use A1111 /sdapi/v1/txt2img so seed is honored

2026-06-28 22:56:25 -04:00

llamaswap.go

fix(llamaswap): address Gadfly review findings

2026-06-27 16:04:23 -04:00