imggen - Local SDXL image generation on Intel Arc B580 under Slackware, via a containerized Intel Level Zero runtime

Age	Commit message (Collapse)	Author	Files	Lines
30 hours	Document resident-model default and IMGGEN_WIDTH/HEIGHT	Danilo M.	1	-5/+13
	Update README and CLAUDE.md for the two behavior changes: a bare daemon-up prompt run now uses the resident model instead of an interactive menu (menu removed), and default size comes from IMGGEN_WIDTH/IMGGEN_HEIGHT in .env (1280x960 landscape example, 1024x1024 fallback), overridable with -W/-H. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
31 hours	Document model menu, daemon lifecycle, and compose setup	Danilo M.	1	-10/+92
	Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
3 days	Initial commit: local SDXL image generation on Intel Arc B580	Danilo M.	1	-0/+100
	Containerized SDXL-base generation targeting a 12GB Arc B580 under Slackware. The container carries the Intel Level Zero runtime the host distro does not package; the fp16-fix VAE removes the fp32 upcast that would otherwise OOM at decode. - imggen: host wrapper (GPU passthrough, /out bind-mount, model cache) - generate.py: in-container XPU pipeline, scope-bounded to SDXL base - Dockerfile: pinned to the known-good torch-XPU / diffusers stack - README.md, CLAUDE.md: rationale, limits, and version-pinning notes Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>