The static workflow JSONs default to CyberRealisticXLPlay (set in an
earlier commit), but the KSampler still had euler/normal/CFG7/20 — the
generic settings I scaffolded with. Updated to the creator-published
defaults: dpmpp_2m_sde / karras / CFG 4 / 28 steps. CLIP skip 1
already correct (no node needed; default behavior).
Added a section to the deployment README spelling out the trade-off:
static workflows are locked to one checkpoint family at a time because
Open WebUI's nodes mapping doesn't expose sampler/CFG/scheduler/CLIP
skip/prefix. For multi-checkpoint use, the smart_image_gen Tool path is
the only one that gets these right per-prompt.
Re-paste workflows into Open WebUI Settings → Images to pick up.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Each style now gets a proper baseline covering quality, anatomy, and
watermark/signature suppression — plus the appropriate style-leak guards
(no-cartoon for photo, no-human for furry, score_4–6 suppression for
pony). Quality terms only; no NSFW filtering by default since several
checkpoints in this set are commonly used for adult work and would
fight a baked-in content filter. If SFW-by-default is wanted, add an
explicit safe-mode flag rather than expanding NEGATIVES.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Open WebUI overwrites node 7's text when the request supplies a
negative_prompt, so the default only takes effect when one isn't
provided — which is the common case for the image-button path since the
chat UI doesn't expose the field. Generic quality terms only (no style
or content restrictions) so the default is safe across SD/SDXL/Flux
swaps and doesn't fight whichever checkpoint is loaded.
The smart_image_gen Tool already had per-style defaults; this only
affects the non-Tool image-gen path.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Open WebUI Tool the LLM invokes instead of the built-in image action.
Auto-routes among the seven SDXL checkpoints (photo / juggernaut /
pony / general / furry-{nai,noob,il}) based on either an explicit
`style` arg or first-match-wins regex over the prompt. Constructs the
ComfyUI workflow inline, submits via /prompt, polls /history, returns
the result as a base64 data-URI markdown image so no extra hosting is
needed. Per-style default negatives. ComfyUI URL / steps / CFG /
timeout are admin-tunable Valves.
Filters can't see image-gen requests in Open WebUI (the routers skip
the filter chain), so the LLM-driven Tool is the only path that
gives intent-aware routing without changing the chat UX.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Drops the SD 1.5 placeholder. The shipped txt2img/img2img workflows now
reference CyberRealisticXLPlay_V8.0_FP16.safetensors (the checkpoint
figment used in production), and comfyui-init-models.sh ships with no
active fetches — operators uncomment examples or add their own URLs.
The script + workflow filenames have to line up; README explains.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Mirrors the Ollama model-init pattern: a one-shot Alpine container that
mounts the comfyui-models volume and runs comfyui-init-models.sh, which
curls direct download URLs (HuggingFace by default) into the right
subdirectories. Idempotent — already-present files are skipped.
HF_TOKEN is plumbed through for gated repos (Flux-dev, SD3, etc.) and is
opt-in via .env. The default list ships SD 1.5 only, matching the
placeholder filename in workflows/*.json. Examples for SDXL, Flux, and
upscalers are commented in the script.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
So changing the deployment's hostnames is a one-file edit (.env) instead
of touching docker-compose.yml. WEBUI_URL is the full URL with scheme
(Open WebUI uses it for auth redirects); LLM_URL is the bare hostname
(Anubis wants it for COOKIE_DOMAIN).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Drops the duplicate standalone compose / .env.example / SETUP.md at the
repo root. Bring-up content folded into deployments/ai-stack/README.md
so there's exactly one set of deployment instructions, sitting next to
the files it describes. Root README is now just the repo overview and a
pointer at the deployment.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Five models from the production GPU host's current pull set. Picks up
the idempotency-checking loop pattern from the source script so re-runs
print "already present" instead of re-pulling.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Sanitized snapshot of the live srvno.de stack: Caddy + Ollama (with
preseed) + ComfyUI + Open WebUI + Anubis stub. Real hostnames,
secrets, and bcrypt hash replaced with placeholders so the dir is safe
to commit.
Caddyfile updated to point at comfyui:8188 (the source file pointed at
the now-removed forge service). Dropped FIGMENT_/FORGE_/SEGMENT_IMAGE_TAG
from the env example. Harmonised the init-models.sh mount path between
ollama and model-init services.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
CI builds and pushes the comfyui-nvidia image to the Gitea container
registry on every v* tag, mirroring the figment release workflow. Compose
now references the registry image (with build context kept for local
iteration) and the docs reflect the pull-by-default flow.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Replaces the figment/segment/Forge stack with a single ComfyUI backend
fronted by Open WebUI's native ComfyUI integration. ComfyUI is built from
the official manual install for NVIDIA. Ships txt2img and img2img workflow
templates plus matching node-mapping JSONs that paste into Open WebUI's
admin panel.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
