Deploy Stable Diffusion

Cause: A distill/acceleration LoRA and a pre-distilled checkpoint are alternative acceleration paths — the rule is to disable the distill LoRA whenever the checkpoint is already pre-distilled. Stacking two conflicting few-step schedules degrades output.

Fix: Apply AT MOST ONE acceleration path. Note: base Wan DOES need the lightx2v LoRA for few-step (the correct single path); the double-distill hazard only arises with a pre-merged/FusionX-style Wan checkpoint that already bakes lightx2v/CausVid in.

Cause: A relight LoRA above strength 0 imposes a relighting color shift matching the driving scene instead of preserving source color (shipped default is 0.0; Kijai's enabled default is 1.0).

Fix: Zero the relight/style LoRA when you want source color preserved. A tinted/off-color output means suspect an auxiliary LoRA near strength 1.0.

Cause: CORRECTED: RunPod caps a single env value at ~30KB and the total env payload at ~100KB (measured empirically; practical guardrails are MAX_ENV_VAR_SIZE=30000 and MAX_TOTAL_ENV_SIZE=100000). Cram a large workflow graph into a raw WORKFLOW_JSON and you blow the per-var or total budget, so other values (e.g. MODELS_TO_DOWNLOAD) may not take effect.

Fix: Never pass large JSON as a raw value — bake the default workflow into the image, or let the deploy path gzip it (WORKFLOW_JSON_GZ) or hand it off by URL (WORKFLOW_URL / GCS). Keep per-value <30KB and total <100KB. Small inline WORKFLOW_JSON is fine (the intended SDXL-checkpoint pattern). Diagnose by inspecting the pod's on-disk /models, not startup logs.

Cause: Unpinned by default: models pull from floating HF /resolve/main (branch HEAD), custom nodes are git-clone-latest (no SHA), Docker tags are reused, and only ~95% file-size is validated, not content hash. An upstream re-upload or newer node code silently changed bytes/behavior behind unchanged names.

Fix: Pin weights to a commit/revision, nodes to a SHA, images to a digest. Verify a pinned HF URL with `curl -sI -r 0-0 -A 'Mozilla/5.0' -L '<url>'` — MUST include -L (HF /resolve/ 302-redirects to a CDN; without -L you see 302 not 206).

Cause: The node was pinned to a commit predating when the required node class was added upstream. (The inverse also bites: a too-NEW pin can fail to import, forcing a rollback to an older release.)

Fix: Two-sided constraint: pin new enough that EVERY referenced node class is registered, but NOT so new it needs a ComfyUI newer than the baked image. Verify the pinned commit's NODE_CLASS_MAPPINGS registers all referenced classes AND imports cleanly against the deployed ComfyUI.

Cause: A reused mutable Docker tag means the container host serves an image it already cached under that tag and skips the re-pull after a rebuild (unless pull policy forces it or a differing digest is detected) — so it runs the stale image.

Fix: Push to a fresh tag or an immutable @sha256 digest. Treat 'not taking effect after rebuild' as a pull-cache symptom first.