71-style character creator: Style + Wardrobe node, expanded attributes, Studio wired

README: New in 2.0 - RiftCast, Studio, Render Clock, 24fps default

v1.7: the 24fps rule (fps steers accents) - default 24 + warning; fp8 loader passthrough fix; AutoFinish console-flash fix

v1.6: voice casting system + sampler-path audit fixes

Cheat sheet: add the transformers version trap (requirements pin downgrades 5.x)

Add GitHub Sponsors to the support links

Add Ko-fi / Liberapay support links

Correct the fp8_scaled_mm guidance: it needs a bf16 or INT8 source, never the fp8 file

Add a Quick fixes cheat sheet at the top, led by fp8_scaled_mm and the INT8 trap

Point the Lite section at its dedicated repo

Card: document the Multishot Lite workflow (core-nodes-only) and distinguish it from the node pack

Set expectations up front: not one-click, tuning per machine expected, and I troubleshoot - open a discussion

Link the GitHub repo (nodes, workflow, releases, issues)

Card: answer 'zip or loose files?' at the top - a user got stuck on exactly this

docs: hires routing table everywhere (hires_factor = routing switch); PREVIEW-labeled SaveVideo; routing-framed tooltip; refreshed v1.5 zip

autofinish hires-aware: worker finishes from shot_hires masters and skips RTX when hires_factor>1 (RTX path kept for 1.0 runs); README section 19

credits: JD Joy Future Academy, Lightricks, TenStrip (strong-mode sigma ladder), RealRebelAI, Comfy-Org, Google

fix: cast float32 stragglers under quantization policies (plain-distilled-1.1-derived files store F32 tables; fp8_scaled_mm load crashed with Float x BFloat16) + sync drifted files

Add demo video (rendered with this build)

Changelog: split v1.2 (api_key local endpoints, refs force-inject) from v1.1 (workflow release)

Lead with the workflow: retitle card, workflow section first, patch as 'under the hood'; add workflow/video tags

v1.1: A/V sync fix, AutoFinish nodes, gemma_file dropdown, manual_path, framing/movement doctrine, ready-to-run multishot workflow

README: document memory-trim fix (critical), fp8_scaled_mm, resident_blocks, encoder_fp8, hires-fix, ref scheduling, robustness; full file list + no-cherry-pick warning

README: document fp8 gemma scale-key layout fix

LoRA hardening: kohya lora_down/up support + alpha scaling, fuse telemetry + zero-match warning, refuse comfy_quant checkpoints with clear error; lora_file dropdown

RefPicker: character dropdown, no silent scan-fallback, cache fix; head-trim applied to all outputs; lora_file dropdown on ModelLoader; gemma_path guard

Upload 11 files

initial commit