Everything here is free and stays free — the format spec, the nodes, the workflows, the cartridges, the LoRAs. If it saved you a night of debugging (it contains several hundred of mine), tips keep the 5090 warm:<ul><li>☕ <a target="_blank" rel="ugc" href="https://ko-fi.com/joeygambino">Buy me a coffee on Ko-fi</a></li><li>💛 <a target="_blank" rel="ugc" href="https://github.com/sponsors/jlucasmcrell">Sponsor on GitHub</a></li><li>🔁 <a target="_blank" rel="ugc" href="https://liberapay.com/joeygambino">Liberapay</a> (recurring)</li><li>⚡ Or right here: the Civitai tip button on this page sends Buzz directly.</li></ul><h3 id="v2.0-is-here-riftcast:-characters-are-files-now.-design-a-human-from-dropdowns-watch-them-audition-and-get-a-portable-character-file-anyone-can-reuse-zero-training.-plus-the-24fps-accent-discovery-that-fixes-every-&quot;why-is-she-suddenly-british&quot;-bug.-full-story-in-the-v2.0-version-notes.">🚨 v2.0 IS HERE — RIFTCAST: CHARACTERS ARE FILES NOW. Design a human from dropdowns, watch them audition, and get a portable character file anyone can reuse — zero training. Plus the 24fps accent discovery that fixes every "why is she suddenly British" bug. Full story in the v2.0 version notes. 🚨</h3><hr /><h1 id="joyai-echo-multishot-the-character-video-studio-for-ltx-2.3">JoyAI-Echo Multishot — the character video studio for LTX-2.3</h1>One character. Any number of shots. Same face, same voice, every time — and as of 2.0, your characters are files you can share.This is a complete local pipeline for character-driven video on LTX-2.3's joint audio-video model: it generates the picture AND the voice in one diffusion pass — no TTS chain, no lip-sync post, no per-word API costs. A cross-shot memory bank keeps identity and voice locked across an entire multi-shot production, and a set of hard-won fixes makes the base model behave in ways stock workflows can't.<h2 id="riftcast-characters-are-files-now">RiftCast — characters are files now</h2>Things come through the Rift. Now characters do too.A <code>.riftcast</code> cartridge is one file carrying a character's voice (a 4-second anchor clip), face (reference stills), canonical description, and optionally their LoRAs and home environments. Drop it in <code>input/riftcast/</code>, restart, and mention the character in any script: they render with their face and their voice, in any scene, zero training. Cartridges extend the roleplay world's Character Card V3/CHARX lineage into photoreal video — a cartridge can carry a chat persona too, so the same character works in your roleplay client.Three ways to get one:<ul><li>Download — <code>WREN.riftcast</code> ships in this package; more on the <a target="_blank" rel="ugc" href="https://huggingface.co/joeygambino/joyai-echo-multishot-workflow">HuggingFace repo</a>.</li><li>Cut one from any render you like — one command: <code>python riftcast.py cut &lt;master.mp4&gt; &lt;NAME&gt; &lt;dna.txt&gt;</code>.</li><li>Design one from scratch — the bundled RiftCast Studio workflow is a full character creator. A Character Designer node covers identity (gender, age, ethnicity, skin, height, build, voice timbre, accent) and a Style + Wardrobe node covers appearance: 71 styles across 10 families, plus hair colour, hair shape, makeup, accessories, demeanor and a freeform wardrobe override. Queue it and the character records an audition tape; the Packer cuts their anchor and reference stills from that render and installs the cartridge automatically. Don't like who showed up? Re-queue with a new seed. Like them? They're a file, forever. (Our test reviewer rated a Designer character's lip sync "Real — very high confidence.")</li></ul>One workflow, one switch: RiftCast Studio routes between your prompt files (LPFF/JSON batch rendering, the classic path) and the Character Designer with a single dropdown.<h2 id="the-style-dropdown-never-sends-its-own-name">The style dropdown never sends its own name</h2>This is the part that makes it work rather than being a word list. "Goth" and "preppy" mean nothing to a video model, so no style label is ever written into a prompt. Each of the 71 entries expands into concrete renderable descriptors — garments named with material and condition, hair shape, makeup with placement, worn objects, and a demeanor that drives how the character physically carries themselves on camera. Picking one goth entry produces, in part:<blockquote>"...hair backcombed high at the crown with a straight fringe cut level with the eyebrows, wearing a long-sleeved black velvet dress with a frayed hem over laddered fishnet tights, and buckled boots scuffed grey at the toe, matte pale foundation, black liner drawn thick and winged past the outer corner..."</blockquote>Hair colour stays its own dropdown and styles specify only shape, so the two can never collide. Every style carries both a masculine and a feminine wardrobe reading, so it works across presentations instead of being gender-locked, and anything you set explicitly overrides the style's contribution.<h2 id="the-24-fps-law-why-your-accents-broke">The 24 fps law — why your accents broke</h2>The single most important thing this package knows: LTX-2.3's joint audio-video prior is 24 fps-native, and render fps is a hidden accent dial. At 25 fps the same prompt and seed render non-rhotic southern British; at 30 fps, broad Australian — and off-24 fps overrides accent wording in your prompt entirely. Verified by A/B with blind phonetic review. Everything here defaults to 24 and warns when you stray. If you want a British or Australian character, render their scenes at 25/30 — it beats any wording. (Pairs with the <a target="_blank" rel="ugc" href="https://huggingface.co/joeygambino/ltx23-accent-american-audio-lora">American-accent audio LoRA</a>, which makes accent wording enforceable in the young-voice registers the base model ignores.)<h2 id="the-rest-of-the-studio">The rest of the studio</h2><ul><li>Cross-shot memory bank — identity and voice persist across shots; anchor+latest policy stops drift snowballs.</li><li>Voice casting — drop a clip in <code>joyecho_voices/&lt;tag&gt;/</code> and that character speaks with that voice in every render. Script-pinned voices via <code>voice_refs</code>.</li><li>Finishing — AutoFinish builds your master automatically; deterministic upscale; optional <code>temporal_upscale</code> doubles motion to ~48 fps masters (24 fps render law preserved, audio untouched).</li><li>Long takes — up to 1441 frames (60 s) single-shot; the old ~10 s lip-sync cliff is fixed at the RoPE-clock level (Bug fix #0).</li><li>Correctness — a full sampler-path audit (seeded hires, cache keyed on checkpoint, cloned banks), fp8/INT8/GGUF loading paths, and widget values that survive updates (saved by name, not position).</li></ul><h2 id="hardware">Hardware</h2>Built and tested on RTX 5090/3090. GGUF DiT + the <a target="_blank" rel="ugc" href="https://huggingface.co/joeygambino/ltx23-gguf-vae-companion">9 GB VAE companion</a> runs the whole stack in ~11 GB system RAM instead of ~60.Everything is also on <a target="_blank" rel="ugc" href="https://github.com/jlucasmcrell/joyai-echo-multishot-patch">GitHub</a> and <a target="_blank" rel="ugc" href="https://huggingface.co/joeygambino">HuggingFace</a> — node pack, format spec, LoRAs (<a target="_blank" rel="ugc" href="https://huggingface.co/joeygambino/ltx23-surfaces-realism-lora">surface realism</a> too), quants, and demo cartridges. LTX-2 Community License.

JoyAI-Echo Multishot Workflow - one character, many shots, same face + voice

<pre><code>**v1.2 — A/V sync fix, AutoFinish, encoder picker, ready-to-run workflow**

This listing goes from v1.0 straight to v1.2. v1.1 was the workflow release, which now has its own listing.

**Breaking:** JoyEcho Model Loader's widgets were reorganized — all inputs are now optional, with file pickers above their manual-path fallbacks. Saved graphs from v1.0 will load this node with shifted values: delete and re-add the node (one output wire to reconnect), or start from the bundled workflow.

**Fixed**

- **Multi-shot A/V sync drift.** Each shot's generated audio runs ~30 ms shorter than its video, and the final assembly compounded that — audio ran ~120 ms early by shot 5, so lip sync visibly degraded through the piece. Each shot's wav is now padded to its own video duration before concat; sync is exact by construction. If multi-shot renders drifted out of sync late in a piece, this was why.
- **LLM Enhance no longer demands an API key for local endpoints.** When base_url is a local address (localhost, 127.0.0.1, 192.168.x, .local), a placeholder is sent automatically — Ollama, LM Studio and llama.cpp ignore it anyway. Cloud providers still raise a clear error naming the endpoint. An empty field previously errored even against a local server, which was the most common first-run stumble.
- **Reference Picker loads scripted refs for non-character scenes.** A scene's JSON `refs` block (`{"kelpie": "shot.png"}`) is now honored directly, so creature and location references load without the folder name having to appear in the prompt prose. Previously only names written in the prose matched.
- Hires refine no longer crashes on resolution retarget (cached seqlen mismatch).

**New**

- **AutoFinish node + worker** (missing from v1.0 entirely): after the render it automatically upscales the per-shot masters and assembles the audio-synced final MP4 — no manual upscale/concat step.
- **Model Loader: `gemma_file` dropdown** — pick the text encoder from `models/text_encoders` or `models/clip` instead of typing a path. Single-file .safetensors or .gguf encoders supported (v1.0 required the HF directory).
- **Prompt Source: `manual_path`** — point at any .txt/.json prompt file anywhere on disk, no folder conventions needed.
- **Conditioning cache** — the slow Gemma encode is cached per (prompt, encoder); re-renders with unchanged text skip the encode entirely.
- **Reference Picker:** character dropdown that survives node refreshes; default refs folder is now `input/joyecho_refs/` (one subfolder per character).
- **Writer system prompts** gained two hard-won sections: FRAMING (use shot-type nouns — "framed from the waist up" gets ignored or mis-read; keep speaking shots at medium close-up or tighter, because the VAE packs 32 px into one latent token and a wide shot puts the mouth below one token) and HUMAN MOVEMENT (state gait/turn/contact mechanics; only describe body parts that are in frame). The short-story prompt file is now included alongside the long-story one.

Canonical source and updates: https://huggingface.co/joeygambino/joyai-echo-multishot-workflow

</code></pre>

Files with SHA256: 121e68503e45d3572f044bd6086ff63a12ce8bc234bef1bd9b5ed1032ac56435