The JoyAI-Echo × LTX-2.3 surgical merge — JoyAI-Echo's video/conditioning branch (cross-shot character memory) married to LTX-2.3-distilled-1.1's audio branch (the voice) — published in five encodings, one for every tier of hardware. Every clip below was rendered by the build it sits under.
43.0 GB · exact weights · the ground truth every number below is measured against
THE WITNESS (bf16 take) — the five-location identity demo on the reference weights. (This take has a brief voice drift in shot two; a replacement render is on the way.) For reference renders on 32 GB+ cards with sequential offload. model repo
23.4 GB · ~1.7° weight deviation, ~2.3° on the full scaled-mm compute path · needs RTX 40/50-series
THE WITNESS — five locations, one woman, one voice, one repeated sentence. Rendered on the bf16 checkpoint under the same fp8 scaled-mm compute path this file uses (hybrid: fp8 linears, bf16-exact modulation). Native fp8 tensor-core matmul for iteration speed. model repo
23.1 GB · 0.36° deviation, 44 dB SNR — functionally the same model as bf16
ONE ROOM (final) — one den, fixed tripod, she walks, sits, and returns. For the JoyAI-Echo multishot pack; weights dequantize to bf16 compute. Runs on any GPU. model repo
15.5 GB · 2.82° deviation · samples differently rather than worse
THE WITNESS (Q5_0 take) — the same five-location piece, Q5_0's own sample. For 16 GB cards on the multishot pack. model repo
27.2 GB full bundle · W8A8 with Hadamard rotation · stock ComfyUI ≥ 0.27, SM ≥ 7.5
Low-light stress test — she says “even in the dark, the gradients hold,” and they do. Standard LTX-2.3 workflows, no custom nodes; 1.5–2x faster on 30-series. model repo
Identical activations pushed through the real weight matrices — 60 layers, six types, five depths, both the audio and video branches — compared against bf16:
| build | cosine similarity | rel. error | SNR | angular deviation |
|---|---|---|---|---|
| Q8_0 GGUF | 0.999980 | 0.62% | 44.2 dB | 0.36° |
| fp8 as stored | 0.999564 | 2.94% | — | 1.69° |
| fp8 as computed (W8A8-style) | 0.999215 | 3.95% | — | 2.27° |
| Q5_0 GGUF | 0.998757 | 4.95% | 26.2 dB | 2.82° |
Three findings that were not givens: quantization error does not compound across the 48 transformer blocks (flat from block 0 to 47); the audio and video branches degrade identically (the audio branch is this merge's reason to exist — it is not more fragile); and Q8_0 is close enough to bf16 that the sampler cannot act on the difference.