indigo
110adc781e
Port mechanism 2 of SCAIL-2 (arXiv:2606.10804) to LTX-2: extra per-token in-context conditioning channels (1 environment switch + K=6 character binding slots) concatenated onto the latent before the first projection. Faithful temporal encoding for LTX's VAE (temporal factor 8): each latent frame stacks its 8 pixel sub-frames along the channel dim, giving 8*(K+1)=56 channels (vs the paper's 4*(K+1)=28 on Wan 2.1). Plumbing (backward compatible; cond_channels=None leaves every existing pipeline unchanged): - LatentState/Modality gain an optional cond_channels field (patchified [B,T,C]). - LTXModel(mask_conditioning_channels=0) config-gates a widened patchify_proj; TransformerArgsPreprocessor concatenates cond_channels (or zero-pads) before it. - tools.clear_conditioning trims it; token-appending conditioning items (reference video/audio, driving, keyframe) extend it via extend_cond_channels. New: - VideoConditionByMaskChannels: encodes (K+1) pixel masks -> 56 channels, written onto the trailing driving tokens (noisy target stays all-zero, per the paper). - widen_patchify_proj_for_mask_channels: zero-init checkpoint surgery so a converted model reproduces the base output exactly until finetuned. Verified (CPU, random weights): backward compat, zero-init widened forward is bit-identical to baseline for any cond_channels, and the driving+mask pipeline forwards without crashing with correct placement/clipping. Visual quality requires Phase 3 finetuning; Replacement-mode z_ref height shift still deferred. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
47 lines
3.7 KiB
Markdown
47 lines
3.7 KiB
Markdown
# SCAIL-2 → LTX-2 移植任務追蹤
|
||
|
||
狀態圖例：✅ 完成 ｜ 🔄 進行中 ｜ ⬜ 未開始 ｜ ⏸️ 暫緩
|
||
|
||
相關計畫見 [`plan.md`](./plan.md)。
|
||
|
||
## Phase 1 — Driving 串接 item（推論期 PoC）
|
||
|
||
| # | 任務 | 狀態 | 產出 / 備註 |
|
||
|---|---|---|---|
|
||
| 1.1 | 新增 `VideoConditionByDrivingLatent` + `DrivingMode` | ✅ | `packages/ltx-core/src/ltx_core/conditioning/types/driving_video_cond.py`，以 `reference_video_cond.py` 為藍本，實作 ΔW width 偏移、時間對齊 target、`max_pos` 防呆、token 數防呆 |
|
||
| 1.2 | 匯出新 conditioning 類別 | ✅ | `conditioning/types/__init__.py`、`conditioning/__init__.py` |
|
||
| 1.3 | 免-GPU 資料流驗證腳本 | ✅ | 序列長度、ΔW 不重疊、時間對齊、frozen denoise_mask、attention_mask=None、`clear_conditioning` 剝除、超界/token 數防呆 — 全通過；ruff clean |
|
||
| 1.4 | （選配）端到端 smoke run | ✅ | 本機 CPU-only、無 checkpoint，改用小型真實 `LTXModel`（隨機權重）跑 pipeline 實走路徑：`create_noised_state`（含 driving cond）→ `modality_from_latent_state` → **真 transformer forward**（seq 160=target 80+driving 80）→ `clear_conditioning`（→80）。ANIMATION/REPLACEMENT 皆通過：不 crash、輸出 finite、driving frozen 且正確剝除。**僅驗證整合，不評估畫質** |
|
||
|
||
## Phase 2 — In-context mask channel（checkpoint 手術）
|
||
|
||
> **決策**：mask channel 時間編碼採**忠實堆疊**——每 latent 幀對應 8 個 pixel 子幀沿 channel 堆疊，`8×(K+1)=56` channel（LTX 時間因子 8，K=6）。非 Wan 的 4×(K+1)=28。
|
||
|
||
| # | 任務 | 狀態 | 備註 |
|
||
|---|---|---|---|
|
||
| 2.1 | `patchify_proj` 加寬（config-gated） | ✅ | `LTXModel(mask_conditioning_channels=0)`；>0 時 `patchify_proj=Linear(in+mask, inner)`。預設不變 |
|
||
| 2.2 | `LatentState`/`Modality` 帶 `cond_channels` 欄位 | ✅ | `types.py`、`modality.py` 加 `cond_channels: Tensor\|None=None`（patchified [B,T,C]）；`tools.clear_conditioning` 裁切；`helpers.modality_from_latent_state` 帶入 |
|
||
| 2.3 | 投影前 concat/zero-pad cond_channels | ✅ | `transformer_args.py` `_apply_patchify_proj`：寬度不足時用 cond_channels 補齊，None 則補零 |
|
||
| 2.4 | checkpoint zero-init 加寬轉換 | ✅ | `mask_channels_checkpoint.py` `widen_patchify_proj_for_mask_channels`：尾端補零欄，載入舊權重行為不變 |
|
||
| 2.5 | `VideoConditionByMaskChannels`（56ch） | ✅ | `mask_channels_cond.py`：1 環境開關 + K=6 綁定槽 → 空間下採樣 + 時間 8× 堆疊(causal 首幀複製)=56ch，寫入尾端 driving token，target 保持零 |
|
||
| 2.6 | token-append conditioning 延伸 cond_channels | ✅ | `cond_channels.py` `extend_cond_channels`；reference_video/reference_audio/driving/keyframe 皆接上 |
|
||
| 2.7 | Phase 2 驗證（免訓練） | ✅ | `verify_mask_channels.py`：mask=0 向後相容；zero-init 加寬 forward == baseline（任意 cond_channels）；driving+mask pipeline forward 不 crash、cond_channels 形狀/placement 正確、`clear_conditioning` 剝除 |
|
||
| 2.8 | Replacement Mode z_ref 高度位移 ΔH_ref | ⬜ | 仍暫緩（Phase 1 divergence，需獨立 reference token group） |
|
||
|
||
## Phase 3 — 訓練整合（ltx-trainer）
|
||
|
||
| # | 任務 | 狀態 | 備註 |
|
||
|---|---|---|---|
|
||
| 3.1 | dataset 產出 (target, driving, mask) | ⬜ | |
|
||
| 3.2 | 接上 conditioning + 微調 loss / 凍結策略 | ⬜ | |
|
||
|
||
## Phase 4 — Pipeline + CLI
|
||
|
||
| # | 任務 | 狀態 | 備註 |
|
||
|---|---|---|---|
|
||
| 4.1 | `scail_animation.py` pipeline + arg parser | ⬜ | 仿 `lipdub.py` |
|
||
|
||
## 決議紀錄
|
||
- **範圍**：先只做 Phase 1（推論期 PoC）。Phase 2+ 待 Phase 1 驗證後再討論。
|
||
- **架構前提**：SCAIL-2 建構於 Wan 2.1，本移植為跨架構移植。
|