Link released Qwen prompt pipeline

Replace the manual prompt-alignment outline with executable CLI instructions from the public release.

README.md

@@ -110,43 +110,40 @@ trajectories.
 
 ## Qwen3-VL prompt alignment for custom inputs
 
-For a new first frame and an ordinary user request, we recommend using a local
-`Qwen/Qwen3-VL-8B-Instruct` call before ReMind inference. Give Qwen only the
-initial image and the user's text; do not provide future frames, evaluation
-criteria, or a hand-written target caption. Use greedy decoding and ask for a
-JSON object containing:
-
-- `scene_caption`: an English, content-only description of the initial state,
-  physical progression, and requested final state;
-- `control_requests`: any explicit `camera`, `occluder`, or `light` request,
-  with an exact supporting substring from the user text; and
-- `clarification_questions`: unresolved intent or conflicting controls.
-
-Preserve actions, negations, identities, directions, and stated end goals.
-Keep camera motion and reversible visibility events out of `scene_caption`:
-camera geometry belongs in a bundled trajectory, while occluder/light timing
-belongs in the preset's `control` block. Never ask Qwen to invent camera
-matrices or replace a bundled pair-fixed trajectory with an analytic path.
-
-Copy the accepted `scene_caption` into the closest preset, configure at most
-one supported control, and validate the resolved seven-chunk schedule before
-loading weights:
+The optional adapter turns one initial image and an ordinary user request into
+an audited, executable ReMind preset using greedy
+`Qwen/Qwen3-VL-8B-Instruct` inference:
 
 ```bash
-python inference.py --preset /path/to/custom_case.yaml --dry-run
+pip install -r requirements_prompt_engineering.txt
+
+python tools/rewrite_remind_prompt.py \
+  --input-image /path/to/first_frame.png \
+  --user-prompt '继续把谷物倒进盘子里，让它逐渐堆积，但不要洒出来。' \
+  --name cereal_user \
+  --output-dir outputs/prompt_alignment/cereal_user
+
+python inference.py \
+  --preset outputs/prompt_alignment/cereal_user/preset.yaml \
+  --dry-run
 
 python inference.py \
-  --preset /path/to/custom_case.yaml \
+  --preset outputs/prompt_alignment/cereal_user/preset.yaml \
   --model-folder checkpoints/Wan2.2-TI2V-5B \
   --base-checkpoint checkpoints/ReMind-5B/ReMind-5B.safetensors \
   --ema-checkpoint checkpoints/ReMind-5B/ReMind-5b-dmd-ema.safetensors \
-  --output outputs/custom_case.mp4
+  --output outputs/cereal_user.mp4
 ```
 
-Treat Qwen's rewrite and self-review as heuristic. Reject or manually review
-outputs that drop a negation, invent an event, mix control language into the
-scene caption, request multiple controls, or leave the intent ambiguous.
-Fixed project-page captions should be used verbatim rather than rewritten.
+The adapter keeps scene dynamics separate from camera/visibility controls,
+compiles seven chunk-local prompts, and only exports a preset after schema and
+heuristic VLM self-audit checks pass. It never invents camera geometry: camera
+requests must select one of the bundled pair-fixed trajectories.
+
+See [`docs/prompt_alignment.md`](docs/prompt_alignment.md) for camera,
+occluder, light, local-model, and failure-handling options. The self-audit is
+heuristic, so review unusual requests and keep fixed project-page captions
+unchanged.
 
 ## Checkpoint lineage and validation