[Model] Adapt Wan2.2-I2V-A14B via LightX2V offline conversion path (#2134)

Signed-off-by: Celeste-jq <591998922@qq.com>
Co-authored-by: Canlin Guo <canlinguosdu@gmail.com>

examples/offline_inference/image_to_video/README.md

@@ -59,12 +59,13 @@ Key arguments:
 - `--negative-prompt`: Optional list of artifacts to suppress.
 - `--boundary-ratio`: Boundary split ratio for two-stage MoE models.
 - `--flow-shift`: Scheduler flow shift (5.0 for 720p, 12.0 for 480p).
+- `--sample-solver`: Wan2.2 sampling solver. Use `unipc` for the default multistep solver, or `euler` for Lightning/Distill checkpoints.
 - `--num-inference-steps`: Number of denoising steps (default 50).
 - `--fps`: Frames per second for the saved MP4 (requires `diffusers` export_to_video).
 - `--output`: Path to save the generated video.
 - `--vae-use-slicing`: Enable VAE slicing for memory optimization.
 - `--vae-use-tiling`: Enable VAE tiling for memory optimization.
-- `--cfg-parallel-size`: set it to 2 to enable CFG Parallel. See more examples in [`user_guide`](../../../docs/user_guide/diffusion/parallelism_acceleration.md#cfg-parallel).
+- `--cfg-parallel-size`: set it to 2 to enable CFG Parallel. See more examples in [`user_guide`](https://github.com/vllm-project/vllm-omni/tree/main/docs/user_guide/diffusion/parallelism/cfg_parallel.md).
 - `--tensor-parallel-size`: tensor parallel size (effective for models that support TP, e.g. LTX2).
 - `--enable-cpu-offload`: enable CPU offloading for diffusion models.
 - `--use-hsdp`: Enable Hybrid Sharded Data Parallel to shard model weights across GPUs.
@@ -74,3 +75,6 @@ Key arguments:
 
 
 > ℹ️ If you encounter OOM errors, try using `--vae-use-slicing` and `--vae-use-tiling` to reduce memory usage.
+
+For Wan2.2 LightX2V-converted local Diffusers directories and related LoRA
+assets, see the [LoRA guide](../../../docs/user_guide/diffusion/lora.md#wan22-lightx2v-offline-assembly).

examples/offline_inference/image_to_video/image_to_video.py

@@ -84,6 +84,13 @@ def parse_args() -> argparse.Namespace:
     parser.add_argument(
         "--flow-shift", type=float, default=5.0, help="Scheduler flow_shift (5.0 for 720p, 12.0 for 480p)."
     )
+    parser.add_argument(
+        "--sample-solver",
+        type=str,
+        default="unipc",
+        choices=["unipc", "euler"],
+        help="Sampling solver for Wan2.2 pipelines. Use 'euler' for Lightning/Distill setups.",
+    )
     parser.add_argument("--output", type=str, default="i2v_output.mp4", help="Path to save the video (mp4).")
     parser.add_argument("--fps", type=int, default=None, help="Frames per second for the output video.")
     parser.add_argument(
@@ -305,6 +312,7 @@ def main():
     print(f"  Model: {args.model}")
     print(f"  Inference steps: {args.num_inference_steps}")
     print(f"  Frames: {args.num_frames}")
+    print(f"  Solver: {args.sample_solver}")
     print(
         f"  Parallel configuration: cfg_parallel_size={args.cfg_parallel_size},"
         f" tensor_parallel_size={args.tensor_parallel_size}, vae_patch_parallel_size={args.vae_patch_parallel_size}"
@@ -326,9 +334,14 @@ def main():
             generator=generator,
             guidance_scale=guidance_scale,
             guidance_scale_2=args.guidance_scale_high,
+            boundary_ratio=args.boundary_ratio,
             num_inference_steps=num_inference_steps,
             num_frames=num_frames,
             frame_rate=frame_rate,
+            extra_args={
+                "sample_solver": args.sample_solver,
+                "flow_shift": args.flow_shift,
+            },
         ),
     )
     generation_end = time.perf_counter()

examples/online_serving/image_to_video/README.md

@@ -26,6 +26,23 @@ The script allows overriding:
 - `CACHE_BACKEND` (default: `none`)
 - `ENABLE_CACHE_DIT_SUMMARY` (default: `0`)
 
+### Ascend / Local LightX2V Example
+
+For a local Wan2.2-LightX2V Diffusers directory on Ascend/NPU, you can start the server like this:
+
+```bash
+vllm serve /path/to/Wan2.2-I2V-A14B-LightX2V-Diffusers-Lightning \
+  --omni \
+  --port 8091 \
+  --flow-shift 12 \
+  --cfg-parallel-size 1 \
+  --ulysses-degree 4 \
+  --use-hsdp \
+  --trust-remote-code \
+  --allowed-local-media-path / \
+  --seed 42
+```
+
 ## Async Job Behavior
 
 `POST /v1/videos` is asynchronous. It creates a video job and immediately
@@ -69,10 +86,35 @@ curl -X POST http://localhost:8091/v1/videos/sync \
   -F "guidance_scale_2=1.0" \
   -F "boundary_ratio=0.875" \
   -F "flow_shift=12.0" \
+  -F 'extra_params={"sample_solver":"euler"}' \
   -F "seed=42" \
   -o sync_i2v_output.mp4
 ```
 
+For Wan Lightning/Distill checkpoints, pass `{"sample_solver":"euler"}` via `extra_params`. The default solver is `unipc`.
+
+Example matching the local LightX2V deployment above:
+
+```bash
+curl -sS -X POST http://localhost:8091/v1/videos/sync \
+  -H "Accept: video/mp4" \
+  -F "prompt=A cat playing with yarn" \
+  -F "input_reference=@/path/to/input.jpg" \
+  -F "width=832" \
+  -F "height=480" \
+  -F "num_frames=81" \
+  -F "fps=16" \
+  -F "num_inference_steps=4" \
+  -F "guidance_scale=1.0" \
+  -F "guidance_scale_2=1.0" \
+  -F "boundary_ratio=0.875" \
+  -F "seed=42" \
+  -F 'extra_params={"sample_solver":"euler"}' \
+  -o ./output.mp4
+```
+
+Use `/v1/videos/sync` if you want to write the MP4 directly to a file. `POST /v1/videos` is async and returns job metadata, not inline `b64_json`.
+
 ## Storage
 
 Generated video files are stored on local disk by the async video API.
@@ -96,6 +138,9 @@ export VLLM_OMNI_STORAGE_MAX_CONCURRENCY=8
 # Basic image-to-video generation
 bash run_curl_image_to_video.sh
 
+# Wan Lightning/Distill checkpoints
+SAMPLE_SOLVER=euler bash run_curl_image_to_video.sh
+
 # Or execute directly (OpenAI-style multipart)
 create_response=$(curl -s http://localhost:8091/v1/videos \
   -H "Accept: application/json" \
@@ -111,6 +156,7 @@ create_response=$(curl -s http://localhost:8091/v1/videos \
   -F "guidance_scale_2=1.0" \
   -F "boundary_ratio=0.875" \
   -F "flow_shift=12.0" \
+  -F 'extra_params={"sample_solver":"euler"}' \
   -F "seed=42")
 
 video_id=$(echo "$create_response" | jq -r '.id')
@@ -169,9 +215,12 @@ curl -X POST http://localhost:8091/v1/videos \
   -F "guidance_scale_2=1.0" \
   -F "boundary_ratio=0.875" \
   -F "flow_shift=12.0" \
+  -F 'extra_params={"sample_solver":"euler"}' \
   -F "seed=42"
 ```
 
+`sample_solver` is supported by Wan2.2 online serving through the existing `extra_params` field, which is merged into the pipeline `extra_args`. Use `unipc` for the default multistep solver, or `euler` for Lightning/Distill checkpoints.
+
 ## Create Response Format
 
 `POST /v1/videos` returns a job record, not inline base64 video data.

examples/online_serving/image_to_video/run_curl_image_to_video.sh

@@ -7,6 +7,7 @@ INPUT_IMAGE="${INPUT_IMAGE:-../../offline_inference/image_to_video/qwen-bear.png
 BASE_URL="${BASE_URL:-http://localhost:8099}"
 OUTPUT_PATH="${OUTPUT_PATH:-wan22_i2v_output.mp4}"
 NEGATIVE_PROMPT="${NEGATIVE_PROMPT:-}"
+SAMPLE_SOLVER="${SAMPLE_SOLVER:-}"
 POLL_INTERVAL="${POLL_INTERVAL:-2}"
 
 if [ ! -f "$INPUT_IMAGE" ]; then
@@ -34,6 +35,10 @@ if [ -n "${NEGATIVE_PROMPT}" ]; then
   create_cmd+=(-F "negative_prompt=${NEGATIVE_PROMPT}")
 fi
 
+if [ -n "${SAMPLE_SOLVER}" ]; then
+  create_cmd+=(-F "extra_params={\"sample_solver\":\"${SAMPLE_SOLVER}\"}")
+fi
+
 create_response="$("${create_cmd[@]}")"
 video_id="$(echo "${create_response}" | jq -r '.id')"
 if [ -z "${video_id}" ] || [ "${video_id}" = "null" ]; then