From db40fd83d2b91298a2f1138c05a356463a7cf3f7 Mon Sep 17 00:00:00 2001 From: HuangJi <32611516+IPostYellow@users.noreply.github.com> Date: Wed, 8 Jul 2026 10:42:50 +0800 Subject: [PATCH] [diffusion] model: support LingBot-World 2.0 (#30361) --- .../LingBot-World/LingBot-World-2.0.mdx | 177 ++++++++++++++++++ docs_new/cookbook/diffusion/intro.mdx | 6 + docs_new/docs.json | 3 +- .../configs/pipeline_configs/__init__.py | 2 + .../configs/pipeline_configs/lingbot_world.py | 8 + python/sglang/multimodal_gen/registry.py | 8 + 6 files changed, 203 insertions(+), 1 deletion(-) create mode 100644 docs_new/cookbook/diffusion/LingBot-World/LingBot-World-2.0.mdx diff --git a/docs_new/cookbook/diffusion/LingBot-World/LingBot-World-2.0.mdx b/docs_new/cookbook/diffusion/LingBot-World/LingBot-World-2.0.mdx new file mode 100644 index 000000000..24757a3a4 --- /dev/null +++ b/docs_new/cookbook/diffusion/LingBot-World/LingBot-World-2.0.mdx @@ -0,0 +1,177 @@ +--- +title: LingBot World 2.0 +metatags: + description: "Serve LingBot World 2.0 realtime camera-controlled video world models with SGLang-diffusion." +tag: REALTIME +--- + +
+ realtime + world model + causal DiT +
+ +## 1. Model Introduction + +LingBot World 2.0 is a realtime camera-controlled video world model. In SGLang-diffusion, it belongs to the realtime causal path: the server keeps a live session, samples control signals per chunk, reuses causal DiT state, and decodes video frames incrementally. + +This is different from offline diffusion video models such as Wan or LTX. Offline models denoise a bounded latent sequence for one request. Realtime world models generate a continuing stream, so the runtime must manage session state, control events, causal attention cache, and VAE decode cache. + +## 2. Deployment + +```bash Command +export SGLANG_LINGBOT_LAZY_VAE_ENCODE_BLACK_FRAMES=60 +export SGLANG_LINGBOT_ENABLE_INTERACTIVE_KV_WINDOW=true +sglang serve \ + --model-path robbyant/lingbot-world-v2-diffusers \ + --pipeline-class-name LingBotWorldCausalDMDPipeline \ + --num-gpus 8 \ + --ulysses-degree 8 \ + --dit-cpu-offload false \ + --text-encoder-cpu-offload false \ + --vae-config.use-parallel-decode true \ + --vae-config.parallel-decode-mode spatial \ + --enable-torch-compile false +``` + +## 3. Realtime WebUI + +The lightweight local WebUI is useful for validating latency, frame transport, and camera control behavior. + +```bash Command +python -m http.server 18080 -d python/sglang/multimodal_gen/apps/realtime_webui +``` + +Open `http://127.0.0.1:18080` and use: + +```text Example +ws://127.0.0.1:30000/v1/realtime_video/generate +``` + +## 4. HTTP and WebSocket API + +LingBot World 2.0 uses the realtime video WebSocket endpoint. The server keeps one live session, generates one chunk at a time, and accepts runtime control events while generation is running. + +### Endpoints + +| API | Method | Purpose | Notes | +| --- | --- | --- | --- | +| `/v1/models` | `GET` | Query the served model id before opening a session. | The WebUI uses this to fill the model field when the server exposes model metadata. | +| `/v1/realtime_video/generate` | `WebSocket` | Create one realtime LingBot session and stream generated video chunks. | The first client message must be an `init` message encoded with MessagePack. | + +### `init` message + +Send this MessagePack map immediately after the WebSocket opens. + +| Parameter | Type | Required | Meaning | +| --- | --- | --- | --- | +| `type` | string | Yes | Must be `"init"`. | +| `model` | string | No | Model id. Leave empty to use the served model. | +| `prompt` | string | Yes | Text prompt for the initial scene and motion style. | +| `first_frame` | bytes or string | Yes | Initial reference image. Send bytes from the WebUI/client, or a server-readable image path/string. | +| `size` | string | Yes | Generation size as `WIDTHxHEIGHT`, for example `832x480`. | +| `fps` | number | Yes | Target playback FPS for the generated stream. | +| `num_frames` | integer | Yes | Frames per generated chunk. LingBot uses chunked causal generation, so this controls per-chunk latency and queue size. | +| `seed` | integer | No | Random seed for deterministic sampling. | +| `num_inference_steps` | integer | No | Denoising steps per chunk. LingBot defaults to `4` when omitted. | +| `guidance_scale` | number | No | Classifier-free guidance scale. Realtime LingBot commonly uses `1`. | +| `negative_prompt` | string | No | Negative prompt passed to the diffusion pipeline. | +| `max_chunks` | integer | No | Stop after this many chunks. Omit for a continuous session. | +| `realtime_causal_sink_size` | integer | No | Number of sink frames/tokens retained in the causal attention window. | +| `realtime_causal_kv_cache_num_frames` | integer | No | Number of recent frames retained in the causal KV cache window. | +| `realtime_output_format` | `"webp"`, `"jpeg"`, `"raw"` | No | Preview/output transport. `webp` and `jpeg` send encoded preview frames; `raw` sends raw RGB; omit for lossless delta-gzip RGB. | +| `output_compression` | integer | No | Preview quality for `webp` or `jpeg`, from `1` to `100`. | +| `enable_upscaling` | boolean | No | Enable server-side super resolution after frame decode. | +| `upscaling_scale` | integer | No | Super-resolution scale. Current default is `4` when upscaling is enabled. | +| `upscaling_model_path` | string | No | Optional Real-ESRGAN model path. | +| `enable_frame_interpolation` | boolean | No | Enable frame interpolation. Keep this disabled when measuring true generated FPS. | +| `frame_interpolation_exp` | integer | No | Interpolation multiplier exponent. `1` means 2x frames. | +| `frame_interpolation_scale` | number | No | RIFE internal scale for interpolation. | +| `frame_interpolation_model_path` | string | No | Optional RIFE model path. | +| `condition_inputs.camera_actions` | `list[list[string]]` | No | Initial scripted camera actions, one action list per frame. | + +### Runtime `event` messages + +After `init`, send MessagePack event maps to update the live session. + +| Parameter | Type | Required | Meaning | +| --- | --- | --- | --- | +| `type` | string | Yes | Must be `"event"`. | +| `kind` | `"prompt"`, `"camera_actions"`, or `"composite_input"` | Yes | Runtime event kind. | +| `payload` | string, object, or list | Yes | For `prompt`, a non-empty string. For `camera_actions`, either scripted `list[list[string]]` or state-mode payload. For `composite_input`, a map containing `input_types` plus each named input. | +| `event_id` | integer | No | Client sequence id. The server echoes it in chunk/frame metadata after the event is sampled. | + +`camera_actions` supports two payload modes: + +| Mode | Payload shape | Meaning | +| --- | --- | --- | +| Script | `list[list[string]]` | A fixed sequence of per-frame actions consumed by upcoming chunks. | +| State | `{ "mode": "state", "transitions": [{"actions": [...], "client_ts_ms": ...}] }` | Live control state transitions from keyboard or UI controls. | + +Supported LingBot action tokens include `w`, `a`, `s`, `d` for camera movement and `i`, `j`, `k`, `l` for look controls. + +Use `composite_input` when multiple runtime inputs should be sampled together, such as updating the prompt and camera controls in one event. + +### Server messages + +| Message | Payload | Meaning | +| --- | --- | --- | +| `frame_batch` | MessagePack map with `payload` bytes | One batch of frames. The map includes `chunk_index`, `num_frames`, `content_type`, `encoding`, `width`, `height`, and frame-batch metadata. | +| `chunk_stats` | MessagePack map | Per-chunk timing and transport metrics, including `scheduler_forward_ms`, `raw_payload_build_ms`, `chunk_total_ms`, `num_frames`, and `ws_payload_bytes`. | +| `error` | MessagePack map | Server-side validation or generation error. | + +### Minimal client sketch + +```python Python +import msgspec.msgpack +import websocket + +ws = websocket.create_connection("ws://127.0.0.1:30000/v1/realtime_video/generate") +ws.send_binary(msgspec.msgpack.encode({ + "type": "init", + "prompt": "A quiet rainy London alley, stable camera motion.", + "first_frame": open("reference.jpg", "rb").read(), + "size": "832x480", + "fps": 25, + "num_frames": 9, + "num_inference_steps": 4, + "guidance_scale": 1, + "realtime_output_format": "webp", + "output_compression": 95, +})) + +ws.send_binary(msgspec.msgpack.encode({ + "type": "event", + "kind": "camera_actions", + "event_id": 1, + "payload": {"mode": "state", "transitions": [{"actions": ["w"], "client_ts_ms": 0}]}, +})) + +ws.send_binary(msgspec.msgpack.encode({ + "type": "event", + "kind": "prompt", + "event_id": 2, + "payload": "A quiet snowy Tokyo alley, stable camera motion.", +})) + +ws.send_binary(msgspec.msgpack.encode({ + "type": "event", + "kind": "composite_input", + "event_id": 3, + "payload": { + "input_types": ["prompt", "camera_actions"], + "prompt": "A quiet neon Shanghai alley, stable forward camera motion.", + "camera_actions": [["w"], ["w"], []], + }, +})) +``` + +## 5. Consistency + +LingBot World 2.0 uses raw-frame websocket GT plus per-chunk latency guards for consistency checks. + +## 6. Notes + +- Use the realtime endpoint for interactive sessions: `/v1/realtime_video/generate`. +- Prefer WebP preview transport for interactive testing; use raw-frame transport for consistency checks. +- Long-running sessions should be validated with raw-frame consistency before changing causal cache, condition sampling, or VAE decode behavior. diff --git a/docs_new/cookbook/diffusion/intro.mdx b/docs_new/cookbook/diffusion/intro.mdx index a09975fad..b96c2e8a8 100644 --- a/docs_new/cookbook/diffusion/intro.mdx +++ b/docs_new/cookbook/diffusion/intro.mdx @@ -99,6 +99,12 @@ Realtime models keep a session alive and generate chunk by chunk with causal sta href="/cookbook/diffusion/LingBot-World/LingBot-World" img="/cards/logos/inclusionai.png" /> +