Bailian CLI command reference for full-modal models: text chat, image, video, speech, and vision understanding.
A single command invokes Bailian's full-modal models from the terminal: text chat and Omni, image generation and editing, video generation and editing, speech synthesis and recognition, and vision understanding.
Chat and Omni
| Capability | Command | Typical model | Notes | Common options |
|---|---|---|---|---|
| Text generation | bl text chat | qwen3.8-max (default) | Flagship model for the agent era; strong at coding, office, and long-horizon autonomy | --model model, --system system prompt, --temperature, --max-tokens, --stream streaming, --output json formatted output |
| Omni | bl omni | qwen3.5-omni-plus | Text / image / audio / video understanding and interaction | --image / --audio input, --voice output voice, --audio-format, --audio-out save audio, --text-only, --list-voices |
Image generation and editing
| Capability | Command | Typical model | Notes | Common options |
|---|---|---|---|---|
| Image generation | bl image generate | qwen-image-2.0 | Pro text rendering, photorealism, strong semantic adherence | --prompt, --model, --size, --async async task |
| Image editing | bl image edit | qwen-image-2.0 | Supports multi-image composition | --image repeat to merge multiple images, --prompt edit instruction |
Video generation and editing
| Capability | Command | Typical model | Notes | Common options |
|---|---|---|---|---|
| Video generation | bl video generate | wan3.0-video (default) | Text-to-video and image-to-video, faithful dynamic motion | --prompt, --image first frame (image-to-video), --download <path> save output, --async async task |
| Reference-to-video | bl video ref | wan3.0-video (default) | Up to 9 reference images; stable subject and scene | --image reference (repeatable), --image-voice subject voice, --prompt |
| Video editing | bl video edit | happyhorse-1.0-video-edit (default) | Natural-language video editing | --video input, --prompt edit instruction, --download <path> save output |
| Video download | bl video download | — | Download a completed video task | --task-id (required), --out <path> (required) |
| Video task query | bl video task get | — | Query async video task status | --task-id |
Speech synthesis and recognition
| Capability | Command | Typical model | Notes | Common options |
|---|---|---|---|---|
| Speech synthesis | bl speech synthesize | cosyvoice-v3-flash | Multi-voice streaming TTS; clone from 5–20s samples | --list-voices, --voice, --instruction natural-language style control, --enable-ssml, --stream, --concurrent, --seed reproducible synthesis |
| Speech recognition | bl speech recognize | fun-asr | 30 languages, including Chinese dialects and accents | --diarization speaker separation, --speaker-count, --vocabulary-id hotword list, --language, --async, --out save result, batch up to 100 files |
Vision understanding
| Capability | Command | Typical model | Notes | Common options |
|---|---|---|---|---|
| Vision understanding | bl vision describe | qwen3-vl-plus (default) | Long-form video analysis, chart/document parsing, multilingual OCR | --image / --video input (local path or URL), multi-image input, --prompt, --output json |