Poe API

Wan-2.6

Wan 2.6 is Alibaba’s multimodal video generation model built for cinematic, multi-shot storytelling—creating high-fidelity videos from text and/or images while keeping characters and style consistent across scenes. It also supports native audio-visual sync (including lip-sync) and can generate or align dialogue/music/SFX with the visuals, enabling “prompt-to-video” results that feel production-ready without heavy post work. Notes: - This model is served from the Singapore area. - Upload an image to enable image-to-video generations or video(s) for reference-to-video generations. - Responses may take upwards of 5 minutes (or more) to finish generating. Parameter controls available: 1. Video Settings - Set Resolution: Select from 1080p (Full HD) or 720p (HD). This is set to 1080p (Full HD) by default. - Set Aspect Ratio: Select from (16:9, 4:3, 1:1, 3:4, 9:16). It is set to 16:9 aspect ratio as default. (ignored for image-to-video as it uses the input image's aspect ratio) - Set Duration: Select from (5 seconds, 10 seconds, 15 seconds) to specify video length in seconds. (reference-to-video limited to 10s max) 2. Advanced Settings - Flash Mode: Faster generation at reduced cost. Only applies to Image-to-Video and Reference-to-Video. (Default: disabled) - Prompt Enhancement: AI prompt enhancement. (Default: enabled) - Enable Audio: Enable/disable audio generation. (Default: enabled) - Shot Type: Multi-shot narrative vs single continuous shot. (Default. Multi-shot narrative) - Seed: Set from (0-2147483646) Random seed for reproducibility. - Negative Prompt: Type things to avoid in generated images Attachments - For i2v: Attach an image as the first frame - For r2v: Attach up to 5 images + 1-3 reference videos (1-30 seconds each, 100MB max, MP4/MOV) (Use `character1`, `character2`, `character3` in prompt to reference subjects, ex. character1 references the subject in the first uploaded video) (combined max 5) - For t2v/i2v: Optionally attach an audio file (3-30 seconds, max 15mb, .mp3/.wav) for custom audio - Images are automatically resized to fit limits (I2V: 360–2,000px, R2V: 240–5,000px). HEIC/HEIF images are auto-converted. Videos for R2V are validated (MP4/MOV, 1–30s, ≤100 MB) and auto-trimmed if longer than 30 seconds. Multi-Shot Prompting - For multi-shot mode, use timeline syntax: `[Shot #] [Timestamp] [Action]`. Example: `[Shot 1] [0-5s] Wide shot of city skyline. [Shot 2] [5-10s] Close-up of character walking.` - Ensure timestamps match your selected duration and use transition keywords like "Hard cut" or "Fade in" between shots.

OFFICIAL

Build with Wan-2.6 using the Poe API

Start by creating an API key, for use with any bot on Poe:

Generate API key

Code samples

python

import openai

client = openai.OpenAI(
    api_key = "YOUR_POE_API_KEY",  # or os.getenv("POE_API_KEY")
    base_url = "https://api.poe.com/v1",
)

chat = client.chat.completions.create(
    model = "wan-2.6",
    messages = [{
      "role": "user",
      "content": "FPV drone shot of a tropical beach with bright turquoise waters and lush tropical palm trees. The camera flies over the beach, bright colors, low contrast, fast footage"
    }]
)

print(chat.choices[0].message.content)

See the full documentation for comprehensive guidance on getting started.