> ## Documentation Index
> Fetch the complete documentation index at: https://docs.oxen.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Wan2.2 A14B - Text to Video

> High-fidelity open text-to-video, 720p

<CardGroup cols={1}>
  <Card title="Try Wan2.2 A14B - Text to Video in the Workbench" icon="flask" href="https://www.oxen.ai/ai/workbench?model=wan-ai-wan2-2-t2v-a14b-diffusers">
    Run this model interactively, tune parameters, and compare outputs.
  </Card>
</CardGroup>

**Model ID:** `wan-ai-wan2-2-t2v-a14b-diffusers`

Wan-AI/Wan2.2-T2V-A14B-Diffusers is a video generation model (diffusion-based) with a Mixture-of-Experts architecture, designed for high-quality text-to-video and image-to-video synthesis at 720P resolution and 24fps. It excels in generating high-definition videos with efficient resource usage, enabling professional-level output while maintaining practical hardware requirements (e.g., consumer-grade GPUs or single 80GB VRAM GPU).

Some other noteworthy features of Wan-AI/Wan2.2-T2V-A14B-Diffusers include support for both academic research and industrial applications, and the ability to handle both text-to-video and image-to-video tasks within a unified framework.

| Metric                 | Value                                   |
| ---------------------- | --------------------------------------- |
| Parameter Count        | 27 billion (14 billion active per step) |
| Mixture of Experts     | Yes                                     |
| Active Parameter Count | 14 billion                              |
| Context Length         | Unknown                                 |
| Multilingual           | Unknown                                 |
| Quantized\*            | No                                      |

\**Quantization is specific to the inference provider and the model may be offered with different quantization levels by other providers.*

## Example request

<Tip>
  Use the [Workbench](https://www.oxen.ai/ai/workbench?model=wan-ai-wan2-2-t2v-a14b-diffusers) as a request builder: configure parameters for this model in the UI, then open the **API** tab to copy the exact cURL or Python call.
</Tip>

<Tabs>
  <Tab title="Sync">
    This blocks until the video is ready (typically 5-15 minutes). Prefer **Async** or **Async with SSE** for anything beyond quick experimentation.

    See the [video generation reference](/inference-api/reference/video_generation) for more details.

    <Tabs>
      <Tab title="Minimal">
        <CodeGroup>
          ```bash cURL theme={null}
          curl -X POST https://hub.oxen.ai/api/ai/videos/generate \
            -H "Content-Type: application/json" \
            -H "Authorization: Bearer $OXEN_API_KEY" \
            -d '{
            "model": "wan-ai-wan2-2-t2v-a14b-diffusers",
            "prompt": "A beautiful landscape painting of a serene lake with mountains in the background and an ox in the foreground."
          }'
          ```

          ```python Python theme={null}
          import os
          import requests

          response = requests.post(
              "https://hub.oxen.ai/api/ai/videos/generate",
              headers={
                  "Content-Type": "application/json",
                  "Authorization": f"Bearer {os.environ['OXEN_API_KEY']}",
              },
              json={
                  "model": "wan-ai-wan2-2-t2v-a14b-diffusers",
                  "prompt": "A beautiful landscape painting of a serene lake with mountains in the background and an ox in the foreground."
              },
          )
          response.raise_for_status()
          print(response.json())
          ```
        </CodeGroup>
      </Tab>

      <Tab title="All parameters">
        <CodeGroup>
          ```bash cURL theme={null}
          curl -X POST https://hub.oxen.ai/api/ai/videos/generate \
            -H "Content-Type: application/json" \
            -H "Authorization: Bearer $OXEN_API_KEY" \
            -d '{
            "model": "wan-ai-wan2-2-t2v-a14b-diffusers",
            "prompt": "A beautiful landscape painting of a serene lake with mountains in the background and an ox in the foreground.",
            "height": 480,
            "width": 832,
            "negative_prompt": " ",
            "num_inference_steps": 4,
            "num_frames": 41,
            "guidance_scale": 5.0,
            "run_fast": true
          }'
          ```

          ```python Python theme={null}
          import os
          import requests

          response = requests.post(
              "https://hub.oxen.ai/api/ai/videos/generate",
              headers={
                  "Content-Type": "application/json",
                  "Authorization": f"Bearer {os.environ['OXEN_API_KEY']}",
              },
              json={
                  "model": "wan-ai-wan2-2-t2v-a14b-diffusers",
                  "prompt": "A beautiful landscape painting of a serene lake with mountains in the background and an ox in the foreground.",
                  "height": 480,
                  "width": 832,
                  "negative_prompt": " ",
                  "num_inference_steps": 4,
                  "num_frames": 41,
                  "guidance_scale": 5.0,
                  "run_fast": true
              },
          )
          response.raise_for_status()
          print(response.json())
          ```
        </CodeGroup>
      </Tab>
    </Tabs>
  </Tab>

  <Tab title="Async">
    See the [async queue reference](/inference-api/reference/async_queue) for more details.

    <Tabs>
      <Tab title="Minimal">
        <CodeGroup>
          ```bash cURL theme={null}
          # Enqueue, capture the generation id.
          GEN_ID=$(curl -s -X POST https://hub.oxen.ai/api/ai/queue \
            -H "Content-Type: application/json" \
            -H "Authorization: Bearer $OXEN_API_KEY" \
            -d '{
            "model": "wan-ai-wan2-2-t2v-a14b-diffusers",
            "prompt": "A beautiful landscape painting of a serene lake with mountains in the background and an ox in the foreground."
          }' | jq -r '.generations[0].generation_id')

          # Poll until the generation reaches a terminal status.
          while true; do
            STATUS=$(curl -s -H "Authorization: Bearer $OXEN_API_KEY" \
              "https://hub.oxen.ai/api/ai/queue/$GEN_ID" | jq -r '.status')
            echo "Status: $STATUS"
            case $STATUS in succeeded|failed|cancelled) break;; esac
            sleep 5
          done

          # Print the result.
          curl -s -H "Authorization: Bearer $OXEN_API_KEY" \
            "https://hub.oxen.ai/api/ai/queue/$GEN_ID" | jq .
          ```

          ```python Python theme={null}
          import os
          import time
          import requests

          HEADERS = {
              "Content-Type": "application/json",
              "Authorization": f"Bearer {os.environ['OXEN_API_KEY']}",
          }

          enqueue = requests.post(
              "https://hub.oxen.ai/api/ai/queue",
              headers=HEADERS,
              json={
                  "model": "wan-ai-wan2-2-t2v-a14b-diffusers",
                  "prompt": "A beautiful landscape painting of a serene lake with mountains in the background and an ox in the foreground."
              },
          )
          enqueue.raise_for_status()
          generation_id = enqueue.json()["generations"][0]["generation_id"]

          while True:
              data = requests.get(
                  f"https://hub.oxen.ai/api/ai/queue/{generation_id}",
                  headers=HEADERS,
              ).json()
              if data["status"] in {"succeeded", "failed", "cancelled"}:
                  break
              time.sleep(5)

          if data["status"] == "succeeded":
              print(f"Result: {data['result_url']}")
          else:
              print(f"Generation {data['status']}: {data.get('error_message')}")
          ```
        </CodeGroup>
      </Tab>

      <Tab title="All parameters">
        <CodeGroup>
          ```bash cURL theme={null}
          # Enqueue, capture the generation id.
          GEN_ID=$(curl -s -X POST https://hub.oxen.ai/api/ai/queue \
            -H "Content-Type: application/json" \
            -H "Authorization: Bearer $OXEN_API_KEY" \
            -d '{
            "model": "wan-ai-wan2-2-t2v-a14b-diffusers",
            "prompt": "A beautiful landscape painting of a serene lake with mountains in the background and an ox in the foreground.",
            "height": 480,
            "width": 832,
            "negative_prompt": " ",
            "num_inference_steps": 4,
            "num_frames": 41,
            "guidance_scale": 5.0,
            "run_fast": true
          }' | jq -r '.generations[0].generation_id')

          # Poll until the generation reaches a terminal status.
          while true; do
            STATUS=$(curl -s -H "Authorization: Bearer $OXEN_API_KEY" \
              "https://hub.oxen.ai/api/ai/queue/$GEN_ID" | jq -r '.status')
            echo "Status: $STATUS"
            case $STATUS in succeeded|failed|cancelled) break;; esac
            sleep 5
          done

          # Print the result.
          curl -s -H "Authorization: Bearer $OXEN_API_KEY" \
            "https://hub.oxen.ai/api/ai/queue/$GEN_ID" | jq .
          ```

          ```python Python theme={null}
          import os
          import time
          import requests

          HEADERS = {
              "Content-Type": "application/json",
              "Authorization": f"Bearer {os.environ['OXEN_API_KEY']}",
          }

          enqueue = requests.post(
              "https://hub.oxen.ai/api/ai/queue",
              headers=HEADERS,
              json={
                  "model": "wan-ai-wan2-2-t2v-a14b-diffusers",
                  "prompt": "A beautiful landscape painting of a serene lake with mountains in the background and an ox in the foreground.",
                  "height": 480,
                  "width": 832,
                  "negative_prompt": " ",
                  "num_inference_steps": 4,
                  "num_frames": 41,
                  "guidance_scale": 5.0,
                  "run_fast": true
              },
          )
          enqueue.raise_for_status()
          generation_id = enqueue.json()["generations"][0]["generation_id"]

          while True:
              data = requests.get(
                  f"https://hub.oxen.ai/api/ai/queue/{generation_id}",
                  headers=HEADERS,
              ).json()
              if data["status"] in {"succeeded", "failed", "cancelled"}:
                  break
              time.sleep(5)

          if data["status"] == "succeeded":
              print(f"Result: {data['result_url']}")
          else:
              print(f"Generation {data['status']}: {data.get('error_message')}")
          ```
        </CodeGroup>
      </Tab>
    </Tabs>
  </Tab>

  <Tab title="Async with SSE">
    See the [async queue reference](/inference-api/reference/async_queue) for more details.

    <Tabs>
      <Tab title="Minimal">
        <CodeGroup>
          ```bash cURL theme={null}
          # Enqueue, capture the generation id.
          GEN_ID=$(curl -s -X POST https://hub.oxen.ai/api/ai/queue \
            -H "Content-Type: application/json" \
            -H "Authorization: Bearer $OXEN_API_KEY" \
            -d '{
            "model": "wan-ai-wan2-2-t2v-a14b-diffusers",
            "prompt": "A beautiful landscape painting of a serene lake with mountains in the background and an ox in the foreground."
          }' | jq -r '.generations[0].generation_id')

          # Stream the SSE channel, grab the data line that follows a
          # media_generation_completed event for our id, and pretty-print it.
          curl -sN -H "Authorization: Bearer $OXEN_API_KEY" https://hub.oxen.ai/api/events \
            | awk -v id="$GEN_ID" '
              /^event: media_generation_completed$/ { expect=1; next }
              /^data: / && expect {
                payload = substr($0, 7)
                if (index(payload, "\"generation_id\":\"" id "\"")) { print payload; exit }
                expect = 0
              }
            ' | jq .
          ```

          ```python Python theme={null}
          import json
          import os
          import requests

          API_KEY = os.environ["OXEN_API_KEY"]
          AUTH = {"Authorization": f"Bearer {API_KEY}"}

          enqueue = requests.post(
              "https://hub.oxen.ai/api/ai/queue",
              headers={**AUTH, "Content-Type": "application/json"},
              json={
                  "model": "wan-ai-wan2-2-t2v-a14b-diffusers",
                  "prompt": "A beautiful landscape painting of a serene lake with mountains in the background and an ox in the foreground."
              },
          )
          enqueue.raise_for_status()
          generation_id = enqueue.json()["generations"][0]["generation_id"]

          with requests.get(
              "https://hub.oxen.ai/api/events",
              headers=AUTH,
              stream=True,
          ) as stream:
              event_name = None
              for line in stream.iter_lines(decode_unicode=True):
                  if line.startswith("event: "):
                      event_name = line.removeprefix("event: ")
                  elif line.startswith("data: ") and event_name == "media_generation_completed":
                      payload = json.loads(line.removeprefix("data: "))
                      if payload.get("generation_id") == generation_id:
                          print(payload)
                          break
          ```
        </CodeGroup>
      </Tab>

      <Tab title="All parameters">
        <CodeGroup>
          ```bash cURL theme={null}
          # Enqueue, capture the generation id.
          GEN_ID=$(curl -s -X POST https://hub.oxen.ai/api/ai/queue \
            -H "Content-Type: application/json" \
            -H "Authorization: Bearer $OXEN_API_KEY" \
            -d '{
            "model": "wan-ai-wan2-2-t2v-a14b-diffusers",
            "prompt": "A beautiful landscape painting of a serene lake with mountains in the background and an ox in the foreground.",
            "height": 480,
            "width": 832,
            "negative_prompt": " ",
            "num_inference_steps": 4,
            "num_frames": 41,
            "guidance_scale": 5.0,
            "run_fast": true
          }' | jq -r '.generations[0].generation_id')

          # Stream the SSE channel, grab the data line that follows a
          # media_generation_completed event for our id, and pretty-print it.
          curl -sN -H "Authorization: Bearer $OXEN_API_KEY" https://hub.oxen.ai/api/events \
            | awk -v id="$GEN_ID" '
              /^event: media_generation_completed$/ { expect=1; next }
              /^data: / && expect {
                payload = substr($0, 7)
                if (index(payload, "\"generation_id\":\"" id "\"")) { print payload; exit }
                expect = 0
              }
            ' | jq .
          ```

          ```python Python theme={null}
          import json
          import os
          import requests

          API_KEY = os.environ["OXEN_API_KEY"]
          AUTH = {"Authorization": f"Bearer {API_KEY}"}

          enqueue = requests.post(
              "https://hub.oxen.ai/api/ai/queue",
              headers={**AUTH, "Content-Type": "application/json"},
              json={
                  "model": "wan-ai-wan2-2-t2v-a14b-diffusers",
                  "prompt": "A beautiful landscape painting of a serene lake with mountains in the background and an ox in the foreground.",
                  "height": 480,
                  "width": 832,
                  "negative_prompt": " ",
                  "num_inference_steps": 4,
                  "num_frames": 41,
                  "guidance_scale": 5.0,
                  "run_fast": true
              },
          )
          enqueue.raise_for_status()
          generation_id = enqueue.json()["generations"][0]["generation_id"]

          with requests.get(
              "https://hub.oxen.ai/api/events",
              headers=AUTH,
              stream=True,
          ) as stream:
              event_name = None
              for line in stream.iter_lines(decode_unicode=True):
                  if line.startswith("event: "):
                      event_name = line.removeprefix("event: ")
                  elif line.startswith("data: ") and event_name == "media_generation_completed":
                      payload = json.loads(line.removeprefix("data: "))
                      if payload.get("generation_id") == generation_id:
                          print(payload)
                          break
          ```
        </CodeGroup>
      </Tab>
    </Tabs>
  </Tab>
</Tabs>

## Fetch model details

The [models endpoint](/inference-api/reference/models/overview) returns the full model object, including its `json_request_schema`.

```bash theme={null}
curl -H "Authorization: Bearer $OXEN_API_KEY" https://hub.oxen.ai/api/ai/models/wan-ai-wan2-2-t2v-a14b-diffusers
```

## Request parameters

### Required parameters

| Field    | Type     | Default                                                                                                           | Description                |
| -------- | -------- | ----------------------------------------------------------------------------------------------------------------- | -------------------------- |
| `prompt` | `string` | `"A beautiful landscape painting of a serene lake with mountains in the background and an ox in the foreground."` | Prompt for generated image |

### Optional parameters

| Field                 | Type      | Default | Description                                                                                       |
| --------------------- | --------- | ------- | ------------------------------------------------------------------------------------------------- |
| `height`              | `integer` | `480`   | Height of the video Range: 1 – 720.                                                               |
| `width`               | `integer` | `832`   | Width of the video Range: 1 – 832.                                                                |
| `negative_prompt`     | `string`  | `" "`   | Negative prompt for generated image                                                               |
| `num_inference_steps` | `integer` | `4`     | Number of diffusion steps to take Range: 1 – 100.                                                 |
| `num_frames`          | `integer` | `41`    | Number of frames of video to generate (`num_frames - 1` should be divisible by 4) Range: 1 – 120. |
| `guidance_scale`      | `number`  | `5.0`   | Guidance for generated video. Lower values can give more realistic videos. Range: 0 – 10.         |
| `seed`                | `integer` | —       | Random seed. Set for reproducible generation                                                      |
| `run_fast`            | `boolean` | `true`  | Run the model with a lightning LoRA                                                               |