Wan2.5: Image to Video

Transform images into videos with synchronized audio, enhanced motion, and superior quality.

Download Workflow Try in Cloud

Input

First frame

Prompt

Duration

Resolution

Advanced settings

Generate audio

Negative prompt

Enhance prompt

Seed

Run

Output

00:00

Example

Call this model from your code

The request below uses the same prepared graph and settings as the Playground. Each submission can start a paid run; do not automatically retry a submission whose outcome is unknown.

Get API key

What you need

Runs on: Comfy Cloud
Key: COMFY_API_KEY
Your files: Uploaded by the code from their urls

Needs a paid Cloud plan and credits.

Download API JSON

# Python 3.10+: pip install comfy-sdk==0.4.0
import os

from comfy_sdk import Comfy

api_key = os.environ.get("COMFY_API_KEY", "").strip()
if not api_key: raise RuntimeError("Set COMFY_API_KEY")
os.environ.setdefault("COMFY_BASE_URL", "https://cloud.comfy.org")
client = Comfy(api_key=api_key)
workflow = client.workflows.from_json({
    "3": {
        "class_type": "LoadAudio",
        "inputs": {
            "audio": "audio_ace_step_1_m2m_editing_input_audio.mp3"
        },
        "_meta": {
            "title": "Load Audio"
        }
    },
    "7": {
        "class_type": "SaveVideo",
        "inputs": {
            "filename_prefix": "video/Wan2.5",
            "format": "auto",
            "format.codec": "auto",
            "video": [
                "10",
                0
            ]
        },
        "_meta": {
            "title": "Save Video"
        }
    },
    "10": {
        "class_type": "WanImageToVideoApi",
        "inputs": {
            "duration": 5,
            "generate_audio": True,
            "image": [
                "11",
                0
            ],
            "model": "wan2.5-i2v-preview",
            "negative_prompt": "",
            "prompt": "At golden hour on the mountain pass, the old crawler tractor coughs to life: a puff of dark exhaust bursts from the vertical pipe, the engine shudders and the tracks start to grind forward over the gravel, kicking up amber dust that drifts through the low sunlight. The surveyor turns from the edge of the cliff, shields their eyes against the glare and walks toward the machine. The camera starts wide and low behind a boulder, then cranes up and orbits slowly to the right, revealing the full depth of the red-rock canyon falling away below as long shadows stretch across the ledge. Sound: diesel engine rumble, crunching gravel, desert wind.",
            "prompt_extend": True,
            "resolution": "720P",
            "seed": 265691414,
            "shot_type": "single",
            "watermark": False
        },
        "_meta": {
            "title": "Wan Image to Video"
        }
    },
    "11": {
        "class_type": "LoadImage",
        "inputs": {
            "image": "UPLOADED_image_FILENAME"
        },
        "_meta": {
            "title": "Load Image"
        }
    }
})
workflow.set_input("11", "image", client.assets.from_url("https://comfy.org/catalog-media/80ff7f17-6305-40c1-abce-bdb84ffeea2b/c180c89f-d666-41b1-a705-ef87fd9e0bf9"))

# run() also passes api_key to the partner nodes in this workflow.
job = client.run(workflow, api_key=api_key)
for output in job.get_outputs("7"):
    output.to_file(output.name)

API documentation

Try an example

About this workflow

The 'Wan2.5: Image to Video' workflow is designed to transform static images into dynamic video content, complete with synchronized audio. This workflow leverages the Wan2.5 and Wan models to enhance motion and ensure superior video quality. The process begins with uploading an image using the LoadImage node, which serves as the foundation for video generation. The optional audio component can be integrated via the LoadAudio or RecordAudio nodes, allowing for a more immersive video experience. The core of the transformation occurs through the WanImageToVideoApi node, which processes the image and audio to produce a cohesive video output.

Finally, the SaveVideo node is used to store the resulting video file. This workflow is particularly useful for creators looking to add motion to still images, whether for social media content, marketing materials, or creative projects.

Wan2.5: Image to Video

Input

Inside the workflow

Call this model from your code

What you need

Try an example

About this workflow

Questions & answers

Input

Inside the workflow

Call this model from your code

What you need

Try an example

About this workflow

Questions & answers

Do I need to use audio for this workflow?

What are the requirements for the audio file?

Can I use this workflow without an internet connection?

How do I enable the RecordAudio node?