Image to Video | Fast Image-to-Video API

Midjourney — Image-to-Video Model

Midjourney Image-to-Video transforms static artworks or illustrations into cinematic video clips with motion, lighting, and depth — while maintaining Midjourney’s signature artistic fidelity. This model captures subtle camera movement, breathing effects, and dynamic perspective shifts, bringing your images vividly to life.

✨ Why It Looks Great

Midjourney-grade aesthetic — built on the same visual backbone as the legendary Midjourney image engine.
Artistic motion synthesis — intelligently infers camera movement, light flicker, and environmental animation.
High visual consistency — preserves texture, detail, and lighting from the input image.
Multi-resolution support — generate videos at 480p or 720p resolution.
Tunable creativity — control motion randomness and artistic deformation with parameters like chaos, stylize, and weird.

⚙️ Limits and Performance

Input: one reference image (JPEG / PNG / WebP).
Output duration: fixed short cinematic clip (~5 seconds).
Resolutions:
480p for faster, lower-cost generation.
720p for enhanced clarity and professional output.
Supported aspect ratios: 1:1, 16:9, 4:3, 3:4, 2:3, 9:16, etc.
Estimated processing time: 30–60 seconds per video (depending on prompt complexity).

💰 Pricing

Resolution	Example Price
480p	$0.15
720p	$0.48

🧠 Parameters Overview

Parameter	Description
resolution	Choose `480p` or `720p`.
aspect_ratio	Controls video composition (e.g., 16:9 for widescreen).
quality	Higher values produce more refined visuals but increase render time.
stylize	Adjusts how strongly Midjourney’s artistic style influences the animation.
chaos	Adds controlled randomness to camera and scene motion.
weird	Introduces surreal, experimental effects for creative exploration.
version	Model version selector (`7` is current).
niji	Toggles anime-style adaptation (`close` for realistic style).
seed	Fix this for reproducible motion results.

🚀 How to Use

Upload your image as the base frame.
Write a prompt describing the desired motion, lighting, and tone. Example: “Slow cinematic zoom on a magical fox reading under warm lamp light.”
Choose resolution (480p or 720p).
Adjust parameters:

stylize for artistry
chaos and weird for creativity
quality for detail

Click Run to generate your video.
Download and preview the animated result.

🧠 Understanding -- stylize

The stylize parameter defines how strongly Midjourney’s internal aesthetic “rules” guide your output.

Low values (≈50–150) → lower visual coherence, rougher details, but higher prompt control. Ideal for original or hybrid concepts (“catragon,” “centaur,” etc.).
High values (≈250–750) → smoother, more realistic images, but weaker prompt adherence. MJ leans toward dataset beauty rather than creative deviation.
Pro tip: for both coherence and control, use strong visual prompts and mention your style at both the beginning and end, e.g.:

“Salvador Dali painting of surreal architecture, by Salvador Dali —stylize 250”

Midjourney has confirmed: the higher the --stylize value, the closer results align with the average user’s preferred visual aesthetic.

💡 Quick Presets

Goal	Suggested Settings
Precise control / faithful to prompt	`stylize=100, chaos=0, weird=0`
Visually beautiful / cohesive	`stylize=300, chaos=0, weird=0`
Creative exploration	`stylize=150, chaos=20–40, weird=100–400`

🧩 Tips for Best Results

Keep prompts visual and descriptive (use lighting, materials, mood, and camera terms).
Lower stylize to make Midjourney listen more closely to your wording.
Raise stylize for a more polished or realistic look.
Avoid high chaos or weird unless experimenting with concept art.
Reuse the same seed to refine results iteratively.

🧩 Notes

Motion style depends heavily on prompt clarity and the original image composition.
Extreme weird values can produce abstract deformation effects — experiment for creativity.
For consistent results, fix the seed parameter across multiple runs.

Image To Video API — Quick start

Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/midjourney/image-to-video with your input as JSON. The endpoint returns a prediction id; poll the prediction endpoint until status flips to completed, then read the output URL from data.outputs[0]. Examples for Image To Video below.

HTTP example

# Submit the prediction
curl -X POST "https://api.wavespeed.ai/api/v3/midjourney/image-to-video" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $WAVESPEED_API_KEY" \
  -d '{
    "prompt": "A cinematic shot of a city at sunset, soft golden light",
    "image": "https://example.com/your-input.jpg",
    "resolution": "480p",
    "aspect_ratio": "1:1",
    "motion": "low",
    "quality": 1,
    "stylize": 0,
    "chaos": 0,
    "weird": 0,
    "seed": -1,
    "enable_base64_output": false
}'

# Response includes a prediction id. Poll for the result:
curl -X GET "https://api.wavespeed.ai/api/v3/predictions/{request_id}/result" \
  -H "Authorization: Bearer $WAVESPEED_API_KEY"

# When status is "completed", read the output from data.outputs[0].

Node.js example

// npm install wavespeed
const WaveSpeed = require('wavespeed');

const client = new WaveSpeed(); // reads WAVESPEED_API_KEY from env

const result = await client.run("midjourney/image-to-video", {
        "prompt": "A cinematic shot of a city at sunset, soft golden light",
        "image": "https://example.com/your-input.jpg",
        "resolution": "480p",
        "aspect_ratio": "1:1",
        "motion": "low",
        "quality": 1,
        "stylize": 0,
        "chaos": 0,
        "weird": 0,
        "seed": -1,
        "enable_base64_output": false
});

console.log(result.outputs[0]); // → URL of the generated output

Python example

# pip install wavespeed
import wavespeed

output = wavespeed.run(
    "midjourney/image-to-video",
    {
    "prompt": "A cinematic shot of a city at sunset, soft golden light",
    "image": "https://example.com/your-input.jpg",
    "resolution": "480p",
    "aspect_ratio": "1:1",
    "motion": "low",
    "quality": 1,
    "stylize": 0,
    "chaos": 0,
    "weird": 0,
    "seed": -1,
    "enable_base64_output": false
}
)

print(output["outputs"][0])  # → URL of the generated output

Image To Video API — Frequently asked questions

What is the Image To Video API?

Image To Video is a Midjourney model for video generation from images, exposed as a REST API on WaveSpeedAI. Midjourney Image-to-Video turns a single image into an artistically rich, high-quality video using Midjourney's creative AI. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing. You can call it programmatically or try it from the playground above.

How do I call the Image To Video API?

POST your input parameters to the model's REST endpoint (shown in the API tab of this playground) with your WaveSpeedAI API key in the Authorization header. Submission returns a prediction ID; poll the prediction endpoint until status flips to "completed", then read the output URL from the result. The playground generates a ready-to-paste code sample in Python, JavaScript, or cURL for whatever inputs you've set. Full request/response shape is documented at https://wavespeed.ai/docs/docs-api/midjourney/midjourney-image-to-video.

How much does Image To Video cost per run?

Image To Video starts at $0.025 per run. That figure is the base price — the final charge scales with the parameters you set in the form (output size, length, count, references, or whatever knobs this model exposes), so a higher-quality or larger output costs more than a minimal one. The exact cost for your current input is shown live next to the Generate button before you submit, and the actual per-call charge is recorded on the prediction afterwards.

What inputs does Image To Video accept?

Key inputs: `prompt`, `image`, `aspect_ratio`, `resolution`, `seed`, `chaos`. The full JSON schema (types, defaults, allowed values) is rendered above the Generate button and mirrored in the API reference at https://wavespeed.ai/docs/docs-api/midjourney/midjourney-image-to-video.

How long does Image To Video take to generate?

Average end-to-end generation time on WaveSpeedAI is around 85 seconds per request — measured across recent runs. Queue time scales with global demand; live status is visible in the prediction record.

Can I use Image To Video outputs commercially?

Commercial usage rights depend on the model's license, set by its provider (Midjourney). The license summary appears on the model card above; see WaveSpeedAI's Terms of Service for platform-level conditions.

EsempiVedi tutto

Modelli correlati

README