On midjourney.com (recommended)

1. Open any image in the gallery, every MJ image has Animate Image buttons below it.
2. Pick one of:
   • Animate Auto. generates immediately using the source image's prompt
   • Animate Manually. opens the Imagine bar so you can adjust the prompt
   • Loop. generates a looping video (start frame = end frame)
3. The job runs in the background; the result appears in the Create page.

For user-uploaded images: click the image icon in the Imagine bar, drag the uploaded image into the Starting Frame slot. A text prompt is optional.

In Discord

<image_URL> <prompt_text> --video

The image URL goes first, then the text prompt, then --video. The image must be online, host on Discord first if the user has a local file.

If the user already has a Midjourney image upscaled in Discord, they can use the Animate (High motion) / Animate (Low motion) buttons directly under it.

The video-specific parameters

Video generations ignore most regular image parameters. Only these work:

That's it. Trying to put --ar, --stylize, --sref, --oref on a video prompt does nothing. The aspect ratio is inherited from the starting image. The style is inherited from the starting image.

GPU costs, read this before generating

MJ video is significantly more expensive than images. Memorize this table:

Key implication: HD video is 3.25× more expensive than SD. The agent should default-recommend SD for exploration and only switch to HD when the user has picked the final shot.

Per-clip USD cost on Standard plan ($0.0333 per GPU-min):

• SD batch-of-4: $0.27 (4 clips for that)
• SD single clip (--bs 1): $0.07
• HD batch-of-4: $0.87
• HD single clip (--bs 1): $0.23

If the user is on Basic plan ($0.05 per GPU-min), all numbers go up 50%.

Plan gating, also memorize

• Basic plan: SD only, Fast mode only. No Relax video.
• Standard plan: SD + HD in Fast mode. No video Relax.
• Pro / Mega plans: SD + HD in Fast. Unlimited Relax SD video (queue-waited, but free from the budget).

Recommend Relax SD on Pro+ for experimentation. Switch to Fast HD for final.

Extending videos

A single video starts at 5 seconds. You can extend it up to 4 more times, gaining 4 seconds per extension, max 21 seconds total.

Each extension costs the same as the initial video. A 21-second HD clip = 5 video jobs × 26 GPU-min = 130 GPU-min ≈ $4.33 on Standard. Tell the user before they start chaining.

Two extension modes (web UI buttons or Discord buttons):

• Extend Auto. uses the original prompt
• Extend Manual. lets you edit the prompt mid-sequence (great for changing what's happening in the clip without losing visual continuity)

Looping and end frames

--loop reuses the start frame as the end frame. Use this for: subtle scene loops, ambient backgrounds, parallax-style breathing motion. The result genuinely loops cleanly.

--end <URL> uses a different image as the end frame. MJ interpolates between the two. Use this for:

• Morph effects (start frame: object 1, end frame: object 2)
• Transition stings between two scenes
• Reveal animations (start: empty room, end: same room with character)

Either flag goes at the end of the prompt with the other video params.

Motion settings, when to pick which

--motion low (default):

• Subjects mostly still, subtle camera drift
• Best for portraits, product shots, atmospheric scenes
• Lower risk of glitchy artifacts
• Pick this for first attempt every time

--motion high:

• Big camera moves (pans, zooms), large body motion
• Best for action scenes, dramatic reveals
• Higher risk of warping or temporal artifacts
• Pick this when low motion produces something too static

If both look bad, the starting image is probably the problem. Re-generate the still first.

Aspect ratio is inherited

The video inherits the starting image's aspect ratio. The exact pixel dimensions:

For social-platform deliverables, generate the starting image at the target AR first:

• TikTok / Reels / Shorts: --ar 9:16 on the still → video stays vertical
• YouTube / web: --ar 16:9
• Square Instagram: --ar 1:1

What to deliver to the user

For an MJ video request, the agent should return:

1. Setup confirmation. which starting image they're animating, on which platform
2. The pasteable command (Discord) or the click sequence (web)
3. Motion + batch recommendation. usually --motion low --bs 1 for first attempt
4. Estimated GPU cost in min + USD on the user's plan
5. Downstream options. extend / loop / re-render with different motion

Example output:

**Animating your fisherman image** (1280×720, HD on Standard plan)

**Discord:**

```
https://your-image-url.jpg moody push-in, gentle fog rolling, fisherman keeps mending nets --motion low --bs 1 --video
```

**Or on midjourney.com:** open the image, click **Animate Manually**, paste the prompt above (without the leading image URL or `--video`).

**Cost estimate:**
- HD, batch-of-1: ~7 GPU-min ≈ $0.23 on Standard
- HD, batch-of-4: ~26 GPU-min ≈ $0.87 (recommended for first pick)
- SD equivalent batch-of-1: 2 GPU-min ≈ $0.07 (recommended for cheap exploration)

**Likely follow-ups:**
- Extend by 4 s if you like the first 5 s (~7 more GPU-min)
- Add `--loop` to make it loop seamlessly
- Switch `--motion low` → `--motion high` if it's too static

Downloading + sharing

Right-click any video on the Create or Organize page to get three download options:

• Download for Social. optimized encoder, less compression on platforms like Instagram/TikTok. Use this for posting.
• Download Raw Video. the original, best quality. Use this for editing in Premiere/DaVinci.
• Download Gif. animated GIF. Use this only for messaging contexts.

In Discord, right-click only downloads the raw file.

Frequent failures and how to recover

• "My video looks frozen". --motion low is too low; try --motion high. If that's also static, the source image has no implied motion direction; pick a more dynamic still.
• "The character morphs into a different person". --motion high over-warps; drop to low. Or the source image had ambiguous anatomy (hands, faces in profile).
• "It generates SD even though I'm on Standard". the user didn't set Video Resolution in More Options → Settings panel. SD is the global default.
• "My batch of 4 has 1 great clip and 3 bad ones". that's expected. Use --bs 1 next time for the same prompt to spend less burning bad variants, or rerun the great one with --motion high for a variant.