Add CGI To Any Video With Higgsfield

In this guide, you will learn how to add a believable AI VFX element to a short video clip with Higgsfield. You will pick footage the model can preserve, use ChatGPT to tighten the effect prompt before spending video credits, then generate and review the edit in Gemini Omni Flash.

  • Beginner
  • 6 steps
  • By The Rundown University

Step by step 6 steps

  1. Step 1 of 6

    Pick Footage The Model Can Preserve

    Start with the source clip, not the prompt. When you are ready to generate, use the exact Gemini Omni Flash (https://higgsfield.ai/gemini-omni-flash) link because this workflow can be hard to find from the main Higgsfield interface. The best AI VFX results come from footage with enough open space for the model to add something without rewriting the whole scene.

    Use clips with:

    • One readable shot and no cuts.
    • A clear subject or simple empty scene.
    • Enough background room for the VFX element.
    • Foreground and background that are both reasonably visible.
    • Simple camera motion and stable lighting.

    Avoid tight, cluttered shots for the first pass. A tight shot with an out-of-focus fence can make an effect like a background portal harder to solve because the model may not cleanly understand the depth of the scene. A quick prompt like "put me in the jungle" can create the same problem from another angle: vague prompts and cramped source footage invite the model to remake the scene instead of editing it.

    Pro tip: If you have a 10-second clip, trim a 2-second test first. AI video generation is usually billed by duration, so short tests are cheaper while you are still finding the right prompt.

  2. Step 2 of 6

    Improve The Prompt Before Spending Video Credits

    Do not start with a tiny vibe prompt and hope the model guesses correctly. In the demo, the weak first prompt was:

    Giant donut monster running past the guy in the warehouse, acid trip style.

    That prompt produced a fun result, but it also changed too much of the scene. It added rainbow lighting and extra style changes that were not part of a controlled edit.

    Overchanged donut output
    Overchanged donut output

    Before generating, use ChatGPT to expand the idea into a more specific video-edit prompt. The useful instruction is:

    Help me improve this prompt for an AI special effects generator. I want to be more specific about exactly what to add into the scene and what not to change.
    
    Source clip: [describe the shot]
    Effect idea: [describe the effect]
    
    Return a concise prompt that adds one effect and preserves the original subject, camera movement, framing, timing, background, and lighting.

    The stronger spaceship prompt worked because it named the object, the quantity, the position, the motion, and the preservation rules:

    Add one large photorealistic sci-fi craft hovering far in the background outside the parking garage. It should move slowly and feel distant, heavy, and physically present in the scene.
    
    Keep everything else the same: same person, same camera movement, same framing, same timing, same background/environment, and same lighting direction.
    
    Single continuous shot. No scene cuts. No new characters. No face changes. No body warping. No extra explosions or camera moves.

    That specificity is the difference between "make this epic" and "add one thing without breaking the shot."

  3. Step 3 of 6

    Generate The Edit In Higgsfield

    Open Higgsfield Gemini Omni Flash (https://higgsfield.ai/gemini-omni-flash), then click Start generating. In the logged-in workspace, use the video workflow that accepts source media. The visible route may be https://higgsfield.ai/ai/video?model=gemini-omni or it may normalize to https://higgsfield.ai/ai/video.

    You are in the right place when the panel has an upload area for media, a prompt box, and the model set to Gemini Omni Flash.

    Upload the source clip, paste the improved prompt, and generate one pass. Higgsfield may take a few minutes to generate the edit. If live generation stalls, use a prepared output and continue the walkthrough from the review step.

    If Gemini Omni Flash is not available, use Higgsfield AI Video Editor (https://higgsfield.ai/ai-video-editor) or https://higgsfield.ai/ai/video/edit, but only if the editor accepts an uploaded video plus a text prompt. A fallback model such as Kling 3.0 Omni Edit or Kling O1 Video Edit is acceptable. Do not switch to a generic text-to-video or image-to-video flow and pretend it is the same workflow.

  4. Step 4 of 6

    Review The Result Against The Original

    After the generation finishes, compare the AI edit against the original clip. Do not only ask whether it looks cool. Ask whether it still behaves like the same shot.

    Check:

    • Subject integrity: did the person, face, hands, or body change?
    • Camera continuity: did the camera motion, framing, or timing drift?
    • Effect integration: does the object sit in the background instead of floating on top?
    • Lighting match: do the shadows, glow, color temperature, and haze fit the source?
    • Source preservation: did Higgsfield change anything unrelated?

    In the strong spaceship example, the prompt kept the main shot intact because it clearly said the object should be one distant sci-fi craft outside the parking garage and repeated the preservation constraints.

    Spaceship prompt details
    Spaceship prompt details

    In the weaker examples, the model either added too much style, struggled with depth, or stacked a new spaceship in front of the old one. Those failures are useful because they tell you exactly what to fix in the next prompt.

  5. Step 5 of 6

    Make One Targeted Revision

    Use the review pass to fix one issue at a time. Do not rewrite the whole concept unless the first result is unusable.

    Good revision targets:

    • Make the object smaller or farther away.
    • Remove unwanted color effects.
    • Preserve the subject more strictly.
    • Match the lighting better.
    • Reduce edge flicker.
    • Reframe for vertical video.

    Use a revision prompt like:

    Revise the previous edit. Keep the same sci-fi craft idea, but make the craft feel farther away and more physically integrated into the background.
    
    Preserve the original person, camera motion, framing, timing, background, and lighting. Keep everything else the same.

    One useful workaround is to download the generated clip and upload that result back into Gemini Omni Flash as the new source if an edit gets stuck or a direct revision does not behave. Then ask for a narrower correction, such as removing unwanted rainbow light effects while keeping the main character or object.

  6. Step 6 of 6

    Change The Aspect Ratio With Ratio And Crop Adjuster

    A useful tool we found while recording was Higgsfield's Ratio and Crop Adjuster. When you edit a video, it can automatically crop and change the aspect ratio of your video.

    Ratio and Crop Adjuster result
    Ratio and Crop Adjuster result

    Use this as a separate workflow. First get the VFX edit looking right. Then use Ratio and Crop Adjuster to test vertical versions for TikTok, Shorts, or Reels. If you ask for too many creative changes at the same time, it becomes harder to know which instruction caused the failure.

That's the whole workflow

Mark it complete to keep your progress. The background follows.

Keep learning with Rundown Pro

Guides stay free. This is what Rundown Pro adds:

  • Every course and recording
  • The Rundown Certified Operator program
  • Member perks

$29/mo, cancel anytime

Background and context

Who This Is Useful For

  • Creators who want to add sci-fi, monster, portal, or stylized VFX moments to short social clips.
  • Editors who need a fast way to test AI video effects without burning credits on weak prompts.
  • Anyone turning horizontal, real-world footage into more cinematic or vertical-friendly AI edits.

What You Will Build

You will learn how to take a short video shot and add one controlled AI VFX element into it, such as a creature, portal, spaceship, explosion, or stylized background effect.

In the demo, we added a sci-fi spaceship into the background of a plain parking-garage clip:

Higgsfield spaceship output
Higgsfield spaceship output

The reusable part is the workflow:

  • A source-clip checklist for deciding whether a shot is worth editing.
  • A prompt structure that separates the new VFX element from the parts of the video that must stay unchanged.
  • A visual QA pass for checking subject integrity, camera motion, lighting, scale, and unwanted changes.
  • One targeted revision prompt instead of starting over from scratch.

What You Need To Get Started

  • A Higgsfield (https://higgsfield.ai/) account.
  • A short video clip.
  • Optional: ChatGPT or Claude for improving the effect prompt before generating.

Going Further

Once you have one believable output, save the source clip, prompt, generated result, and QA notes together. That gives you a repeatable prompt pattern for future edits:

Add [one specific VFX object or effect] to [specific location in the shot].

Keep everything else the same: same [subject], same [camera motion], same [framing], same [timing], same [background/environment], and same [lighting].

Single continuous shot. No scene cuts. No unrelated changes.

You can also browse Higgsfield's Visual Effects collection (https://higgsfield.ai/collection/effects) for effect ideas, or use Mixed Media (https://higgsfield.ai/mixed-media-intro) when you want a stylized preset look instead of precise object insertion. Treat those as alternate paths, not replacements for the source-video edit workflow.

The main takeaway is simple: pick footage the model can preserve, make the prompt specific before spending video credits, and review the result against the original before trusting it.