Turn an image and a prompt into 2K video with sound
Open this ready-to-run workflow on Floyo. No install needed.
HOW IT WORKS
Step 1. Upload your start image. The frame the video begins from. It sets the subject, the scene, and the framing. Works great with: portraits · characters · products · scenes
Step 2. Write your prompt. Describe the motion, the camera, the lighting, and the sound you want, like "a woman walks through a sunlit garden, camera tracks beside her, birds singing." The model builds the audio from the same prompt.
Step 3. Run text-only instead (optional). No image? Mute the image node and the model generates the whole clip from your prompt alone.
Step 4. Hit run and download. The model builds the picture and stereo audio together in one pass and saves a single video file. This is a large model, so give it time. Ready for: editing timelines · social · ads
First time? Leave every setting as-is. The defaults (16:9 · scale 0.4 · 5 seconds) are the right starting point for almost everyone.
Overview
This workflow turns a start image and a prompt into a 2K video with sound using MiniMax H3, also called Hailuo 3.0, an open-weights model from MiniMax. The audio is the point. Most video models give you a silent clip you have to score later. H3 is a 33B multimodal model that builds the picture and native stereo audio in the same pass, so dialogue, effects, and ambient sound are timed to the action and come back embedded in one file. It outputs 2K at 24fps, up to 15 seconds, and you can mute the image to run it text-only from a prompt alone. You upload an image, write a prompt, and get a finished clip with sound in about 2 minutes 32 seconds. No setup, no nodes to wire.
Who it's for: creators and ad teams who want finished video with synced sound in ComfyUI without wiring the pipeline or scoring the clip afterward. Not for: a fast draft or a run past 15 seconds. It is a heavy model, and anything longer than 15 seconds needs a separate extend step.
Why Floyo
Floyo is the only ComfyUI platform built for teams in the browser.
Made for teams. Share run history, files, and models across your whole team. A teammate opens your exact run and picks up where you left off. No file handoffs, no version confusion.
No install, no setup. Every workflow and model is preloaded. Open it in your browser and run. Nothing to download, nothing to configure.
No local hardware. Workflows run on H100 NVL GPUs, so heavy models run fast without a card of your own. Your VRAM stops being the limit.
Open and closed models in one place. Floyo runs open-source workflows and API models side by side.
How to use (in your browser on Floyo)
Upload your start image, or mute the image node to go text-only.
Write a prompt describing the motion, camera, and sound, then run.
Download the 2K clip with embedded stereo audio, ready for any editor.
Expectations The models are preloaded, so there is nothing to download. Running it needs a free Floyo account. This is a large model, so each clip takes about 2 minutes 32 seconds, and raising the scale or the duration makes a run take longer. A few things decide the result. A clear, well-lit start image and a prompt that names the motion, camera, and sound give the cleanest clip. Keep it to one defined scene and 15 seconds or less, since past that needs a separate extend step. On licensing: H3 is open weights under the MiniMax H3 Community License. Commercial use is free for organisations under 20 million dollars in annual revenue, with attribution, and the license excludes the US, EU, UK, and South Korea from running the weights locally. Check the current terms for your region before you rely on it.
Use Cases
Ad & Promo Clips. Generate short branded spots with sound from a single image and a brief, no separate scoring pass.
Bring a Photo to Life. Animate a still into a short clip with matching ambient sound.
Text to Video. Mute the image and build a whole scene, picture and audio, from a prompt alone.
Social & Short-form. Make vertical clips with sound for feeds without a shoot or a mic.
What can MiniMax H3 turn into a video with sound?
