MiniMax H3 Max Turbo: Image to Video

Generate video sequences from a starting image using MiniMax H3 Max Turbo, producing two video outputs from a single input frame. This rapid image-to-video workflow generates short clips in seconds, with optional prompt enhancement and 2K upscaling stages. Ideal for animating still photographs, creating quick motion previews for storyboards, and fast visual effects iteration.

Download Workflow Try in Cloud

About

This MiniMax H3 Max Turbo image-to-video workflow turns a single still image into motion in seconds and saves two distinct clips per run. The core video generation happens in parallel through two MiniMax nodes: MinimaxHailuo03FirstLastFrameNode and MinimaxHailuo03ContextIRNode. Both consume the same start image from LoadImage and the same text prompt, then SaveVideo writes each result to disk. A ComfySwitchNode sits between your prompt and the generators, routing either your original text from PrimitiveStringMultiline or an auto-improved version from MinimaxHailuo03RegenerateNode when the Prompt Enhancer is enabled.

For traceability, SaveText captures prompt metadata so you can reproduce strong results later.

Two optional stages are exposed via the Feature Flags group (PrimitiveBoolean). First, you can enable the Prompt Enhancer to have MinimaxHailuo03RegenerateNode refine your instruction before it is passed to both video generators. Second, you can enable 2K upscaling for higher-resolution deliverables. Important: the upscale stage only accepts 768p source video, so set the MiniMax generation resolution to 768p when you plan to upscale. The template also includes MarkdownNote guidance on-canvas and sensible defaults to get you from a single frame to dual video outputs fast, making it ideal for animating stills, storyboards, and quick VFX look-dev.

What you provide

Reading the workflow

Runs in ComfyUI. This workflow can't run on this page. Open it in Comfy Cloud with everything loaded, or download it for your own ComfyUI.

Try in Cloud

Output

Example

Sample output

Use this workflow from code

Generated from the workflow graph and inputs when possible; stored examples are shown otherwise. Review credentials and endpoints before running code, which may incur charges.

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({
    "2": {
        "class_type": "SaveVideo",
        "inputs": {
            "codec": "auto",
            "filename_prefix": "video/video/MiniMax_H3_Max_turbo_i2v_768P",
            "format": "auto",
            "format.codec": "auto",
            "video": [
                "24",
                0
            ]
        },
        "_meta": {
            "title": "Save Video"
        }
    },
    "7": {
        "class_type": "MinimaxHailuo03ContextIRNode",
        "inputs": {
            "first_frame": [
                "25",
                0
            ],
            "model": "MiniMax H3",
            "model.duration": 5,
            "model.prompt": [
                "14",
                0
            ],
            "model.ratio": "adaptive"
        },
        "_meta": {
            "title": "MiniMax H3 Context IR (Prompt Enhancer)"
        }
    },
    "8": {
        "class_type": "SaveText",
        "inputs": {
            "filename_prefix": "H3_prompt",
            "format": "txt",
            "text": [
                "12",
                0
            ]
        },
        "_meta": {
            "title": "Save Text"
        }
    },
    "10": {
        "class_type": "MinimaxHailuo03RegenerateNode",
        "inputs": {
            "first_frame": [
                "25",
                0
            ],
            "model": "MiniMax H3",
            "model.prompt": [
                "8",
                0
            ],
            "model.resolution": "2K",
            "video": [
                "2",
                0
            ],
            "watermark": False
        },
        "_meta": {
            "title": "MiniMax H3 Regenerate to 2K"
        }
    },
    "11": {
        "class_type": "SaveVideo",
        "inputs": {
            "codec": "auto",
            "filename_prefix": "video/Minimax_h3_max",
            "format": "auto",
            "format.codec": "auto",
            "video": [
                "13",
                0
            ]
        },
        "_meta": {
            "title": "Save Video"
        }
    },
    "12": {
        "class_type": "ComfySwitchNode",
        "inputs": {
            "on_false": [
                "14",
                0
            ],
            "on_true": [
                "7",
                0
            ],
            "switch": [
                "18",
                0
            ]
        },
        "_meta": {
            "title": "If/Else Switch"
        }
    },
    "13": {
        "class_type": "ComfySwitchNode",
        "inputs": {
            "on_false": [
                "24",
                0
            ],
            "on_true": [
                "10",
                0
            ],
            "switch": [
                "19",
                0
            ]
        },
        "_meta": {
            "title": "If/Else Switch"
        }
    },
    "14": {
        "class_type": "PrimitiveStringMultiline",
        "inputs": {
            "value": "At 0.00 seconds, cinematic live-action arc shot with slow push-in, centered on a futuristic metallic teal aerodynamic sports car parked on a spacious light grey tiled concrete platform. The background features a calm deep blue ocean, clear cloudless sky, and sharp angular dark grey concrete architectural structures. The car adopts sharp angular body lines, slim white LED headlights, geometric front air intakes with delicate copper aerodynamic fins, and fully raised gull-wing doors. It is equipped with black and silver turbine-style alloy wheels, paired with white leather bucket seats with dark grey inserts and a minimalist futuristic interior.\n\nThe camera slowly circles to the right and pushes closer to the vehicle. The sports car performs a smooth and precise mechanical decomposition in mid-air. The metallic teal body panels, gull-wing doors and four turbine wheels float outward steadily. Interior leather seats and central console hover slightly upward, exposing intricate carbon fiber frameworks, metal brake discs, calipers and suspension structures. All disassembled components suspend in orderly spaced mid-air arrangement with stable posture. Ultra-fine surface textures are clearly presented: delicate metallic flakes inside teal paint, fine leather stitching and grain, and high-precision brushed metal finishes, creating a clean, high-tech and realistic mechanical explosion visual effect."
        },
        "_meta": {
            "title": "Text (Prompt)"
        }
    },
    "18": {
        "class_type": "PrimitiveBoolean",
        "inputs": {
            "value": False
        },
        "_meta": {
            "title": "Boolean (Prompt Enhance)"
        }
    },
    "19": {
        "class_type": "PrimitiveBoolean",
        "inputs": {
            "value": False
        },
        "_meta": {
            "title": "Boolean (Upscale to 2K)"
        }
    },
    "24": {
        "class_type": "MinimaxHailuo03FirstLastFrameNode",
        "inputs": {
            "first_frame": [
                "25",
                0
            ],
            "model": "MiniMax H3 Max Turbo",
            "model.duration": 5,
            "model.prompt": [
                "12",
                0
            ],
            "model.prompt_expansion_mode": "balanced",
            "model.resolution": "768P",
            "seed": 2188635952,
            "watermark": False
        },
        "_meta": {
            "title": "MiniMax H3 First-Last-Frame to Video"
        }
    },
    "25": {
        "class_type": "LoadImage",
        "inputs": {
            "image": "UPLOADED_image_FILENAME"
        },
        "_meta": {
            "title": "Load Image"
        }
    }
})
# Replace each example.com URL with a public URL of your file.
workflow.set_input("25", "image", client.assets.from_url("https://example.com/replace-with-a-url/image"))

# run() also passes api_key to the partner nodes in this workflow.
job = client.run(workflow, api_key=api_key)

API documentation

MiniMax H3 Max Turbo: Image to Video

About

What you provide

Inside the workflow

Requires custom nodes

Use this workflow from code

What you need

Questions & answers

About

What you provide

Inside the workflow

Requires custom nodes

Use this workflow from code

What you need

Questions & answers

What is the difference between the two video outputs?

Why does the 2K upscaling stage fail or get skipped?

Do I need an API key for MiniMax?

Can I control clip length or motion intensity?