THE ULTIMATE CAR TRANSITION FIELD GUIDE

THE ULTIMATE
CAR TRANSITION.

FREE + LOCAL VIDEO

Turn a miniature on a train windowsill into a full-size car on the road. A practical MiniMax H3 reference-to-video workflow in ComfyUI.

Start the tutorial ↓

BY KAZI AHMED / IMAGES, PROMPTS & STEP-BY-STEP DIRECTION

ONE CAR. TWO SCALES. ONE CONTINUOUS SHOT.

01 / THE WORKFLOW

GET THE FILES.
SET THE STAGE.

Start with an installed ComfyUI and the supplied files in this folder. The video generation runs locally; ChatGPT or Gemini are optional hosted tools for preparing reference images.

Keep the workflow PNG original. Download the file below directly. Do not convert, recompress, screenshot, or resave it: its embedded metadata contains the ComfyUI workflow.
Download original workflow PNG ↓ Project workflow on Drive ↗

Original ComfyUI workflow screenshot

01 / Load the graph

Drag the original workflow PNG from your file manager onto the ComfyUI canvas. Wait for the graph to appear. If it does not load, download the original again and make sure it was not re-encoded.

02 / Install missing nodes

Use ComfyUI Manager's missing-node installer if available, or inspect each missing node's source and install its package. Restart ComfyUI and reload the graph. Update ComfyUI if native H3 nodes are missing.

03 / Download the models

Read each loader in the graph, download its exact model from its trusted source, and put it in the corresponding folder below. Refresh or restart ComfyUI, then select each file in its loader.

04 / Relink and test

Load the three supplied reference images in the order shown below. Check previews and connections, paste the prompt, and run a smaller test before committing to the full render.

Model folders from the supplied graph

The names above are the saved selections, not bundled model downloads. Use the exact dependencies required by your installed graph. See ComfyUI’s H3 documentation for the native components; this graph uses a FastH3 model, so do not substitute a different model without checking compatibility.

02 / THE REFERENCES

ONE CAR.
THREE MOMENTS.

Use the supplied Ferrari reference or choose any car. Select a clear rear three-quarter photo and use it as the visual authority for all three scenes. The rear points toward the camera on the left; the nose points right. Consistent position, angle and apparent size make the transformation easier to follow.

Download the Ferrari reference ↓

Miniature car and hand on train windowsill

01 / The opening

A hand finishes placing the miniature on the train windowsill in warm sunset light.

Download image ↓
Miniature car visible in a train tunnel

02 / The bridge

The train enters a tunnel. Keep the car lit enough to see its silhouette and wheels.

Download image ↓
Full-size car driving through a tunnel

03 / The reveal

The full-size car drives through a road tunnel, matched to the earlier framing.

Download image ↓

Make your own references

Upload your chosen car photo to ChatGPT or Gemini and ask for an image edit using an available image generator such as Nano Banana. Alternatively, use ComfyUI with an image-editing model such as Qwen Image Edit, if installed. Use the same car photo for all three; for scenes 2 and 3 also provide the approved scene 1 as a framing reference if the model supports multiple images. Set a portrait 9:16 canvas in the generator. Availability and model capabilities vary.

Generate scene 1 first. Compare roofline, rear lights, wheels and contact points across subsequent results. Regenerate if the car shifts or changes shape. The provided road image is close, but not perfectly aligned; it may move vertically during generation.

Copy the three image prompts ↓

01 / Opening

Use the attached car as the exact vehicle reference. Create one vertical 9:16 cinematic photograph: a realistic hand finishes placing a miniature of this car on a moving passenger train's windowsill at sunset. Keep the reference car's exact body, wheels, lights and rear three-quarter angle; rear closest to camera on the left, nose pointing right. Keep the entire car visible in the lower half of the frame. Realistic materials, natural hand contact, window reflections and photographic lighting. No text or collage.

02 / Transition

Use the car photo for vehicle identity and the opening frame for composition. Show the same miniature on the same sill as the train enters a tunnel. Remove the hand. Match the car's exact angle, size, position, silhouette and wheel contact points. Let the surroundings fall into shadow, but keep a soft passing light on the red body, roofline, wheels and rear so the car remains visible. Vertical 9:16, realistic low-light photography.

03 / Road

Use the car photo for vehicle identity and the opening frame for composition. Replace the train and sill with asphalt and a road tunnel. The same car is now full-size, driving toward the tunnel exit. Match the opening frame's car angle, size, position, silhouette and wheel contact points. Natural tunnel lights and reflections, subtle wheel rotation blur and background motion blur, sharp body, realistic live-action automotive photography. Vertical 9:16.

03 / THE ANIMATION

KEEP THE CAR.
CHANGE THE WORLD.

Load 01-train.png, 02-transition.png and 03-road-motion.png in that order. The R2V node receives them as <Picture 1>, <Picture 2> and <Picture 3>. These are references, not guaranteed timed keyframes.

The supplied graph saves a 15-second target, portrait selector, 24 fps, an 8-step simple schedule and fixed seed. The duration expression snaps the frame count to its supported grid, so inspect the exported result. Set 1080 × 1920 only if your graph supports it, and check the actual output dimensions: the screenshot's selector does not by itself prove a particular final size. Kazi's run on an RTX 5070 Ti was reported at 1080 × 1920, about 45 seconds per iteration and 8–9 minutes total; hardware and settings affect performance.

Visible car, dark environment. The bridge should never need a full blackout. Keep the body readable as the sill becomes asphalt.

Copy the video prompt

subject_definitions: <Subject 1> is the red Ferrari 849 Testarossa in <Picture 1>, <Picture 2>, and <Picture 3>. Preserve its red paint, body shape, rear winglets, black wheels, and rear-light design throughout. <Picture 1> defines the opening train-window composition and the hand placing the miniature. <Picture 2> defines the tunnel transition composition. <Picture 3> defines the full-size car and road-tunnel composition. summary: A single continuous, photorealistic 15-second cinematic shot. A hand places a miniature Ferrari on a moving train's windowsill. Passing tunnel light reveals a continuous transformation of the surroundings while the car stays visible, becoming the same full-size Ferrari driving through a road tunnel. The camera maintains a consistent rear three-quarter view. retention_analysis: <Subject 1>: Preserve the same vehicle design, orientation, apparent size, and position in the frame across both scales. <Picture 1>: Use the hand, miniature car, train window, and warm sunset for the opening. <Picture 2>: Use the shadowed train-window composition during the transition. <Picture 3>: Use the full-size car and road tunnel for the extended ending. detailed_description: One continuous vertical shot, with no cut. The camera holds a low rear three-quarter view: the rear of the car is closest to the camera and its nose points to the right. 0–3 seconds: Begin with <Picture 1>. A hand gently finishes placing the miniature red Ferrari on the train windowsill. Its wheels touch the surface naturally. The fingers release the roof and the hand withdraws out of frame. Warm sunset light falls across the car as the landscape moves past outside. 3–6 seconds: The miniature remains on the windowsill as the train enters a tunnel. The sunset and scenery outside fade into darkness, but a soft moving tunnel light continues to illuminate the Ferrari. Its red body, roofline, rear winglets, and wheels remain visible at all times. The camera stays steady relative to the car. 6–9 seconds: A soft band of tunnel light passes over the Ferrari as the surroundings transform continuously around it. The window frame recedes into shadow, and the windowsill gradually becomes asphalt beneath the same wheels. Lane markings and tunnel walls emerge around the car. Throughout the change, the Ferrari remains continuously visible in the same position, orientation, and apparent size. There is no blackout, disappearance, cut, or sudden reappearance. The camera smoothly becomes a tracking camera following the full-size car. 9–15 seconds: Stay with the full-size Ferrari as it drives through the tunnel. The camera tracks smoothly behind and alongside at the same speed. Its wheels rotate naturally, lane markings flow backward, and overhead lights sweep across the red bodywork. The car continues toward the distant tunnel exit. Hold the rear three-quarter framing and let the driving shot breathe through the end. Use realistic materials, natural reflections and exposure, subtle film grain, and restrained cinematic color. Live-action automotive cinematography. No cuts, abrupt camera moves, extra vehicles, or changes to the car's design. overall_soundscape: Soft train vibration and a small contact sound as the toy touches the sill. Train rumble gradually blends into tire noise, a restrained engine note, and tunnel reverberation. non_diegetic_music: None.

Why this direction works

The reference definitions give each image a job. The retention section identifies what must stay constant. The timeline separates hand action, entering the tunnel, the environmental change and the longer driving shot. Passing light keeps the car readable while the setting changes. Sound supports the shift from train to road.

04 / TROUBLESHOOTING

FIX THE RELATIONSHIP.
KEEP WHAT WORKS.

The frame goes black

Brighten the car in the transition reference while leaving the surroundings dark. Repeat that the car stays visible, and remove instructions that say darkness hides the whole change.

The car jumps or changes shape

Compare the roof, wheel centers and rear lights in all three images at the same aspect ratio. Rework the mismatched reference using the opening as your composition guide. Keep the same seed while testing one change at a time.

The hand looks strange

Start with a hand already touching the model and ask it to finish placing and release it. Make a shorter hand-action test, then return to the full timeline.

Out of memory or slow generation

Try a smaller supported resolution or shorter test, close other GPU-heavy apps, and check the graph's model and attention settings. Increase the output only after the shot works.

References appear at the wrong time

R2V references guide the model; they are not hard timeline anchors. Clarify each role and timing, or try a compatible first/last-frame workflow if endpoint control is more important. Verify the installed graph before using guide nodes.

YOUR NEXT SCENE STARTS HERE

SMALL ACTION.
BIG CINEMA.

Choose a car. Match the frames. Let the world change around it.

Back to the workflow ↑