CivArchive
    ← All articles
    Published October 5, 2026by PixelaiLabs

    Free AI Ghost Mannequin + 360° Product Video in ComfyUI (Flux 2 Klein + MiniMax H3) Workflow

    58 views0 reactions0 comments on CivitAI2 collected
    comfyuiworkflowsloraimage to videoclothingfashionproduct photographysam 3360minimax h3flux 2 kleinghost mannequinworkflow

    Turn one ordinary clothing photo (like a jacket on a hanger from an eBay listing) into a hollow ghost mannequin product photo and a full 360° spin video. Everything runs in ComfyUI with free, open models: Flux 2 Klein 9B, SAM 3 and MiniMax H3 with the 360 Orbit LoRA.

    ▶️ Video tutorial:


    📖 Full written guide: pixelailabs.com/blog/ai-ghost-mannequin-comfyui-360-product-video
    📦 Workflow: JSON file is in the attachments of this article.

    What you get

    • A hollow ghost mannequin photo of the front and the back of your garment, on a white background, always square.

    • A seamless 360° spin video of the garment (90 frames, 24 fps).

    What you need

    1. Custom nodes

    Open ComfyUI Manager, click Install Missing Custom Nodes, then restart ComfyUI. The workflows use:

    2. Models for the ghost mannequin (Flux 2 Klein)

    3. Models for the 360 spin (MiniMax H3)

    Part 1: Make the ghost mannequin

    Workflow: image_flux2_klein_image_edit_9b_base.json

    Step 1: Load your photo

    Open the workflow and paste your garment photo into the Load Image node (Ctrl+V works). Any shape is fine: SAM 3 finds the garment and the output is always square.

    Step 2: Check the settings

    • CFG 1, 4 steps, sampler euler

    • Input size 2 MP (use 4 MP if the garment has small text or a logo)

    Step 3: Write the first pass prompt

    Swap "jacket" for your garment (shirt, hoodie, jersey...):

    put the exact jacket from picture 1 in the center of the image and on a front-facing mannequin on a white background.

    Step 4: Keep the second pass prompt

    The second pass removes the mannequin. It uses the first pass and your original photo as references:

    remove the mannequin, keeping the garment's shape as a hollow ghost-mannequin product photo.

    Step 5: Run it, then do the back

    Click Run. Your hollow front saves as front-garment_XXXXX.png. Then load the back photo of the garment, change front-facing to back-facing in the first pass prompt and run again.

    Part 2: Make the 360° spin

    Workflow: video_minimax_h3_r2v.json

    Step 6: Load the front and the back

    • Hollow front → first Load Image (Picture 1)

    • Hollow back → second Load Image (Picture 2)

    Keep this order. If you swap them, the spin can stop at 180°.

    Step 7: Check the settings

    • Aspect 1:1, 90 frames (about 3.75 s at 24 fps)

    • 28 steps, euler / beta

    • 360 Orbit LoRA at 1.0, no turbo LoRA

    • ref_image_size: match

    • Resolution: 0.4 MP for a quick draft, 0.9 MP for the final

    Step 8: Run it

    The prompt is already in the workflow. Click Run and you get a full 360° spin that starts and ends on the front. Here is the full prompt if you want to use it in your own setup:

    subject_definitions:
<Subject 1> is the same person, object, or complete frozen arrangement shown in <Picture 1> and <Picture 2>. <Picture 1> defines the front-facing appearance and initial captured state. <Picture 2> defines the rear-facing appearance of that same subject in that same captured state. Both images describe one consistent subject, including its identity, geometry, proportions, materials, clothing, pose, and any accompanying objects.
<Subject 2> is the seamless white background shown in <Picture 1>.
<Picture 1> is the front-view reference and the composition anchor for the beginning and end of [Shot 1].
<Picture 2> is the rear-view reference and the viewpoint anchor for the halfway point of the camera orbit in [Shot 1].

summary:
[keyframe completion + reference generation] A single continuous shot captures <Subject 1> in one frozen instant against <Subject 2>. Only the camera moves, completing one full 360-degree orbit. The shot begins with the front view established by <Picture 1>, reveals the rear appearance established by <Picture 2> halfway through, and returns to the original front view at the end.

retention_analysis:
<Subject 1> (appears throughout [Shot 1]): fully_preserved - preserve the same identity, shape, proportions, pose, materials, clothing, and arrangement throughout. Use <Picture 1> for front-facing details and <Picture 2> for rear-facing details.
<Subject 2> (appears throughout [Shot 1]): fully_preserved - retain the same seamless white background throughout.
<Picture 1> ([Shot 1] opening and closing front-view anchor): fully_preserved - retain the referenced front appearance and opening composition when the camera returns to its starting viewpoint.
<Picture 2> ([Shot 1] halfway rear-view anchor): fully_preserved - retain the referenced rear appearance when the camera reaches the opposite viewpoint.

detailed_description:
The video retains the natural appearance, materials, and lighting of the references, with the subject clearly visible against a seamless white background.

[Shot 1] One frozen instant. Only the camera moves. In a continuous 360 orbit. Preserve every person and object in exactly the same white background, orientation, shape and pose throughout the shot. Airborne objects remain suspended at the captured height and angle: no wobbling, shaking, spinning, drifting, falling or continued action. Keep faces, hands, clothing, liquids and the background motionless while retaining their natural appearance. Camera parallax is the only source of apparent movement. No cuts, zoom, morphing or added objects.

The shot begins from the front-view composition established by <Picture 1>, showing <Subject 1> in its captured pose and arrangement against <Subject 2>. Preserve the visible identity, silhouette, proportions, surface details, colors, clothing, accessories, and positions of all existing elements. Treat <Picture 1> and <Picture 2> as complementary views of this one frozen subject.

The camera follows a smooth circular path around <Subject 1> at a constant height, radius, focal length, and angular speed. Keep the same orbit center and maintain consistent framing. The camera remains directed toward the subject throughout. Its travel reveals the front, one side, the back, the opposite side, and finally the front again.

At the halfway point, after 180 degrees of camera travel, the rear-facing appearance corresponds to <Picture 2>. Use that reference for the subject's actual back-facing geometry, rear silhouette, rear surfaces, clothing construction, and other visible rear details. These features belong to the same subject from the opening frame and become visible naturally as the camera travels.

Between the supplied viewpoints, maintain coherent three-dimensional geometry and continuous surface appearance. Every element keeps its fixed position and orientation in the scene. Changes in visible silhouette, overlap, perspective, and occlusion arise solely from the camera observing the frozen arrangement from successive angles. Preserve the captured spatial relationships among all people, objects, and suspended elements.

Complete exactly one uninterrupted 360-degree orbit over the shot's full duration. The final view returns to the front appearance and composition established by <Picture 1>, with the same captured pose, arrangement, and framing. The scene remains silent throughout.

overall_soundscape:
Silence. No dialogue, ambience, or sound effects.

non_diegetic_music:
N/A

    Tips

    • Spin stops at 180°? Make sure the front is Picture 1 and the back is Picture 2.

    • Output not square? Check that Image Size By Longer Side feeds the latent and the scheduler. Try clothing as the SAM 3 prompt.

    • Logo changed? Raise the input to 4 MP and use your sharpest photo.

    Credits

    360 Orbit LoRA by Pablo Dawson. Flux 2 Klein by Black Forest Labs. MiniMax H3 and SAM 3 run natively or through the open source nodes listed above.

    More from PixelAI Labs

    Attachments

    Archived from CivitAI · Updated October 5, 2026View source