DigitalByte/LTX-2.5-Exploded-View-XPLDV

XPLDV — Exploded-View LoRA for LTX-2.5

Turn a source image into an animated exploded view. XPLDV separates an object's exterior parts to reveal the components underneath, for product showcases, mechanical reveals, architectural breakdowns, and stylized cutaways.

Download LoRA · ComfyUI workflow · Sample image · Workflow guide · Prompt guide

How it works

1. Load the included workflow and select your installed model files.
2. Download the sample PC image and upload it in Starting image, or copy it to ComfyUI/input/xpldv_computer.png. The workflow is prefilled with its exact tested prompt.
3. Generate the video with XPLDV at strength 0.5.

For your own subject, replace the image and fill the BASIC template in the note directly above the positive prompt, or use the COMPLEX template in the reference note. Describe which parts separate, what they reveal, and how the camera moves.

The recommended starting model, based on our tests, is ltx-2.5-22b-distilled-transformer-bf16.safetensors. It can also be used with ltx-2.5-22b-dev-transformer-bf16.safetensors, which it was trained on. The included workflow uses the distilled model. Base models: Lightricks/LTX-2.5.

Featured videos

Six 10-second single-image examples at strength 0.5, plus a six-second shoe example at 0.7 using first and last frame guidance. Each video includes its exact recorded prompt.

Prompt

An open laptop separates into an ordered exploded view while resting stationary on the wooden table. The complete display assembly lifts free of its hinge mounts and translates upward and backward, keeping the screen, bezel and rear cover together at the original open angle, with a clear air gap between the display and the rear edge of the base. The entire keyboard and trackpad deck, including all keys and the palm rest, detaches and translates straight upward as one flat horizontal assembly. It rises high above the lower case, exposing the circuit board and cooling system toward the back and the flat battery pack beneath the palm rest. These exterior parts move first and travel furthest, leaving generous open gaps around the internal assemblies. One compact circuit board with its chips, cooling fans and metal heat pipes rises beneath the keyboard deck, with all of these components remaining mounted together as a single assembly. The flat dark battery cells remain joined as one battery pack and translate upward and slightly forward from the front portion of the lower case, exposing the shallow battery compartment and mounting points underneath. The remaining lower case is one empty shallow metal tray resting on the tabletop. The raised keyboard deck, circuit board and battery pack occupy three separate horizontal levels with broad bands of open air between them; the upright display is positioned behind the stack and the empty lower tray stays beneath it. Each of the five major assemblies retains its original shape as the layers settle into an organized arrangement and hold steady. The camera slowly orbits to the right around the laptop from the starting three-quarter view, keeping the full expanded arrangement visible. The soft daylight remains consistent throughout one continuous shot.

Prompt

The desktop computer tower separates into an ordered exploded view. The glass side panel, front panel, top cover and lower power-supply cover move outward along controlled paths, revealing the motherboard, graphics card, liquid-cooling assembly and power supply. The components separate into an organized layered arrangement around the case while retaining their original shapes. The case base stays on the desk. The camera slowly orbits to the right around the computer from the starting three-quarter view. The blue-white computer lighting and surrounding room remain consistent throughout the continuous shot.

Prompt

A black SUV keeps driving down the highway as it separates into an ordered exploded view. The hood and roof lift into separate horizontal layers; the four doors slide sideways; the front bumper and grille slide forward; the four wheels slide outward along their axles while spinning. These exterior parts move first and travel furthest along controlled paths, revealing the chassis, SUV V6 engine block, steering column and front and rear seats, all remaining assembled in their original positions. Each detached component keeps its shape in a clearly spaced suspended arrangement around this exposed core, and the entire arrangement travels forward together. The camera tracks alongside at matching speed as the road and guardrail flow backward continuously. Warm sunlight remains consistent.

Prompt

A luxury automatic mechanical wristwatch separates into an ordered exploded view while resting stationary on its dark velvet display cushion. The front sapphire crystal and surrounding polished bezel rim detach as a single unit and translate forward and slightly upward, keeping its circular orientation facing the camera. The hour, minute, and slender seconds hands lift cleanly above the dial plane, each translating upward along its own short vertical path with slight lateral spacing between them. The main dial plate carrying its applied hour markers, subdial components, and open-heart cutout details moves forward a shorter distance than the crystal, creating a clear gap between it and the hands above. These exterior parts move first and travel furthest, leaving generous gaps between each successive layer. They reveal the mechanical movement at the center of the stack—its polished bridges, interlocking gears, escapement fork, oscillating balance wheel, ruby jewels, and complication modules all visible in their assembled configuration—with the rear exhibition caseback and its oscillating automatic rotor translating backward and slightly downward as the final layer. The movement's bridges, gears, and escapement remain mounted together as a single mechanical unit. Each detached section retains its original shape as the five layers settle into an organized axial arrangement and hold steady. A slow, steady camera pull-back provides room for the full expanded stack. The soft upper-left key light, cool right-side fill, and subtle rim highlight consistent with the source image continue through one continuous shot.

Prompt

The two-story house separates into an ordered exploded view. The main roof and garage roof lift straight upward and remain suspended above the building. The front door, garage door and individual window units move forward out of their openings; the exterior wall panels slide sideways and forward away from the house. These exterior parts move first and travel furthest along controlled paths, exposing one continuous timber frame with vertical studs, horizontal beams, floor joists, roof trusses and the interior staircase. The timber frame and foundation remain assembled in their original positions. The detached roofs, wall panels, doors and windows retain their original shapes in a clearly spaced suspended arrangement around the exposed frame. The camera slowly pulls back to keep the entire arrangement visible while the dusk lighting, garden and neighboring houses remain consistent throughout the continuous shot.

Prompt

The single-engine fighter jet separates into an ordered exploded view while its landing gear remains planted on the runway. The nose radome slides straight forward along the aircraft centreline, revealing a circular radar antenna in the nose and compact avionics boxes immediately behind it. The clear canopy lifts upward, exposing the single ejection seat and instrument panel in the cockpit. Upper fuselage skin panels rise in separate sections, and the two wing assemblies translate sideways while remaining level. These exterior components move first and travel furthest, opening clear gaps around the internal airframe. One cylindrical turbofan engine remains mounted lengthwise in the central rear fuselage behind the cockpit, with metallic compressor casing and turbine sections visible. The cockpit, intake duct, fuselage ribs and landing-gear supports stay assembled in their original positions. Each detached section retains its shape as the arrangement settles and holds steady. The camera slowly pulls back in the original three-quarter view, keeping the whole aircraft visible under consistent sunset light.

Prompt

A premium running shoe separates into an ordered exploded view. The woven upper and laces lift together as one recognizable shoe-shaped shell. The insole rises beneath the upper, the pale cushioning midsole separates into its own curved horizontal layer, and the thin carbon-fiber plate lifts slightly above the dark rubber outsole. Each long shoe-shaped component stays aligned heel to toe, revealing the cushioning structure and support plate between the upper and the sole. The outsole remains on the display surface. The parts settle into a clean suspended stack with distinct air gaps and retain their original shapes. The camera slowly arcs to the right and pulls back enough to keep the full arrangement visible. Cool teal studio light and a restrained warm edge highlight remain consistent throughout the shot.

With and without XPLDV

Matched comparisons using the same image, prompt, seed, and settings. Comparison videos are silent.

Laptop · Computer · SUV · Watch · House · Fighter jet · Running shoe

The shoe comparison keeps both image guides fixed and uses the recorded strength of 0.7 on the XPLDV side. Compare the movement and component behavior between the guided endpoints. Shoe workflow and guidance.

Recommended settings

Start with LoRA strength 0.5.

Setting	Recommended value
CFG	1 in both stages
Duration	10 seconds: 241 frames at 24 FPS
First stage	960 × 544; Euler ancestral; 8 steps
Second stage	1920 × 1088; Euler; 3 steps
Second-stage manual sigmas	0.85, 0.7250, 0.4219, 0.0
Image conditioning	0.7 in the first stage; 1.0 in the second
Prompt enhancement	Can be enabled; off in the recorded examples
Negative prompt	Empty
Seed for comparisons	42 in both stages

The workflow includes these settings and applies the LoRA to both stages. The manual sigmas above belong in Upscale and re-sampler (3 steps); keep the first-stage schedule unchanged.

Prompt enhancement: Enabling Enhance prompt works with XPLDV, but results may vary. It has not been extensively tested. The recorded examples used enhancement off to preserve the supplied prompts.

LoRA strength

These are observed tendencies from the tests, not fixed rules for every subject.

LoRA strength	Observed behavior
0.5	Recommended balance of separation, shape, and detail.
0.75	Stronger influence; can improve separation, but may simplify detail or repeat parts.

Change one setting at a time while keeping the image, prompt, and seed fixed.

Prompting

Start with "separates into an ordered exploded view." This phrase appears in all 204 separation training captions. Name the parts that move, the components revealed underneath, and the final arrangement. Write one continuous paragraph.

Use the slot reference to fill the placeholders in either template.

“Separates into individual components” is another phrasing we tested. With either opening, describe the movement and the final arrangement.

BASIC template — a short, readable reveal

[SUBJECT] separates into an ordered exploded view. [NAMED OUTER PARTS] move outward along controlled paths, revealing [NAMED INTERNAL COMPONENTS] underneath. The parts settle into an organized [LAYERED / RADIAL] arrangement around [EXPOSED CORE] while retaining their original shapes. [CAMERA BEHAVIOR]. [LIGHTING CONSISTENT WITH THE IMAGE] remains consistent throughout the continuous shot.

Example: Desktop PC

The desktop computer tower separates into an ordered exploded view. The glass side panel, front panel, top cover and lower power-supply cover move outward along controlled paths, revealing the motherboard, graphics card, liquid-cooling assembly and power supply. The components separate into an organized layered arrangement around the case while retaining their original shapes. The case base stays on the desk. The camera slowly orbits to the right around the computer from the starting three-quarter view. The blue-white computer lighting and surrounding room remain consistent throughout the continuous shot.

Watch the example · Download its starting image

COMPLEX template — a detailed, cinematic reveal

A COMPLEX prompt guides a more detailed, cinematic reveal through successive layers, describing deeper internal components, their appearance, and their positions, including details hidden or difficult to see in the starting image. These descriptions give LTX 2.5 the information needed to construct the intended reveal beyond what the image alone shows.

[SUBJECT] separates into an ordered exploded view while [CONTINUING ACTION OR ANCHORED SUPPORT]. [OUTER PART A] detaches and translates [DIRECTION], keeping [ORIENTATION]. [OUTER PART B] moves [DISTINCT PATH], and [OTHER OUTER PARTS] move [PATHS]. These exterior parts move first and travel furthest, leaving clear gaps. They reveal [SPECIFIC COMPONENT AND RECOGNIZABLE FEATURES] at [POSITION RELATIVE TO THE OBJECT], with [OTHER COMPONENTS AND THEIR LOCATIONS]. [CORE COMPONENTS] remain mounted together. Each detached section retains its shape as the arrangement settles and holds steady. [CAMERA BEHAVIOR]. [CONSISTENT LIGHTING] continues through one continuous shot.

Example: Watch

A luxury automatic mechanical wristwatch separates into an ordered exploded view while resting stationary on its dark velvet display cushion. The front sapphire crystal and surrounding polished bezel rim detach as a single unit and translate forward and slightly upward, keeping its circular orientation facing the camera. The hour, minute, and slender seconds hands lift cleanly above the dial plane, each translating upward along its own short vertical path with slight lateral spacing between them. The main dial plate carrying its applied hour markers, subdial components, and open-heart cutout details moves forward a shorter distance than the crystal, creating a clear gap between it and the hands above. These exterior parts move first and travel furthest, leaving generous gaps between each successive layer. They reveal the mechanical movement at the center of the stack—its polished bridges, interlocking gears, escapement fork, oscillating balance wheel, ruby jewels, and complication modules all visible in their assembled configuration—with the rear exhibition caseback and its oscillating automatic rotor translating backward and slightly downward as the final layer. The movement's bridges, gears, and escapement remain mounted together as a single mechanical unit. Each detached section retains its original shape as the five layers settle into an organized axial arrangement and hold steady. A slow, steady camera pull-back provides room for the full expanded stack. The soft upper-left key light, cool right-side fill, and subtle rim highlight consistent with the source image continue through one continuous shot.

Watch the example

See the prompt guide for motion, preservation, and optional audio, plus troubleshooting.

Limitations and tips

• Hidden construction is imagined by the model. Detailed-looking internals may be inaccurate or misplaced.
• Parts can merge, duplicate, bend, or lose their identity. Start with a few major assemblies and give them distinct movement paths.
• Background objects, text, and camera framing can change. Leave room around the subject and check the full clip.
• Review new images and seeds individually. The settings above are a starting point, and stronger LoRA influence is not always an improvement.

Training

Setting	Value
Trainer	Lightricks LTX trainer
Base transformer	LTX-2.5 22B DEV BF16
Hardware	One NVIDIA RTX PRO 6000 Blackwell Workstation Edition, 96 GB VRAM
LoRA rank / alpha	64 / 64
Training steps	4,000
Released weights	Step 3000

Dataset

Item	Details
Creation	Synthetic clips created in-house with Blender EEVEE Next
Objects	102 multipart objects
Clips	256 total: 204 separation clips and 52 reversed reassembly clips
Resolution	960 × 544
Length and frame rate	121 frames at 24 FPS
Arrangements	Radial, horizontal, and vertical
Audio	No audio in the training clips; audio was not trained

The photographic example images were used for inference, not training. Image-to-video is the evaluated use. Training includes reassembly, but a complete separate-hold-reassemble sequence within ten seconds is not established.

Training configuration · Dataset summary

License

Distributed under the included LTX-2.x Community License Agreement. See Lightricks/LTX-2.5 for the base model and its terms.