You need to agree to share your contact information to access this model

By clicking "Agree and Access" you acknowledge the Privacy Policy and consent to receive offers and updates. You can unsubscribe at any time.

Cinemagraph

Transforms still images into smooth, looping cinemagraphs with selective motion while keeping the rest of the scene frozen.

It is based on the LTX-2.3 foundation model.

Example Outputs

Prompt: CINEMAGRAPH_MOTION, tripod locked-off static camera, zero camera movement, the man, face, hair, clothing, beach, sky, and background remain completely frozen, only the beach reflection inside his sunglasses moves, reflected time-lapse of ocean waves roll and shimmer in the lenses, everything outside the glasses stays still, seamless natural loop

Prompt: CINEMAGRAPH_MOTION, tripod locked-off static camera, zero camera movement, the man and cow remain completely frozen, only the clouds in the sky move in fast time-lapse, clouds drift and roll across the sky, grass and foreground remain still, seamless natural loop.

Prompt: CINEMAGRAPH_MOTION, tripod locked-off static camera, zero camera movement, the woman is frozen, her face, eyes, hair, clothing, seat, and airplane interior remain completely frozen, only the illustrated tear drops move downward along her cheeks like a cutout collage animation, seamless natural loop.

Model Files

ltx-2.3-22b-lora-cinemagraph-0.9.safetensors

Model Details

Base Model: LTX-2.3-22B Video
Training Type: LoRA
Modality: image-to-video

Intended Use & Out-of-Scope

Intended use: Creating cinemagraph videos from still images — producing looping videos with selective motion (water, light, elements) while keeping the rest of the scene static. Ideal for creating animated wallpapers, social media content, and artistic motion pieces.

Out of scope: Scenes with camera movement, character/body movement, complex dynamic scenes, videos with multiple moving subjects. The LoRA is optimized for static-camera, single-element-motion scenarios.

How It Works

This LoRA fine-tunes LTX-2.3 to generate cinemagraph-style videos from still images. It excels at creating smooth, continuous-loop animations where only specific elements move (water flowing, neon lights pulsing, rain falling, reflections shimmering) while the rest of the frame remains completely frozen. The model learns to respect spatial isolation — keeping backgrounds, people, and static objects completely still while animating only the designated element.

The training dataset consisted of "no moving people" scenarios with locked-off cameras, so the LoRA strongly respects composition and avoids unwanted motion outside the intended subject.

Usage

🔌 ComfyUI

Copy the LoRA weights into models/loras.
Load the LTX-2.3-22B base model.
Add ltx-2.3-22b-lora-cinemagraph-0.9.safetensors as the LoRA.
Use the T2V/I2V workflow from the ComfyUI-LTXVideo repository.
Start with LoRA strength 0.7–3.0 and adjust per generation.
Include the trigger word CINEMAGRAPH_MOTION in the positive prompt.

Recommended Settings

LoRA strength / weight: 0.7–3.0
Spatial Guidance (STG): Use stg_v mode, scale 1.0, targeting block 29 for enhanced motion control and boundary preservation.
Inference steps: 30 (from training validation)
Guidance scale: 4.0
Prompting: See examples below. The model responds well to explicit descriptions of what should move and what should remain still. Emphasize "locked-off static camera" and "seamless natural loop" for best results.

Example positive prompt:

CINEMAGRAPH_MOTION, tripod locked-off static camera, zero camera movement, only the neon sign flickers, the starburst, Desert, MOTEL, and NO VACANCY neon tubes subtly pulse and flicker like a real vintage neon sign, everything else stays perfectly still, seamless natural loop

Example negative prompt:

cars moving, camera movement, pan, tilt, zoom, parallax, whole image moving, background sliding, person moving, flicker on entire image, noisy texture, crawling texture, distorted, blurry, low quality

Tips & Troubleshooting

Explicit motion boundaries: Be very specific about what moves and what doesn't. "Only the [element] moves; everything else frozen" works better than vague descriptions.
Avoid camera language: The LoRA was trained on static-camera footage. Omit phrases like "camera movement," "pan," "zoom," and "parallax."
Seamless loops: Use "seamless natural loop" or "continuous looping motion" in the prompt to encourage cyclical, repeating movement.
Strength tuning: Strength 0.7–1.0 is conservative; 1.2–3.0 pushes selective motion more aggressively. Test both ranges for your use case.
Resolution: Best results at 512×704 pixels, 25 frames (the training resolution).

Dataset

Cinemagraph (No Moving People) — A carefully curated collection of still images and video references designed for cinemagraph creation. The dataset emphasizes scenes with selective motion elements (flowing water, flickering neon, falling leaves, shimmering light reflections) while keeping characters, backgrounds, and static objects completely frozen. All scenes were shot with locked-off, tripod-mounted static cameras to eliminate parallax and camera drift.

Training

Technique: LoRA fine-tuning on LTX-2.3-22B using the LTX-2 Community Trainer.
Hyperparameters: learning_rate=0.0001, batch_size=1, gradient_accumulation_steps=1, optimizer=adamw8bit, scheduler=cosine, rank=32, alpha=32, dropout=0.0
Steps: 1000
Infrastructure: LTX-2 Community Trainer.