Loop Forge

Standing figure

Works, from LTX 2.5 Creative Lab LoRAs, tested locally

Frame from the Still result
Still
Frame from the No LoRA result
No LoRA
Frame from the Cinemagraph LoRA, 1.5 result
Cinemagraph LoRA, 1.5
Watch it in the video at 4:26
LoRA
Cinemagraph at 1.5
Output
768×1152, 121 frames at 24fps
Sampling
8 steps, euler_ancestral
Seed
42
Generated in
6 min
Peak VRAM
11.4 GiB
No LoRA run
Same graph without the LoRA, seed 42, 6 min
Ran on
RTX 3060, 12GB (local)

What was wired in

Works

Her head, her body and the wall stay locked while the hem of the dress and the ends of her hair sway. The eyes still shift slightly, and neither strength 1.5 nor the card's prompt order removed that.

CINEMAGRAPH_MOTION, tripod locked-off static camera, zero camera movement, only the hem of her white dress is swaying gently in a light breeze while her face, glasses, hair and the plain wall behind her stay perfectly still, seamless natural loop, a soft breeze the only sound.

Notes

If the face has to be completely frozen, mask it in the edit.

Download the workflow without the LoRA (json)

The Cinemagraph LoRA on Hugging Face

Run it yourself

Download everything for this test (.zip, 0.5 MB). It holds the workflow, every input it loads and a README. Copy the inputs into ComfyUI/input, put the models below in place and drag the workflow onto ComfyUI.

FilePut it inSize
ltx-2.5-22b-distilled-transformer-comfy-int8-convrot.safetensors gatedmodels/diffusion_models21.5 GB
gemma4-12b-with-proj-ltx-2.5-comfy-int8-convrot.safetensors gatedmodels/text_encoders15.4 GB
ltx-2.5-video-vae-bf16.safetensors gatedmodels/vae1.5 GB
ltx-2.5-audio-vae-bf16.safetensors gatedmodels/vae364.9 MB
ltx-2.5-22b-lora-cinemagraph-0.9.safetensors gatedmodels/loras201.5 MB

The Lightricks repositories (the LTX 2.5 base model and the LoRAs) are gated. Log in to Hugging Face and accept the terms on each repository page before downloading.

No custom nodes. Every node is part of ComfyUI 0.37.0 (commit 0f74f7fb, frontend 1.53.6).