Loop Forge

Dove in flight

Works, from LTX 2.5 Creative Lab LoRAs, tested locally

Frame from the Start still result
Start still
Frame from the No LoRA, slow motion in the prompt result
No LoRA, slow motion in the prompt
Frame from the Slow Motion LoRA, speed 0.2 result
Slow Motion LoRA, speed 0.2
Watch it in the video at 3:07
LoRA
Slow Motion Control at 1.0
Output
1920×1088, 121 frames at 24fps
Sampling
8 + 3 steps, euler_ancestral
Seed
42
Generated in
6 min
Peak VRAM
11.7 GiB
No LoRA run
Same graph without the LoRA, seed 42, 6 min
Ran on
RTX 3060, 12GB (local)

What was wired in

Works

Both clips have the same start still and the same caption. Without the LoRA the wings beat faster and the feather tips blur. With it each frame moves a little, and the flight feathers stay sharp and separate through the stroke.

The prompts

Download workflowDownload everything for this test (.zip, 2.3 MB)
A side-on medium shot follows a white dove flying from left to right low over a sunlit park in the early morning, the trees and grass behind it soft and out of focus. The dove beats its wings: they sweep down from high above its back, the long white flight feathers bending and spreading apart as they push against the air, then fold and rise again for the next stroke, while its fanned tail tilts and its head stays level, its eye fixed ahead. Low golden sunlight shines through the edges of the feathers and rims the bird in light; the camera pans smoothly with the dove to keep it in the frame. The soundscape is the soft, rhythmic whoosh of wing beats and birdsong in a quiet park, rendered with crisp high-resolution detail and warm natural colour.

Notes

The clip without the LoRA mixed slow wings with a neck moving at normal speed, which looked unnatural to me.

Download the workflow without the LoRA (json)

The Slow Motion Control LoRA on Hugging Face

Run it yourself

Download everything for this test (.zip, 2.3 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-latent-spatial-upscaler-x2-bf16-1.0.safetensors gatedmodels/latent_upscale_models995.8 MB
ltx-2.5-22b-lora-slow-motion-control-1.0.safetensors gatedmodels/loras654.5 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).