Water into a sandbox
Works, from LTX 2.5 Creative Lab LoRAs, tested locally


- LoRA
- Water Simulation at 1.0
- Output
- 1920×1088, 121 frames at 24fps
- Sampling
- 8 steps, euler_ancestral
- Seed
- 1212
- Generated in
- 34 min
- Peak VRAM
- 10.5 GiB
- Ran on
- RTX 3060, 12GB (local)
What was wired in
This uses the card's prompt template on a clip of a dry sandbox. Water pools around their knees and the bucket pours water instead of sand. The sand around the edges stays dry, and the cream trousers on the right come out as light jeans.
Reference shows two young women kneeling side by side in a wooden sandbox full of dry golden sand in a sunny backyard, scooping sand in their hands, pouring sand from a red bucket and patting the sand. Edited shows the same scene with water added. ADD WATER clear shallow water flooding the whole sandbox and completely covering the sand up to their knees, rippling around their legs; water streaming out of their cupped hands and dripping from their fingers, the red bucket pouring a stream of water that splashes into the flooded sandbox, and their palms slapping the water surface into splashes and spreading rings of ripples. Subject identity, clothing, framing, and background geometry are identical to the reference; only water-related elements differ between reference and edited.
Notes
I also tried to replace all of the sand with water and could not get that to work. This LoRA is strict about the prompt format it expects. The trigger is ADD WATER.
Run it yourself
Download everything for this test (.zip, 10.5 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.
| File | Put it in | Size |
|---|---|---|
| ltx-2.5-22b-distilled-transformer-comfy-int8-convrot.safetensors gated | models/diffusion_models | 21.5 GB |
| gemma4-12b-with-proj-ltx-2.5-comfy-int8-convrot.safetensors gated | models/text_encoders | 15.4 GB |
| ltx-2.5-video-vae-bf16.safetensors gated | models/vae | 1.5 GB |
| ltx-2.5-audio-vae-bf16.safetensors gated | models/vae | 364.9 MB |
| ltx-2.5-22b-ic-lora-water-simulation-0.9.safetensors gated | models/loras | 906.1 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.
Custom nodes: ComfyUI-LTXVideo at commit 3bf3ca6. Everything else is part of ComfyUI 0.37.0 (commit 0f74f7fb, frontend 1.53.6).
