Woman with umbrella
Works, from LTX 2.5 Creative Lab LoRAs, tested locally


- LoRA
- Clean Plate at 1.0
- Output
- 1024×576, 129 frames at 25fps
- Sampling
- 8 steps, euler_ancestral
- Seed
- 42
- Generated in
- 8 min
- Peak VRAM
- 11.6 GiB
- Ran on
- RTX 3060, 12GB (local)
What was wired in
She and her umbrella are removed from every frame and the graffiti behind her is rebuilt. The bus in the opening frames is left where it was.
An empty clean plate of the exact same location: identical graffiti-covered concrete wall, glass bus-stop shelter, metal bin, pavement and soft daylight as the source video, with no people, no humans, no figures, no umbrella, no trench coat, and no body parts such as arms, hands or legs anywhere in the frame. Static photorealistic footage, natural light, high detail.
person, people, human, figure, limb, arm, hand, leg, body part, umbrella, red umbrella, trench coat, shadow of a person, leftover people, leftover figures, ghosting, semi-transparent remnants, blurry, soft, distorted, inconsistent motion, jitter, worst quality, cartoon, video game, ugly
Notes
Describe the empty scene in the prompt, and name what to remove in both the prompt and the negative. The LoRA was trained at 1024×576 and 25fps, so this runs 129 frames.
Run it yourself
Download everything for this test (.zip, 1.0 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-clean-plate-1.0.safetensors gated | models/loras | 327.3 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).
