1956 Navy film, diploma handover
Works, from LTX 2.5 Creative Lab LoRAs, tested locally


- LoRA
- Deblur at 1.0
- Output
- 960×544, 161 frames at 29.97fps
- Sampling
- 8 steps, euler_ancestral
- Seed
- 42
- Generated in
- 4 min
- Peak VRAM
- 10.8 GiB
- Ran on
- RTX 3060, 12GB (local)
What was wired in
Guide video
Japanese Bride SchoolUS Navy, 1956, National Archives 75330. Public domain, via the Internet ArchiveDownload MP42.7 MB
The National Archives catalogues this shot as out of focus. Her face, earring, collar and buttons come into focus and she stays the same woman, while the background stays soft.
Reference shows a 1950s black-and-white documentary film shot: a smiling middle-aged American woman in a small felt hat and a light wool suit with a brooch stands on a stage in a bright hall and hands a diploma to a young Japanese woman with short dark curled hair who bows and leans in from the right, a dark curtain behind them, heavily out of focus with soft defocused blur and no fine detail. Edited shows the same scene in sharp focus with crisp detail and clean edges. DEBLUR a 1950s black-and-white documentary film shot: a smiling middle-aged American woman in a small felt hat and a light wool suit with a brooch stands on a stage in a bright hall and hands a diploma to a young Japanese woman with short dark curled hair who bows and leans in from the right, a dark curtain behind them Subject identity, framing, and background geometry are identical to the reference; only focus and sharpness differ between reference and edited.
Notes
Together with Decompression, I think this is a good option for old footage.
Run it yourself
Download everything for this test (.zip, 2.8 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-deblur-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).