Loop ForgeA Trip Down Market Street, 1906
Works, from LTX 2.5 Creative Lab LoRAs, tested locally
- LoRA
- Restore at 1.0
- Output
- 1440×1088, 97 frames at 24fps
- Sampling
- 8 steps, euler
- Seed
- 42
- Generated in
- 18 min
- Peak VRAM
- 11.4 GiB
- Ran on
- RTX 3060, 12GB (local)
What was wired in
Guide video
A Trip Down Market StreetMiles Brothers, 1906. Public domain, via the Internet Archive. 640×480Download MP42.2 MB
This is a 640×480 web copy of a film shot from the front of a cable car in San Francisco in 1906. One pass adds colour, removes the scratches and the flicker and adds detail, and the SIGHT lettering on the cable car survives. The far background, the distant people and the building fronts are rebuilt rather than recovered, because there was little detail there to begin with.
a busy city street in 1906 seen from the front of a moving cable car, pedestrians in dark period suits, long coats and bowler hats crossing the tracks, horse-drawn carriages and early open motor cars, a wooden cable car, tall stone and brick buildings, cobblestones and steel rails, spring daylight, natural colour, sharp photographic detail, crisp faces and clothing texture, natural grain, high resolution footage
blocky compression, banding, mosquito noise, ringing, blurry, smeared, ghosting, low resolution, logos, signage, lettering, modern vehicles, modern buildings, traffic lights, graffiti, plastic, oversharpened halos, warped faces
Notes
The source is resized to the 1440×1088 canvas with lanczos and nothing else, then processed in 960×544 tiles. The prompt names the period, the place, the light and the clothing, and the negative names modern objects.
Run it yourself
Download everything for this test (.zip, 2.2 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-audio-vae-bf16.safetensors gated | models/vae | 364.9 MB |
| ltx-2.5-video-vae-bf16.safetensors gated | models/vae | 1.5 GB |
| ltx-2.5-22b-ic-lora-restore-1.0.safetensors gated | models/loras | 1.7 GB |
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).