Loop Forge

4 November 2026

NewMOSS-Image add-ons, tested locally

MOSS-Image is OpenMOSS's open image model, released in October under Apache 2.0. Most of the interest is in its text: it spells long lines and follows a layout prompt that says where everything goes. I ran it in ComfyUI on my RTX 3060 with the official templates, then tried the add-ons people are downloading: layout boxes, chinoll's edit LoRA, two Anime2Real LoRAs, CharRef, depth control, three comic page LoRAs, two transparency LoRAs, the DMD 8-step LoRA, Spectrum, a hi-res LoHa and Scale ROPE and three smaller text encoders.

47 prompts, with reference images, settings and links

Featured

All 11 projects

About Loop Forge

Loop Forge is a hobby project testing open-weight AI models in ComfyUI, by someone with no background in film making. Video so far, and every project gets a page here with the prompts, workflows and settings it used.

The house rules: every clip plays uncut, every prompt is published exactly as it was sent to the model, and the parts that did not work stay in.

Local
RTX 3060 with 12GB of VRAM, i5-13400F, 32GB of RAM
Rented
RTX 5090 on RunPod, for higher resolution runs of the same prompts

Rent the same kind of GPU on RunPodAffiliate link: Loop Forge gets credit if you sign up through it, at no extra cost to you.

Software
ComfyUI, with stock templates unless a page says otherwise

Code