Downloads · 30 days
157
8% of all-time downloads
joeygambino/ltx23-surfaces-realism-lora
ltx23-surfaces-realism-lora is a text-to-video model from joeygambino. Use it when you need video from a text prompt. It is set up for diffusion-single-file. The card lists the license as other.
Kills the plastic. LTX-2.3 (and the image models feeding it first frames) defaults to clean, smooth, showroom-new surfaces: pristine asphalt, unmarked walls, grounds that read as rendered geometry. This LoRA is an alw…
Downloads · 30 days
157
8% of all-time downloads
All-time downloads
2K
Public
Repo size
353 MB
Likes
1
Public
Click a slice to open those files.
.safetensors353 MB · 100%
From the Hugging Face model README
Kills the plastic. LTX-2.3 (and the image models feeding it first frames) defaults to clean, smooth, showroom-new surfaces: pristine asphalt, unmarked walls, grounds that read as rendered geometry. This LoRA is an always-on materials prior: cracked wet asphalt stays cracked and wet, concrete gets pores and rust streaks, floors scuff, weeds mat, wood grains. It pushes the render toward surfaces that have existed in weather.
The training captions name only material, condition, framing, and light — they deliberately contain zero realism vocabulary ("photoreal", "detailed", "8k" never appear). The realism therefore trains as unconditional LoRA behavior instead of a phrase you have to remember to include. Load it at 1.0 and write your prompts normally; concrete material nouns in your prompt ("scuffed linoleum", "rust-streaked concrete") still help composition, as they always did.
1,152 LoRA tensors, all in the video branches — attn1 (480), attn2 (480),
ff (192). Zero audio-touching tensors: dialogue, voices, and accents
render byte-identical with or without this LoRA. Verified alongside an
audio-branch accent LoRA in the same stack with no interference.
ltx-2.3-22b-distilled-1.1. Loss 1.01 -> 0.52.ignore_if_contains: ["audio"]),
which is what guarantees the audio lane stays untouched.LoRA weights follow the LTX-2 Community License of the base model. All training imagery self-generated.