Video LoRAs: keep your Wan and LTX-2 LoRAs in one private vault
Video LoRAs are several times bigger than image LoRAs, and each one is made for one exact base: a Wan 2.2 14B high-noise LoRA, a Wan 2.1 image-to-video LoRA, an LTX 2.3 LoRA. A few dozen of them fill a disk. Keep every video LoRA, labelled by base, in our own encrypted storage, and download it again on any computer.
Plans from 100 GB to 5 TB. From $4.99 a month.
Wan 2.2 and Wan 2.1 LoRAs
Wan 2.2 is Alibaba's open video family: a 5B text-and-image-to-video model and 14B text-to-video and image-to-video models with two experts, high-noise and low-noise. Many trending Wan LoRAs are still made for Wan 2.1 image-to-video. Each LoRA's model page names its base; keep one subfolder per base.
LTX-2 LoRAs
LTX-2 LoRAs cover camera moves, scene transitions and styles, and they are some of the biggest LoRA files on ModelTrends: several trending ones are over 2 GB. LoRA names say whether they are made for LTX 2 or LTX 2.3, so keep the versions apart.
How big are video LoRAs?
Wan: in a sample of 50 Wan Video 14B text-to-video LoRAs on Civitai the median file was 293 MB. LTX-2: in the ModelTrends trending snapshot (8 LoRAs, a small sample) the median was 658 MB. A Flux image LoRA (median 73 MB in our sample of 50) is shown for comparison.
| Plan | Storage | Price | Wan LoRAs (293 MB) | LTX-2 LoRAs (658 MB) | Flux LoRAs (73 MB) |
|---|---|---|---|---|---|
| Locker | 100 GB | $4.99 a month | ≈ 341 | ≈ 151 | ≈ 1,369 |
| Library | 500 GB | $14.99 a month | ≈ 1,706 | ≈ 759 | ≈ 6,849 |
| Archive | 1 TB | $24.99 a month | ≈ 3,412 | ≈ 1,519 | ≈ 13,698 |
| Studio | 5 TB | $99 a month | ≈ 17,064 | ≈ 7,598 | ≈ 68,493 |
Folders for video LoRAs
ComfyUI reads every LoRA, video or image, from ComfyUI/models/loras/. One subfolder per base keeps the right file at hand:
loras/wan22-14b-high/andloras/wan22-14b-low/for the two Wan 2.2 14B expertsloras/wan22-5b/for Wan 2.2 5Bloras/wan21/for Wan 2.1loras/ltx2/andloras/ltx23/for LTX 2 and LTX 2.3
Every other folder: ComfyUI models folder guide.
Add a video LoRA from Civitai in one click
Paste a Civitai model link in your vault and BigVault adds it in one click. It keeps the model's details and trigger words with the file, and tidies file names and descriptions. Imports run on our servers in the background, so you can close the page.
Building a collection? Read how to keep your own Civitai archive.
Best for beginners. Describe what you want in a chat and the picture comes back, no learning curve.
Images and video from a chat, with short commands. The most convenient tool for Telegram users, with a web companion.
Best for power users. Full control over models, settings and workflows in a browser studio.
Best for communities. Add it to your own server and run any workflow from a channel.
One screen for every model and workflow: prompts, references, edits and video, built into your Graydient account.
Set up local programs if your computer has capable hardware.
Generate the same prompt on up to 50 checkpoint/base models at a time.
Video LoRA questions
- Why are video LoRAs so big?
- Video LoRAs carry more weights than image LoRAs. In our samples the median Wan LoRA was 293 MB and the median LTX-2 LoRA 658 MB, against 73 MB for a Flux image LoRA.
- Do Wan 2.1 LoRAs work on Wan 2.2?
- Match the base named on the LoRA's model page and use it with that base. We don't promise that a LoRA works across versions.
- How many video LoRAs fit in 100 GB?
- About 341 Wan LoRAs or about 151 LTX-2 LoRAs. Estimate from the median file size; real numbers vary.
- Where do video LoRAs go in ComfyUI?
- In ComfyUI/models/loras/, with one subfolder per base, such as wan22-14b-high, wan21 or ltx23.
Video LoRAs fill a disk fast.
Plans from 100 GB to 5 TB. From $4.99 a month.
Questions? info@modeltrends.ai