SDXL LoRAs and checkpoints: keep the whole library private
Stable Diffusion XL 1.0 is Stability AI's 2023 latent diffusion model, with two text encoders, a native 1024×1024 resolution and an optional refiner. It is the parent of the largest fine-tune ecosystem on ModelTrends, which is why SDXL libraries get big: LoRAs, checkpoints and VAEs add up fast.
Keep your whole SDXL library, LoRAs and checkpoints, in your private vault.
Plans from 100 GB to 5 TB. From $4.99 a month.
SDXL LoRAs vs checkpoints: why SDXL libraries get big
An SDXL LoRA is a few hundred MB. A full SDXL checkpoint is about 6.9 GB. SDXL has the largest fine-tune ecosystem, so most SDXL users keep several checkpoints plus many LoRAs, and that is what fills a disk.
How big are SDXL LoRAs?
In a sample of 50 SDXL 1.0 LoRAs on Civitai the median file was 218 MB: 84% were under 500 MB, 96% under 1 GB, and the largest was 2,175 MB. The SDXL base 1.0 checkpoint (sd_xl_base_1.0.safetensors) is about 6.9 GB. They are .safetensors files.
| Plan | Storage | Price | About how many fit (218 MB median) | SDXL base-size checkpoints |
|---|---|---|---|---|
| Locker | 100 GB | $4.99 a month | ≈ 458 | ≈ 14 |
| Library | 500 GB | $14.99 a month | ≈ 2,293 | ≈ 72 |
| Archive | 1 TB | $24.99 a month | ≈ 4,587 | ≈ 144 |
| Studio | 5 TB | $99 a month | ≈ 22,935 | ≈ 720 |
Where SDXL LoRAs go, and how to keep them organized
ComfyUI and Forge folders
ComfyUI reads LoRAs from ComfyUI/models/loras/, Forge from webui/models/Lora/. One subfolder per family or base keeps things findable: loras/sdxl/, checkpoints/sdxl/, vae/sdxl/. Then refresh the LoRA list.
Name files and keep trigger words
Name each file author-concept-version and keep its trigger words next to it, so you still know how to use it months later (how to install a LoRA, step by step).
Keep the whole folder in your private vault
Drag your whole models folder into BigVault. It sits in our own encrypted storage, and you can download it again on any computer (download scripts for Mac, Linux and Windows).
Add a SDXL 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.
Render SDXL LoRAs on Graydient (Beta)
Graydient's workflows list shows the workflows it runs today. Rendering a model from your vault on Graydient is in Beta and needs a Graydient plan; .safetensors files under 25 GB are compatible, apart from a few edge cases. Pasting vault links into the Graydient dashboard is coming soon.
Graydient: “Use 100,000+ Civitai models, instantly installable in one click.”
SDXL LoRA questions
- How big is an SDXL LoRA?
- In a sample of 50 SDXL 1.0 LoRAs on Civitai the median was 218 MB, and 96% were under 1 GB.
- How many SDXL checkpoints fit in 100 GB?
- About 14 at the size of the SDXL base checkpoint (about 6.9 GB). Estimate; real numbers vary.
- Where do SDXL files go?
- In ComfyUI: LoRAs in models/loras/, checkpoints in models/checkpoints/, VAEs in models/vae/. In Forge: webui/models/Lora/ for LoRAs.
- Can I keep .ckpt files too?
- Yes. BigVault keeps any model files, not only .safetensors.
Keep your whole SDXL library in one private place.
Plans from 100 GB to 5 TB. From $4.99 a month.
Questions? info@modeltrends.ai