Stability AI
Legacy but still the main LoRA base on Civitai. 1 credits per image, about 2-6 s on a 4090 per run. Sample price.
| SDXL 1.0 spec | |
|---|---|
| Status | Live |
| Type | Image |
| Version | 1.0 (+ Lightning / DMD2 distills) |
| Resolutions | 1MP |
| Audio | No audio track |
| Licence | CreativeML Open RAIL++-M |
| Where it runs | Milvey GPUs. The run queues if the pool is full. |
| Typical time | 2-6 s on a 4090 |
| Price | 1 cr per image |
Prices and times are samples.
Open models run on Milvey GPUs, and the price follows that GPU time. If the pool is full, the run waits in a queue until capacity returns. It never moves to a paid API. If the run can’t be delivered, the hold is released and you pay 0 cr.
How failed runs are chargedSamples on this site are the makers’ own published outputs, each credited with its source. Stability AI has none listed here so far. Outputs made on Milvey will be added as the beta runs.
Made by other people with LoRAs and checkpoints based on SDXL 1.0. Each one is credited and linked to its source. They are not Milvey outputs. Removal requests: see Terms.
Paid runs OKPerfect Eyes XL
Community example of what this model can produce. Not an Milvey output.
Licence: Sell images they generate, run on Civitai, run on services that generate for money, sell this model, sell merges using this model. Base: CreativeML Open RAIL++-M.
Paid runs OKPerfect Eyes XL
Community example of what this model can produce. Not an Milvey output.
Licence: Sell images they generate, run on Civitai, run on services that generate for money, sell this model, sell merges using this model. Base: CreativeML Open RAIL++-M.
Paid runs OKLCM-LoRA Weights - Stable Diffusion Acceleration Module
by @CivitaiOfficial on Civitai
Community example of what this model can produce. Not an Milvey output.
Licence: Sell images they generate, run on Civitai, run on services that generate for money, sell this model, sell merges using this model. Base: CreativeML Open RAIL++-M.
Paid runs OKSPO-SDXL_4k-p_10ep_LoRA_webui
Community example of what this model can produce. Not an Milvey output.
Licence: Sell images they generate, run on Civitai, run on services that generate for money, sell this model, sell merges using this model. Base: CreativeML Open RAIL++-M.
Paid runs OKThinkDiffusionXL
Community example of what this model can produce. Not an Milvey output.
Licence: Sell images they generate, run on Civitai, run on services that generate for money. Base: CreativeML Open RAIL++-M.
Paid runs OKThinkDiffusionXL
Community example of what this model can produce. Not an Milvey output.
Licence: Sell images they generate, run on Civitai, run on services that generate for money. Base: CreativeML Open RAIL++-M.
Showing 6 of 12. See them all.
SDXL-Lightning (2/4/8-step)
Step-distill LoRA for 2-8 step SDXL.
Licence: CreativeML Open RAIL++-M
RAIL use restrictions.
Sourcexinsir ControlNet Union SDXL 1.0
One ControlNet for pose, depth, canny, lineart, scribble, seg.
Licence: Apache-2.0
SourceIP-Adapter SDXL (h94)
Image-prompt style or content conditioning.
Licence: Apache-2.0
SourceOpen weights. Read the licence text for attribution or usage terms that apply to your project.
Note from the licence: use-based restrictions.
Nothing flagged for this model.
Sources for specs and licence
Black Forest Labs
FLUX1 cr
Sharp stills for keyframes, boards and thumbnails.
~6s · 4 routes
per image
ByteDance
Seedream 4.08 cr
Editable stills with strong reference control.
~9s · 2 routes
per image
Black Forest Labs
FLUX 3 Image12 cr
Edit variant: blackforestlabs/flux-3/edit-image.
Seconds at 1MP · 2 routes
per 1MP image
Join the list. I’ll email you when signups open. No card needed.
Email when signups open · Unsubscribe any time