Turn an object photo into a Gaussian splat with a local Python workflow
Idol vs ResLeap
Verified pricing tiers, free plans, public APIs, and honest limitations for Idol and ResLeap side by side.
AI image upscaler and enhancer for sharper photos, portraits, anime, and product images.
Specs & availability
| Dimension | Idol | ResLeap |
|---|---|---|
| Pricing | Open source | Freemium · from $7.90/once |
| Free plan | Yes | Yes |
| Open source | Yes | No |
| Public API | No | No |
| Platforms | CLI | Web |
| Site status | Online | Online |
| Last checked | 16 Nov 2026 | 18 Nov 2026 |
Verified plans
Idol plans
- Self-hosted SDK and Idol weightsFree
No licence charge for the Apache-licensed SDK and the weights marked Apache 2.0 on the Idol model card. Computing resources are excluded. Separate encoder terms and gated download approval apply; this is not a hosted service subscription.
ResLeap plans
- FreeFree
Basic features for personal use; 15 credits per month, max resolution 10K, community support, batch processing, no watermark.
- Pro$49/yr
Advanced features for professionals; 200 credits per month, max resolution 10K, no watermark, batch processing.
- Pro+$149/yr
Premium features for power users; 800 credits per month, max resolution 10K, no watermark, batch processing.
- Business$549/yr
Built for teams and commercial users; 3200 credits per month, max resolution 10K, no watermark, batch processing.
- 200 credits pack$7.90/once
Pay-as-you-go credit package valid for 180 days.
- 500 credits pack$14.90/once
Pay-as-you-go credit package valid for 180 days.
Good for vs watch out for
Idol
- Developers prototyping image-to-3D workflows that consume Gaussian splats
- Researchers comparing single-view object reconstruction with configurable sampling
- A splat PLY represents visual appearance; the documented output does not promise a polygon mesh, animation rig or CAD geometry. Surfaces hidden in the input are inferred and may be inaccurate.
- The zero-dollar plan covers downloadable software and declared Idol weight licensing. GPU time, electricity and any rented hardware remain your expense; no managed API credits or ongoing free hosted allowance are included.
- Setup requires a Hugging Face account with permission to retrieve both image encoders. DINOv3 has separate usage and redistribution obligations; do not describe the entire dependency chain as Apache licensed or universally unrestricted.
- The publisher reports roughly 7.2 GB peak GPU memory, but speed varies with hardware and settings. The README headline and benchmark tables give different timings; aidirecto has reproduced neither.
- The displayed image is an official social preview. It is publisher artwork, not a screenshot captured during an independent product trial.
ResLeap
- Upscaling low-resolution photos for print or web
- Sharpening portraits, anime, and product images
- Restoring blurry or faded images with one-click enhancement
- The site does not list supported file formats or upload size limits.
- Refund rules, payment security details, and exact credit use per image are not shown.
- Free and paid plans are credit-based, so usage is limited by monthly credits or purchased packs.
Key features
Idol
- Image preparationThe workflow removes the background and changes its crop for photographs versus synthetic source images.
- Adjustable splat densitySelect a Gaussian count between 32,768 and 1,048,576 to trade detail against representation size.
- Reusable output filesEach run can save the splat, the processed input image and estimated camera data for inspection in downstream applications.
- Python and terminal entry pointsCall the pipeline from application code or invoke its command-line module for a single image or a folder.
- Sampling controlsSet the seed, step count, guidance and optional compilation behaviour when exploring reconstruction quality and runtime.
ResLeap
- 8x image upscaleEnlarges images by up to 8 times while keeping edge detail and clarity.
- 10K outputExports enhanced images at up to 10K resolution, listed as 10240 px maximum.
- Detail recoveryAttempts to reveal hidden texture and recover fine details in low-quality images.
- Portrait enhancementImproves facial detail for clearer portraits and skin texture.
- Photo restorationHelps revive faded photos and other older images.
- Anime upscalingUpscales anime images with cleaner lines and color detail.