Marigold Depth
Free.ai (self-hosted)
·
image_enhance
·
~1000 tokens per image
Marigold Depth is an image upscaler built by ETH Zurich. Strongest at ControlNet depth conditioning, parallax / 2.5D effects, AR/VR scene reconstruction, displacement maps.. Self-hosted on Free.ai GPUs — runs free against your daily token pool (1,000 tokens per image). Released under OpenRAIL++-M — commercial use permitted on Free.ai.
Use via API
OpenAI-compatible REST API. Generate a key and call this model in seconds.
curl -X POST https://api.free.ai/v1/image/enhance/ \
-H "Authorization: Bearer sk-free-..." \
-H "Content-Type: application/json" \
-d '{"model":"marigold-depth","prompt":"your prompt here"}'Similar models
Frequently Asked Questions
Marigold Depth upscales and sharpens low-resolution images while preserving detail. Upload a small or blurry photo and Marigold Depth returns a higher-resolution version suitable for print, large displays, or further editing.
2× and 4× are the standard targets; some configurations support 8×. Final size is capped at 8192×8192 pixels on Free.ai to keep memory bounded.
PNG, JPG, WebP, HEIC, and BMP up to 10 MB. Animated GIFs are processed frame-by-frame.
Yes — modern enhancers include face-aware restoration. For very degraded portraits the dedicated /image/restore-face/ tool gives the cleanest result. Marigold Depth handles general scenes plus faces in one pass.
Marigold Depth runs on our own GPUs against your daily free pool first; then $5 → 200,000 paid tokens. About ~500 tokens per upscale.
Marigold Depth hallucinates plausible detail at the upscale step — it is not a forensic tool. For most consumer uses (web → print, mobile → desktop wallpaper, archive scan → display) the result is convincing.
Crisp on large text + simple logos; small fine print can warp on aggressive (4×+) settings. Use 2× when text fidelity matters most.
Yes — /batch/ accepts a folder. Outputs land in /account/?tab=history with the original filename suffixed `-upscaled`. For folder-tree preservation use the API.
Yes — POST to /v1/image/enhance/ with model="Marigold Depth" and your image. /api/ has the full reference + auth.
Same policy as the rest of Free.ai — self-hosted models stay on our GPUs; premium pass through with a DPA; uploads expire on the share-window schedule (24h anon, 7d signed-in). We do not train on your images.
Yes. Free.ai grants commercial use of upscaled images. You must own the source you uploaded.
5–20 seconds at 2×, 15–60 seconds at 4× depending on source resolution and GPU load. Premium models tend to finish on the lower end of those ranges.