ControlNet-Union SDXL ProMax
Free.ai (self-hosted)
·
image_enhance
·
~1000 tokens per image
ControlNet-Union SDXL ProMax ni an Àwọn àwọn àwòrán tí xinsir kọ̀. Ó ní ìmọ́ nínú Image generation with strict structural control: pose copying, sketch-to-render, depth-preserving restyles, lineart fills, architectural straight-line preservation, tile refinement.. Self-hosted on Free.ai GPUs — runs free against your daily token pool (1,000 tokens fún àwòrán kan). Ti fi silẹ labẹ Apache 2.0 — lilo iṣowo ti gba laaye lori Free.ai.
Lò nípa 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":"controlnet-union-sdxl-promax","prompt":"your prompt here"}'Similar models
Àwọn Àtòjọ-ẹ̀yàn
ControlNet-Union SDXL ProMax upscales and sharpens low-resolution images while preserving detail. Upload a small or blurry photo and ControlNet-Union SDXL ProMax 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, ati BMP lọ́wọ́lọ́wọ́ sí 10 MB. GIF àti GIF àti GIF àti GIF àti GIF àti GIF àti GIF àti GIF àti GIF àti GIF àti GIF àti GIF àti GIF àti GIF àti GIF àti GIF àti GIF àti GIF àti GIF àti GIF àti GIF àti GIF àti GIF àti GIF àti GIF àti GIF àti GIF àti GIF àti GIF àti GIF àti GIF
Yes — modern enhancers include face-aware restoration. For very degraded portraits the dedicated /image/restore-face/ tool gives the cleanest result. ControlNet-Union SDXL ProMax handles general scenes plus faces in one pass.
ControlNet-Union SDXL ProMax n ṣiṣẹ́ lorí GPUs̀ wà lọ́wọ́ ilé́ ọ̀fẹ́ rẹ̀ lórí ọjọ́ akọkọ́; lẹhinna $5 → 200,000 tokè tí a fi saǹ. Tokè ~500 fun gbogbo ìṣàfilọ́lẹ̀.
ControlNet-Union SDXL ProMax 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="ControlNet-Union SDXL ProMax" 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.
Ya. Free.ai ǹfàyè lórí ìlò àwọn àwòrán tí a tí ìṣàfihàn. Ò ní ìwọ̀n tí o tí fi pamọ́.
5–20 sekondi ni 2×, 15–60 sekondi ni 4× da lori ìṣàfihàn àwọn ìṣàfihàn àti ìṣàfihàn GPU. Àwọn móòdù Pẹ̀mìmù ní ìparí nínú ìsàlẹ̀-ilà ìsàlẹ̀-ilà àwọn ìpele náà.