AI clothes changer
Transform clothing or the full look. Params: image_url, prompt, optional token.
/change?image_url=IMAGE_URL&prompt=TEXTImage generation, editing, enhancement, restoration, background removal, face swap, music, and more — powered by multiple providers behind one proxy-aware service.
Image generation, editing, enhancement, and face tools.
Transform clothing or the full look. Params: image_url, prompt, optional token.
/change?image_url=IMAGE_URL&prompt=TEXTRemove a background. Params: photo_url (or image_url), optional mode.
/bg?photo_url=IMAGE_URLRemove watermarks. Params: photo_url (or image_url).
/watermark?photo_url=IMAGE_URLSwap a face. Params: source_url, face_url; POST also accepts a JSON body.
/faceswap?source_url=SOURCE_URL&face_url=FACE_URLEdit with a prompt. Params: image_url, prompt, model (default nano-banana), aspect_ratio, resolution.
/image-editor?image_url=IMAGE_URL&prompt=TEXTGenerate from text. Params: prompt, model (flux-schnell), aspect_ratio (1:1), style (japanese_anime).
/image-generator?prompt=TEXTUpscale an image. Params: image_url, scale (default 2).
/image-upscaler?image_url=IMAGE_URL&scale=2Improve detail. Params: image_url, creative (default 0.35).
/photo-enhancer?image_url=IMAGE_URL&creative=0.35Create music. Params: lyrics, prompt, tags, duration, style, genre, mood, tempo, instrumental.
/music?lyrics=LYRICS&prompt=TEXT&duration=60Generation, restoration, enhancement, and cleanup.
Params: prompt, model (ezremove_4.0, nano_banana, seedream, gpt_image_2, and more), ratio (1:1), image_resolution (1K/2K/4K).
/ezremove/image-generator?prompt=TEXT&model=MODELParams: image_url, prompt, model, ratio, image_resolution (1K/2K/4K).
/ezremove/photo-editor?image_url=IMAGE_URL&prompt=TEXTParams: image_url, model (v1/v2), mode (v1), resolution (1K/2K/4K).
/ezremove/upscaler?image_url=IMAGE_URL&model=v2&resolution=2KParams: image_url, resolution (1K/2K/4K).
/ezremove/photo-enhancer?image_url=URL&resolution=2KParams: image_url, tone (colorize, black_white, cool_silver, sepia).
/ezremove/photo-restoration?image_url=URL&tone=colorizeParams: photo_url/image_url, mode (general_v1, general_v2, logo, text, anime, custom).
/ezremove/bg?photo_url=IMAGE_URL&mode=general_v1Params: photo_url or image_url. Uses Auto Mode with model v2.
/ezremove/text-remover?photo_url=IMAGE_URLReturns live model, resolution, tone, and background-mode options.
/ezremove/modelsFast image enhancement and creative image tools.
Params: image_url, optional scale_factor/scale (default 2).
/clipsnap/image-enhancer?image_url=IMAGE_URLParams: image_url, optional scale_factor/scale (default 2).
/clipsnap/image-upscaler?image_url=IMAGE_URLParams: image_url or photo_url.
/clipsnap/background-remover?image_url=IMAGE_URLParams: image_url, blur_strength/blur (default 50).
/clipsnap/blur-background?image_url=IMAGE_URLParams: image_url, expand_left/right/top/bottom or left/right/top/bottom (pixels).
/clipsnap/image-extender?image_url=IMAGE_URL&left=200&right=200&top=200&bottom=200Params: prompt, model, aspect_ratio (default 9:16), style, wait (false returns a task).
/clipsnap/image-generator?prompt=TEXTFetch live generator options.
/image-generator/optionsText-to-image and AI image editing with task polling.
Params: prompt, aspect_ratio (default 9:16), optional wait=false for an async task.
/magichour/image-generator?prompt=TEXTParams: image_url, prompt, aspect_ratio (default original), optional wait.
/magichour/image-editor?image_url=IMAGE_URL&prompt=TEXTCheck a queued generation task.
/magichour/image-generator/status/TASK_IDGuest voice cloning from a public reference audio URL.
Uploads generated audio to Catbox (Uguu fallback) and returns its hosted result_url/audio_url. Add response=audio for the raw MP3/WAV response. Optional ref_text, speed, guidance_scale, output_format.
/saydi/voice-cloner?audio_url=URL&text=TEXTGenerate speech with a Saydi preset. Pass the exact sample name from /saydi/voices or saydi-voices.txt. Optional guidance_scale (1-4, default 2.8), speed (0.5-2, default 1), duration (0-600), breaks, and output_format (mp3, wav, flac, ogg).
/saydi/text-to-speech?text=TEXT&sample=SAMPLE_NAMEReturns direct binary audio when response=audio; otherwise returns hosted JSON with result_url/audio_url. The /saydi/tts path is an alias.
/saydi/text-to-speech?text=TEXT&sample=SAMPLE_NAME&output_format=mp3&response=audioBrowse the 1,014 live samples. Optional language/lang, gender, use_case/useCase, search, page, and limit filters.
/saydi/voices?language=en&gender=female&use_case=conversationalHealth and temporary result endpoints.
View live proxy and service-pool health.
/statusRetrieve a temporary image result.
/clipsnap/result/RESULT_IDCompatibility aliases and extra image tools.
Params: image_url, prompt, model, aspect_ratio, resolution.
/photo-editor?image_url=IMAGE_URL&prompt=TEXTParams: image_url, prompt, model, aspect_ratio, resolution.
/image-to-image?image_url=IMAGE_URL&prompt=TEXTParams: prompt and provider-specific JSON body options.
/ezmaker/image-generator?prompt=TEXTParams: image_url and expansion sides in pixels.
/image-extender?image_url=IMAGE_URL&left=200&right=200Params: image_url, blur_strength/blur (default 50).
/clipsnap/background-blur?image_url=IMAGE_URLParams: image_url, mode (general_v1, general_v2, logo, text, anime, custom).
/ezremove/background-remover?image_url=IMAGE_URL