New This Month
42 models added in the last 30 days · 14 new this week
Retexture
Meshy · Oct 8
Generate new textures for an existing 3D model or a prior Meshy task from a text style prompt or a style image.
Vidu Q4 Image to Video
Vidu · Oct 8
Animate a start frame into a 3 to 16 second clip with native audio, preserving the subject and composition of your image. Direct motion, camera cuts and spoken dialogue in the prompt. 540p up to 4K.
Vidu Q4 Reference to Video
Vidu · Oct 8
Build a 3 to 16 second scene from up to 12 reference images and 3 voice clips, keeping characters, products and voices consistent. Optional native audio with dialogue and sound effects, five aspect ratios, 540p up to 4K.
MiniMax H3 Max Relight
MiniMax · Oct 8
Change the lighting of a video from a lighting-sphere image: color, direction and shadow softness. Keeps the subjects, setting, motion, camera and audio. Source up to 15 seconds, 480p to 2K.
Kandinsky 6.0 Lite Image-to-Video
Kandinsky Lab · Oct 6
Fast, low-cost image animation from Kandinsky Lab: a 5-second clip with synchronized audio that keeps your start frame's composition and identity. Good for product shots and social content at scale.
Kandinsky 6.0 Lite
Kandinsky Lab · Oct 6
Fast, low-cost text-to-video from Kandinsky Lab: smooth 5-second clips with synchronized audio, built for drafts and high-volume work. Understands English and Russian.
Kandinsky 6.0 Pro Image-to-Video
Kandinsky Lab · Oct 6
Animate a start frame into a cinematic 5-second clip with synchronized audio, preserving the subject, style and composition. Kandinsky Lab's flagship model.
Kandinsky 6.0 Pro
Kandinsky Lab · Oct 6
Kandinsky Lab's flagship text-to-video model: cinematic 5-second clips with synchronized audio, camera moves, and strong adherence to long structured prompts. Understands English and Russian.
Kandinsky 6.0 VSR
Kandinsky Lab · Oct 6
Upscale and restore video with sharper detail and stable, flicker-free frames. Works on generated and real footage; pairs with Kandinsky 6.0 drafts. Clips are capped at about 5 seconds.
Kandinsky 6.0 VSR Lite
Kandinsky Lab · Oct 6
Fast, low-cost video upscaling for previews and high-volume pipelines. Lower latency than Kandinsky 6.0 VSR, with slightly less detail. Clips are capped at about 5 seconds.
MiniMax H3 Max Turbo Extend Video
MiniMax · Oct 6
Continue an existing clip with 1 to 15 seconds of new footage you describe, faster and cheaper than H3 Max Extend. Optional audio references, 480p to 2K, and the choice of the whole extended video or only the new part.
MiniMax H3 Max Recast
MiniMax · Oct 6
Replace the people in a video with people from your photos, keeping the original motion, gestures, camera, cuts and soundtrack. One photo per new person, up to four. Source video 5 to 30 seconds, 768p or 1080p.
Nano-Banana 2.1
Google · Oct 6
Google's high-efficiency image model. Generates from a prompt at up to 4K, can search the web for reference, and costs roughly a quarter of Nano-Banana Pro.
Nano-Banana 2.1 Edit
Google · Oct 6
Edit images by describing the change. Upload up to 14 references to blend or restyle, at up to 4K. The same model as Nano-Banana 2.1, pointed at image editing.
Grok Imagine 1.5 Lite Image-to-Video
Grok · Oct 2
Animate an image into a video with audio using Grok Imagine 1.5 Lite, a faster and lower-cost tier of Grok Imagine 1.5.
Grok Imagine 1.5 Lite Text-to-Video
Grok · Oct 2
Generate videos with audio from a text prompt using Grok Imagine 1.5 Lite, a faster and lower-cost tier of Grok Imagine 1.5.
Flux 3 Image Edit (Direct)
Black Forest Labs · Oct 1
Edit, restyle, recolor, or combine up to 10 reference images with FLUX 3, served directly by Black Forest Labs. Place elements precisely with bounding boxes in the prompt.
Flux 3 Image (Direct)
Black Forest Labs · Oct 1
Generate images from a text prompt with FLUX 3, served directly by Black Forest Labs. Supports up to 4K output and optional web/image grounding.
MiniMax H3 Max Insert Video
MiniMax · Oct 1
Drop a new scene into the middle of an existing video. Pick where it starts and where the original picks up again, describe what happens, and get back the whole video with the new footage spliced in. Only the new scene is billed.
Pixelcut Looping Video
Pixelcut · Oct 1
Turn one product photo into a seamless loop that starts and ends on the same frame. The camera stays locked; pick gentle ambient motion or a full 360 degree spin. 5 to 15 seconds, up to 1080p.
VEED Clean Audio
Veed · Oct 1
Strip background noise out of a recording while keeping quiet and distant speech intact. Takes any audio or video file up to 30 minutes and returns loudness-normalised 48 kHz audio. The same model behind Clean Audio in the VEED editor.
Generate (4.5)
Ideogram · Oct 1
Generate an image from a prompt with Ideogram 4.5, or supply up to 5 reference images (and an optional mask) to edit or restyle them.
Precise Edit (4.5)
Ideogram · Oct 1
Edit an image with Ideogram 4.5 while keeping every pixel you did not ask to change. Output matches the source image size exactly.
Gemini 3.8 Flash-Lite TTS
Google · Sep 25
Fast, low-cost text-to-speech from Google, built for volume: read-aloud features, voice agents and everyday single-speaker narration. 101 languages, detected automatically. Google's named replacement for Gemini 3.1 Flash TTS.
Gemini 3.8 Flash TTS
Google · Sep 25
Google's flagship text-to-speech model. Studio-grade voice quality with real acting range, authentic regional accents, and a steady voice across long narrations. Over 130 languages, detected automatically.
MiniMax H3 Max 3D to Video
MiniMax · Sep 24
Turn a Blender render or 3D previs into photorealistic video. Your clip drives the scene layout, camera moves and edit timing; add reference images to pin down how characters, objects and sets should look. Up to 15 seconds, 480p to 1080p.
MiniMax H3 Max Extend Video
MiniMax · Sep 24
Continue an existing clip with new footage you describe. Upload a video of 1.6 to 60 seconds, say what happens next, and get back either the whole extended video or just the new part. 5 to 15 seconds of new footage, 480p to 2K.
PixVerse VibeMV
PixVerse · Sep 24
Turn a track into a music video. Upload an MP3 or WAV from 10 seconds to 6 minutes, pick a visual style, and optionally add a character reference and lyrics as subtitles. The video runs the full length of your audio, at 720p or 1080p.
MiniMax H3 Max Styles
MiniMax · Sep 24
Generate stylised video with sound from a prompt, in one of five looks: VHS tape, 1970s hand-painted cartoon, retro low-poly 3D, hand-drawn pencil, or 16-bit pixel art. Add a first frame to carry your own artwork into the shot. 5 to 15 seconds at 768p.
Image to 3D · Tripo P2
Tripo 3D · Sep 24
Tripo P2 (model P2-20260801) is the next-gen P-series 3D model: native quad-mesh output (up to 25,000 quads, or 50,000 triangles), sharper PBR textures than P1, and closer adherence to the source image. Dispatched through Tripo's newer v3 API.
Text to 3D · Tripo P2
Tripo 3D · Sep 24
Tripo P2 (model P2-20260801) is the next-gen P-series 3D model: native quad-mesh output (up to 25,000 quads, or 50,000 triangles), sharper PBR textures than P1, and closer adherence to your prompt. Dispatched through Tripo's newer v3 API.
Seedream 5 Flash Edit
Bytedance · Sep 24
Fast, low-cost image editing with Bytedance's Seedream 5.0 Flash model. Accepts up to 10 reference images.
Seedream 5 Flash Layerize
Bytedance · Sep 24
Decompose an image into a base image plus independently editable layers with Bytedance's Seedream 5.0 Flash model.
Seedream 5 Flash
Bytedance · Sep 24
Fast, low-cost image generation with Bytedance's Seedream 5.0 Flash model, built for workflows where speed and budget matter.
Recraft V4.1 Flash
Recraft · Sep 24
Fast, low-cost Recraft V4.1 Flash text-to-image generation for photography, illustration, and mixed-media compositions.
MiniMax H3 Max Lip Sync
MiniMax · Sep 19
Animate a portrait so its mouth matches a soundtrack you supply, using MiniMax H3 Max. The clip length follows your audio, from 5 up to 14.8 seconds. 480p to 2K.
Sound Effects
Pixio · Sep 14
Generate a sound effect or ambience from a text description, up to 30 seconds. Describe what it should sound like, list what to avoid, and tune steps and guidance strength. Free on every paid plan.
Speaker Separation
Pixio · Sep 14
Put every speaker in a conversation on their own track, up to four voices. Upload audio to get one audio track per speaker, or upload a video and each speaker comes back as that video carrying only their voice. Only the speakers actually found are returned. Free on every paid plan.
Text to Speech
Pixio · Sep 14
Turn a script into natural speech, with optional zero-shot voice cloning. Add a 10 to 30 second reference clip and the voice comes with it; Whisper transcribes the clip for you. Inline tags like [whisper], [laughing] or [excited] steer delivery. WAV output. Free on every paid plan.
Dialog, Effects & Music Splitter
Pixio · Sep 14
Pull a mix apart into three tracks: dialog, sound effects and background music. Upload audio to get three audio tracks, or upload a video and each track comes back as that video carrying only its sound. Dialog is the main result; effects and music are saved alongside it. Free on every paid plan.
Speech to Text
Pixio · Sep 14
Transcribe speech with Whisper large-v3. Upload a recording in MP3, WAV, FLAC, M4A or OGG and get the spoken words back as plain text. The language is detected automatically across 80+ languages. Free on every paid plan.
Video Soundtrack
Pixio · Sep 14
Score a silent video. Describe what it should sound like and the clip comes back as the same video carrying its new audio. Generation is capped at 30 seconds of sound. Free on every paid plan.