Models
The models, with their prices.
Every model below runs in the same studio with the same credits. The price shown is the starting price; the exact number for your settings is on the Generate button.
AI video generatorAI image generatorAI music, voice and soundKling pricingNano Banana pricingCompare AI studios
Video · 106
- Veo 3.1Googlefrom 200 crGoogle's flagship video model: lifelike motion, native dialogue and sound, up to 4K.Text to videoImage to videoStart and end frameNative audio
- Veo 3.1 ReferenceGooglefrom 400 crVeo 3.1 from up to 3 reference images: 8-second shots with native dialogue and sound, up to 4K.ReferencesNative audio
- Veo 3.1 FastGooglefrom 100 crVeo 3.1 quality at a fraction of the price and wait, with native audio.Text to videoImage to videoStart and end frameNative audio
- Kling 3.0 ProKuaishoufrom 84 crKling's top tier: cinematic motion up to 15 seconds with native audio and start/end frames.Text to videoImage to videoStart and end frameNative audio
- Kling 3.0 StandardKuaishoufrom 63 crKling 3.0 at a lower price: the same controls as Pro with lighter detail.Text to videoImage to videoStart and end frameNative audio
- Seedance 2.0ByteDancefrom 135 crMulti-shot storytelling with native audio, start/end frames and up to 9 reference images.Text to videoImage to videoStart and end frameReferences
- Wan 2.6Alibabafrom 125 crAlibaba's open video model: up to 15 seconds at 1080p with automatic multi-shot cuts.Text to videoImage to video
- Hailuo 2.3MiniMaxfrom 70 crExpressive characters and physics at 768p, in 6 or 10 second clips.Text to videoImage to video
- Hailuo 2.3 ProMiniMaxfrom 123 crHailuo 2.3 at 1080p for sharper detail.Text to videoImage to video
- Veo 3.1 LiteGooglefrom 30 crVeo 3.1 at its lowest price: native audio, 720p or 1080p, for drafts and volume.Text to videoImage to videoStart and end frameNative audio
- Veo 3.1 ExtendGooglefrom 350 crContinues a Veo video by 7 seconds, keeping its look, motion and sound.Extend videoNative audio
- Veo 3.1 Fast ExtendGooglefrom 175 crContinues a Veo video by 7 seconds at Veo 3.1 Fast prices.Extend videoNative audio
- Kling 3.0 4KKuaishoufrom 315 crKling 3.0 rendered natively in 4K, with audio, up to 15 seconds.Text to videoImage to videoStart and end frameNative audio
- Kling 3.0 Turbo ProKuaishoufrom 105 crKling 3.0 in about half the time, up to 15 seconds.Text to videoImage to video
- Kling 3.0 Turbo StandardKuaishoufrom 84 crKling 3.0 in about half the time, up to 15 seconds.Text to videoImage to video
- Kling O3 ProKuaishoufrom 84 crKling's omni model: one engine for text, start and end frames and up to four reference images.Text to videoImage to videoStart and end frameReferences
- Kling O3 StandardKuaishoufrom 63 crKling's omni model: one engine for text, start and end frames and up to four reference images.Text to videoImage to videoStart and end frameReferences
- Kling O3 4KKuaishoufrom 315 crKling's omni model in native 4K: text, a start and end frame, or up to seven reference images.Text to videoImage to videoStart and end frameReferences
- Kling 2.6 ProKuaishoufrom 88 crKling 2.6 with native audio and start/end frames, in 5 or 10 seconds.Text to videoImage to videoStart and end frameNative audio
- Kling 2.5 Turbo ProKuaishoufrom 88 crFast, fluid Kling 2.5 motion at 1080p, with start and end frames.Text to videoImage to videoStart and end frame
- Kling 2.5 Turbo StandardKuaishoufrom 53 crKling 2.5 Turbo from a still image at 720p, at the lowest Kling price.Image to video
- Kling 2.1 MasterKuaishoufrom 350 crKling 2.1's top tier: rich motion and strong prompt adherence at 1080p.Text to videoImage to video
- Kling 2.1 ProKuaishoufrom 123 crKling 2.1 at 1080p from a start frame, with an optional end frame.Image to videoStart and end frame
- Kling 2.1 StandardKuaishoufrom 70 crKling 2.1 at 720p from a still image.Image to video
- Kling 1.6 ProKuaishoufrom 123 crThe classic Kling 1.6 at 1080p, with start and end frames.Text to videoImage to videoStart and end frame
- Kling 3.0 Motion Control ProKuaishoufrom 42 cr / sYour character performs the moves of a reference video: dance, acting, gestures, up to 30 seconds.Motion control
- Kling 3.0 Motion Control StandardKuaishoufrom 32 cr / sYour character performs the moves of a reference video: dance, acting, gestures, up to 30 seconds.Motion control
- Kling 2.6 Motion Control ProKuaishoufrom 28 cr / sKling 2.6 motion transfer: your character performs the moves of a reference video, up to 30 seconds.Motion control
- Kling 2.6 Motion Control StandardKuaishoufrom 18 cr / sKling 2.6 motion transfer: your character performs the moves of a reference video, up to 30 seconds.Motion control
- Kling O3 Reference Video ProKuaishoufrom 126 crNew shots that follow the motion and camera style of your video, with up to 4 reference images.References
- Kling O3 Reference Video StandardKuaishoufrom 95 crNew shots that follow the motion and camera style of your video, with up to 4 reference images.References
- Kling O3 Reference Video 4KKuaishoufrom 315 crNew shots in native 4K that follow the motion and camera style of your video, with up to 4 reference images.References
- Seedance 2.5ByteDancefrom 221 crByteDance's newest video model: up to 30 seconds with native audio, frames and up to 16 reference images.Text to videoImage to videoStart and end frameReferences
- Seedance 2.0 FastByteDancefrom 108 crSeedance 2.0 at a lower price and wait, in 480p or 720p, with up to 9 reference images and 3 audio clips.Text to videoImage to videoStart and end frameReferences
- Seedance 2.0 MiniByteDancefrom 68 crThe lightest Seedance 2.0: native audio and references at the lowest price.Text to videoImage to videoStart and end frameReferences
- Seedance 1.5 ProByteDancefrom 12 crSeedance 1.5 with synchronized audio and start/end frames, up to 12 seconds.Text to videoImage to videoStart and end frameNative audio
- Seedance 1.0 ProByteDancefrom 12 crSeedance 1.0 Pro: crisp 1080p motion from text or a start frame, 2 to 12 seconds.Text to videoImage to videoStart and end frame
- Seedance 1.0 Pro FastByteDancefrom 5 crSeedance 1.0 Pro in a fraction of the time and price.Text to videoImage to video
- Hailuo 2.3 FastMiniMaxfrom 48 crHailuo 2.3 from a still image in less time, 6 or 10 seconds at 768p.Image to video
- Hailuo 2.3 Fast ProMiniMaxfrom 83 crHailuo 2.3 Fast at 1080p, 6 seconds from a still image.Image to video
- Hailuo 02MiniMaxfrom 68 crMiniMax Hailuo 02 at 768p: strong physics and motion, 6 or 10 seconds.Text to videoImage to videoStart and end frame
- Hailuo 02 ProMiniMaxfrom 120 crHailuo 02 at 1080p, 6 seconds, with start and end frames.Text to videoImage to videoStart and end frame
- MiniMax H3MiniMaxfrom 63 crMiniMax H3: native audio, frames, an audio track to follow and references (5 images, 3 videos, 3 audio clips), up to 4K.Text to videoImage to videoStart and end frameReferences
- MiniMax H3 MaxMiniMaxfrom 63 crMiniMax's flagship H3 Max: cinematic motion and audio at up to 1080p, with an optional audio track to follow.Text to videoImage to videoStart and end frameNative audio
- MiniMax H3 Max TurboMiniMaxfrom 32 crH3 Max at half the price and wait, with an optional audio track to follow.Text to videoImage to videoStart and end frameNative audio
- MiniMax H3 Max Talking PhotoMiniMaxfrom 13 cr / sA photo speaks your audio with H3 Max, lips in sync, up to 15 seconds and 2K.Talking photo
- MiniMax H3 Max Turbo ExtendMiniMaxfrom 7 crContinues a video by up to 15 seconds with H3 Max Turbo, up to 2K.Extend videoNative audio
- Wan 2.7Alibabafrom 50 crAlibaba's Wan 2.7: up to 15 seconds at 1080p, with start and end frames and an optional audio to follow.Text to videoImage to videoStart and end frame
- Wan 2.5Alibabafrom 63 crWan 2.5 in 5 or 10 seconds, from 480p to 1080p, with optional background music.Text to videoImage to video
- Wan 3.0Alibabafrom 25 crAlibaba's Wan 3.0: up to 30 seconds with native audio, frames and up to 10 reference images.Text to videoImage to videoStart and end frameReferences
- Wan 3.0 PrimeAlibabafrom 34 crWan 3.0 at its highest quality, with native audio, up to 30 seconds.Text to videoImage to videoStart and end frameReferences
- Wan 2.6 ReferenceAlibabafrom 125 crNew shots from Wan 2.6 that keep the subjects of up to 3 reference videos.References
- Wan 2.2 Animate MoveAlibabafrom 15 cr / sAnimates the character of an image with the motion and expressions of a video.Motion control
- Wan 2.2 Animate ReplaceAlibabafrom 15 cr / sSwaps the person in a video for the character of an image, keeping the scene and the motion.Motion control
- Grok ImaginexAIfrom 13 crxAI's video model with native sound, up to 15 seconds at 720p.Text to videoImage to videoNative audio
- Grok Imagine ReferencexAIfrom 13 crGrok Imagine from up to 7 reference images: 1 to 10 seconds with native sound, at 480p or 720p.ReferencesNative audio
- Grok Imagine 1.5xAIfrom 20 crGrok Imagine 1.5: sharper motion and sound, up to 1080p.Text to videoImage to videoNative audio
- Grok Imagine 1.5 ReferencexAIfrom 23 crGrok Imagine 1.5 from up to 7 reference images: up to 15 seconds with native sound, at 480p or 720p.ReferencesNative audio
- Grok Imagine 1.5 LitexAIfrom 5 crGrok Imagine 1.5 at a fraction of the price, up to 1080p.Text to videoImage to videoNative audio
- Gemini Omni FlashGooglefrom 98 crGoogle's omni video model: text, a start frame or up to 10 references, 3 to 10 seconds at 720p.Text to videoImage to videoReferencesNative audio
- Gemini Omni Flash 1.1Googlefrom 23 crGemini Omni Flash 1.1: from 360p drafts to 4K, with frames and up to 10 image and 3 video references.Text to videoImage to videoStart and end frameReferences
- FLUX 3 VideoBlack Forest Labsfrom 213 crBlack Forest Labs' video model: up to 20 seconds with audio, up to 4K.Text to videoImage to videoStart and end frameNative audio
- FLUX 3 Max VideoBlack Forest Labsfrom 213 crFLUX 3 Max: reasoning before rendering for complex scenes, up to 20 seconds at 1080p.Text to videoImage to videoStart and end frameNative audio
- FLUX 3 Video ExtendBlack Forest Labsfrom 513 crContinues a clip of up to 15 seconds by 5 to 20 seconds with FLUX 3, with audio, at 720p or 1080p.Extend videoNative audio
- Happy HorseAlibabafrom 105 crAlibaba's Happy Horse: lively characters from text, a photo or up to 9 references.Text to videoImage to videoReferences
- Happy Horse 1.1Alibabafrom 105 crHappy Horse 1.1: consistent characters from up to 9 references, cheaper at 1080p.Text to videoImage to videoReferences
- LTX 2.3 ProLightricksfrom 120 crLightricks LTX 2.3 at 1080p to 4K, with audio, in 6 to 10 seconds.Text to videoImage to videoStart and end frameNative audio
- LTX 2.3 FastLightricksfrom 90 crLTX 2.3 in less time, up to 20 seconds.Text to videoImage to videoStart and end frameNative audio
- LTX 2.5 ProLightricksfrom 180 crLightricks LTX 2.5 at its best quality, with audio and camera moves.Text to videoImage to videoStart and end frameNative audio
- LTX 2.5 FastLightricksfrom 135 crLTX 2.5 in less time, up to 20 seconds and 4K.Text to videoImage to videoStart and end frameNative audio
- Luma Ray 3.2Luma AIfrom 125 crLuma's Ray 3.2: physically plausible motion and lighting, 5 or 10 seconds up to 1080p.Text to video
- Luma Ray 3.2 FramesLuma AIfrom 38 crLuma Ray 3.2 from a start frame, or a start and end frame, in 5 seconds.Image to videoStart and end frame
- Kling O3 Video Edit ProKuaishoufrom 42 cr / sRewrites a video with a prompt and up to 4 reference images: swap subjects, restyle, keep the motion.Video to video
- Kling O3 Video Edit StandardKuaishoufrom 32 cr / sRewrites a video with a prompt and up to 4 reference images: swap subjects, restyle, keep the motion.Video to video
- Kling O3 Video Edit 4KKuaishoufrom 105 cr / sRewrites a video in native 4K with a prompt and up to 4 reference images, keeping the motion.Video to video
- Grok Imagine Video EditxAIfrom 15 cr / sEdits up to 8 seconds of video from a prompt, at 480p or 720p.Video to video
- Wan 2.7 Video EditAlibabafrom 25 cr / sRestyles or edits a 2 to 10 second video from a prompt and an optional reference image, at 720p or 1080p.Video to video
- Happy Horse Video EditAlibabafrom 70 cr / sEdits a video from a prompt, keeping its motion, up to 15 seconds, guided by up to 5 reference images.Video to video
- Gemini Omni Flash 1.1 EditGooglefrom 8 cr / sEdits a video with Google's omni model, from 360p to 4K, up to 10 seconds.Video to videoNative audio
- FLUX 3 Video EditBlack Forest Labsfrom 8 cr / sFast FLUX 3 edits of clips under 15 seconds, at 720p.Video to video
- LTX 2.3 ReframeLightricksfrom 25 cr / sReframes a video up to 60 seconds to another aspect ratio, filling the new area, at 720p or 1080p.Video to video
- Luma Ray 3.2 ReframeLuma AIfrom 15 cr / sReframes a clip up to 10 seconds to a new aspect ratio, painting the new area from your prompt.Video to video
- Luma Ray 3.2 EditLuma AIfrom 180 crRestyles or edits a video with Ray 3.2 into 5 or 10 seconds up to 1080p, optionally from a new first frame.Video to video
- MiniMax H3 Max RecastMiniMaxfrom 75 cr / sReplaces the people of a 5 to 30 second video with up to 4 people from your photos, keeping the scene and sound.Video to videoNative audio
- MiniMax H3 Max RelightMiniMaxfrom 13 cr / sRelights a video up to 15 seconds to match a sphere render of the lighting you want.Video to video
- Topaz Video UpscaleTopaz Labsfrom 3 cr / sUpscales a video 2x or 4x with Topaz Proteus, keeping its length, sound and frame rate.Upscale
- SeedVR2 Video UpscaleByteDancefrom 4 cr / sByteDance's SeedVR2 for video: temporally consistent 1.5x to 4x upscales, up to 4K, priced by the frame.Upscale
- Topaz Video PrecisionTopaz Labsfrom 3 cr / sTopaz's precision upscalers: Iris for faces, Artemis for clean footage, Dione for interlaced video.Upscale
- Topaz Starlight Precise 2.6Topaz Labsfrom 30 cr / sTopaz's generative upscaler: rebuilds detail in low-quality and old footage.Upscale
- Topaz Astra 2Topaz Labsfrom 75 cr / sTopaz Astra 2: creative upscaling that invents fine texture, for AI and low-resolution video.Upscale
- FLUX Video UpscalerBlack Forest Labsfrom 21 cr / sBlack Forest Labs' video upscaler: faithful 1.5x to 3x upscales up to 4K, for clips up to 20 seconds.Upscale
- Sync Lipsync 2.0Sync Labsfrom 13 cr / sRe-syncs the lips of any video to a new audio track: dubbing, dialogue fixes, UGC ads.Lip sync
- Sync Lipsync 2.0 ProSync Labsfrom 21 cr / sLipsync 2.0 with finer detail on teeth and beards, for close-ups.Lip sync
- Sync Lipsync 3Sync Labsfrom 34 cr / sSync's most accurate lip sync, for any face, angle and language.Lip sync
- Sync 3 AvatarSync Labsfrom 34 cr / sSync 3 animates the face in a photo, illustration or cartoon to lip-sync your audio.Talking photo
- OmniHuman 1.5ByteDancefrom 40 cr / sA photo and a voice track become a person talking and gesturing in sync, up to a minute long.Talking photo
- OmniHuman 2ByteDancefrom 27 cr / sByteDance's newest talking-photo model: natural expressions and body motion for 4 seconds to 5 minutes of audio.Talking photo
- HeyGen Avatar IVHeyGenfrom 25 cr / sHeyGen's photo avatar: lifelike lip sync, head motion and expressions from a single photo.Talking photo
- Kling AI Avatar 2.0 StandardKuaishoufrom 15 cr / sKling's talking avatar from one photo and an audio, at an affordable price.Talking photo
- Kling AI Avatar 2.0 ProKuaishoufrom 29 cr / sKling's talking avatar at its best quality: sharper faces and more natural motion.Talking photo
- VEED Fabric 1.0VEEDfrom 20 cr / sAny photo, cartoon or product shot talks with your audio, in 480p or 720p.Talking photo
- VEED Fabric 1.0 FastVEEDfrom 25 cr / sFabric 1.0 in less time, at a higher price per second.Talking photo
- Creatify AuroraCreatifyfrom 18 cr / sStudio-grade talking avatars for ads and explainers, from a photo and an audio.Talking photo
- HeyGen Translate PrecisionHeyGenfrom 25 cr / sTranslates a video into another language with the speaker's own voice and matching lip sync.Video translation
- HeyGen Translate SpeedHeyGenfrom 13 cr / sHeyGen's video translation at half the price, for drafts and quick turnarounds.Video translation
- ElevenLabs DubbingElevenLabsfrom 150 cr / minDubs a video into another language, keeping each speaker's voice, with speakers detected automatically.Video translation
Image · 52
- Nano Banana ProGooglefrom 38 crGoogle's best image model: reasoning, accurate text and edits with up to 14 references.Text to imageImage to imageEditReferences
- Nano Banana 2Googlefrom 15 crFast, affordable Google image generation and editing from 512px to 4K, from up to 14 images, a video or an audio clip.Text to imageImage to imageEditReferences
- GPT Image 2OpenAIfrom 3 crOpenAI's image model: strongest prompt adherence and readable text inside images.Text to imageImage to imageEditReferences
- Seedream 4.5ByteDancefrom 10 crHigh-resolution images up to 4K with consistent multi-reference editing, at a low flat price.Text to imageImage to imageEditReferences
- FLUX.1 Kontext ProBlack Forest Labsfrom 10 crPrecise instruction-based edits that keep the rest of the image intact.Text to imageImage to imageEdit
- SeedVR2 UpscaleByteDancefrom 3 crRestores detail and upscales any image to 1080p, 1440p or 4K.Upscale
- Topaz UpscaleTopaz Labsfrom 20 crTopaz Labs upscaling 2x or 4x: sharper detail and restored faces, with the image otherwise unchanged.Upscale
- Clarity UpscalerClarityAIfrom 53 crUpscales and sharpens, restoring skin and texture detail, up to 4x.Upscale
- Crystal UpscalerClarityAIfrom 28 crUltra-sharp, crystal-clear upscaling up to 4x.Upscale
- Remove BackgroundBriafrom 5 crCuts the background out of an image, leaving the subject on transparency.Remove background
- Nano BananaGooglefrom 10 crThe original Nano Banana: fast, consistent edits and generations at a flat price.Text to imageImage to imageEditReferences
- Nano Banana 2.1Googlefrom 11 crGoogle's newest Nano Banana: sharper detail and text, up to 4K.Text to imageImage to imageEditReferences
- GPT Image 2.5 SunburstOpenAIfrom 3 crOpenAI's GPT Image 2.5, Sunburst variant: up to 4K, with five quality levels.Text to imageImage to imageEditReferences
- GPT Image 2.5 FlareOpenAIfrom 3 crOpenAI's GPT Image 2.5, Flare variant: up to 4K, with five quality levels.Text to imageImage to imageEditReferences
- GPT Image 1.5OpenAIfrom 9 crOpenAI's GPT Image 1.5: reliable text in images and faithful edits.Text to imageImage to imageEditReferences
- GPT Image 1OpenAIfrom 6 crThe original GPT Image: strong instruction following and edits.Text to imageImage to imageEditReferences
- GPT Image 1 MiniOpenAIfrom 5 crGPT Image at a fraction of the price, for drafts and volume.Text to imageImage to imageEditReferences
- Seedream 5.0 ProByteDancefrom 17 crByteDance's best Seedream: rich detail, accurate text and multi-image edits up to 2K.Text to imageImage to imageEditReferences
- Seedream 5.0 LiteByteDancefrom 9 crSeedream 5.0 at a low flat price, up to 4K.Text to imageImage to imageEditReferences
- Seedream 5.0 FlashByteDancefrom 7 crThe fastest Seedream 5.0, at 2K.Text to imageImage to imageEditReferences
- Seedream 4.0ByteDancefrom 8 crSeedream 4.0: consistent generations and edits up to 4K at a low price.Text to imageImage to imageEditReferences
- FLUX.2 ProBlack Forest Labsfrom 8 crFLUX.2 Pro: photoreal images and precise multi-reference edits, priced by megapixel.Text to imageImage to imageEditReferences
- FLUX.2 FlexBlack Forest Labsfrom 13 crFLUX.2 Flex: the best FLUX.2 for typography and fine detail.Text to imageImage to imageEditReferences
- FLUX.2 MaxBlack Forest Labsfrom 18 crThe most capable FLUX.2: highest fidelity and prompt adherence.Text to imageImage to imageEditReferences
- FLUX.2 DevBlack Forest Labsfrom 3 crFLUX.2's open model: good quality at a very low price.Text to imageImage to imageEditReferences
- FLUX.2 TurboBlack Forest Labsfrom 2 crFLUX.2 in a few seconds, for drafts and variations.Text to imageImage to imageEditReferences
- FLUX.2 FlashBlack Forest Labsfrom 2 crThe fastest, cheapest FLUX.2.Text to imageImage to imageEditReferences
- FLUX 1.1 Pro UltraBlack Forest Labsfrom 15 crFLUX 1.1 Pro at up to 4 megapixels, for large prints and backdrops, from text or guided by one image.Text to imageImage to imageEdit
- FLUX.1 Kontext MaxBlack Forest Labsfrom 20 crKontext at its most capable: stronger prompt adherence and typography in edits.Text to imageImage to imageEdit
- FLUX 3 ImageBlack Forest Labsfrom 12 crBlack Forest Labs' FLUX 3 for images: precise edits with up to 10 references.Text to imageImage to imageEditReferences
- Ideogram 3.0Ideogramfrom 8 crIdeogram 3.0: the best text and layouts in images, for posters and logos, and remixes of one image.Text to imageImage to imageEdit
- Ideogram 4.5Ideogramfrom 8 crIdeogram's newest model: crisp typography and edits with up to 4 references.Text to imageImage to imageEditReferences
- Recraft V4.1Recraftfrom 9 crRecraft V4.1: design-grade images, brand colors and clean composition.Text to image
- Recraft V4.1 ProRecraftfrom 53 crRecraft V4.1 at high resolution for print and large formats.Text to image
- Recraft V4.1 UtilityRecraftfrom 9 crRecraft V4.1 tuned for icons, product shots and UI assets.Text to image
- Recraft V4 StylesRecraftfrom 10 crGenerates in the style of up to 10 reference images: your brand look, on any subject.Image to imageEditReferences
- Wan 2.2 ImageAlibabafrom 7 crAlibaba's open Wan 2.2 for images, at a very low price.Text to image
- Wan 2.6 ImageAlibabafrom 8 crWan 2.6 for images and edits with several references.Text to imageImage to imageEditReferences
- Wan 2.7 Pro ImageAlibabafrom 19 crWan 2.7 Pro: detailed images and edits from Alibaba.Text to imageImage to imageEditReferences
- Grok Imagine ImagexAIfrom 5 crxAI's image model: fast and cheap, for text to image and edits.Text to imageImage to imageEditReferences
- Grok Imagine Image 2.0xAIfrom 10 crGrok Imagine Image 2.0: sharper detail and text, up to 2K, edits with up to 5 images.Text to imageImage to imageEditReferences
- Kling Image 3.0Kuaishoufrom 7 crKling's image model: cinematic stills and edits of one image, at a low price.Text to imageImage to imageEdit
- Kling Image O3Kuaishoufrom 7 crKling's omni image model: generations and multi-image edits up to 4K.Text to imageImage to imageEditReferences
- Kling O1 ImageKuaishoufrom 7 crKling O1: edits that keep the people and products of your reference images.Image to imageEditReferences
- Krea 2 LargeKreafrom 15 crKrea's own model at its best: photographic and artistic images with a strong look, or in the style of up to 10 images.Text to imageImage to imageEditReferences
- Krea 2 MediumKreafrom 8 crKrea 2 at half the price, for faster iterations, with up to 10 style images.Text to imageImage to imageEditReferences
- Luma Uni-1Luma AIfrom 11 crLuma's image model: natural light and composition, edits with up to 9 images.Text to imageImage to imageEditReferences
- Meta Muse ImageMetafrom 3 crMeta's Muse image model: quick images and edits with up to 10 references, at a cent each.Text to imageImage to imageEditReferences
- Qwen Image 3Alibabafrom 10 crAlibaba's Qwen Image 3: precise text rendering and instruction edits, 1K or 2K.Text to imageImage to imageEditReferences
- Z-Image TurboTongyi-MAIfrom 2 crPhotorealistic images and image-to-image edits in seconds, at a fraction of a cent per megapixel.Text to imageImage to imageEdit
- Hunyuan Image 3.0Tencentfrom 25 crTencent's Hunyuan Image 3.0: rich scenes and long prompts, with instruction edits.Text to imageImage to imageEditReferences
- Krea 3Kreafrom 7 crKrea 3: reasoning image model for generations and edits with up to 8 references.Text to imageImage to imageEditReferences
Audio · 16
- ElevenLabs Audio DubbingElevenLabsfrom 150 cr / minDubs a podcast, voiceover or any recording into another language, keeping each speaker's voice.Video translation
- ElevenLabs v3ElevenLabsfrom 5 cr / 1K charsThe most expressive ElevenLabs voice model, with audio tags for emotion and delivery.Text to speech
- ElevenLabs MusicElevenLabsfrom 150 crStudio-quality songs from a description, up to 5 minutes, with vocals or instrumental only.Text to music
- Lyria 3 ProGooglefrom 20 crGoogle's music model: full songs with vocals from one prompt, lyrics included, optionally inspired by an image, at a flat price.Text to music
- ElevenLabs Sound EffectsElevenLabsfrom 1 crSound effects and ambiences from a short description, up to 22 seconds, optionally as a seamless loop.Sound effects
- ElevenLabs Multilingual v2ElevenLabsfrom 5 cr / 1K charsElevenLabs' most stable voice model, natural in 29 languages, for narration and voiceovers.Text to speech
- MiniMax Speech 02 HDMiniMaxfrom 5 cr / 1K charsMiniMax's high-fidelity voices, expressive in over 30 languages.Text to speech
- Lyria 3Googlefrom 10 crGoogle's Lyria 3: a short music track from a description, or inspired by an image, at a flat price.Text to music
- ElevenLabs Voice ChangerElevenLabsfrom 2 cr / sSpeaks your recording again in another voice, keeping its timing, emotion and delivery.Voice changer
- MiniMax Music 2.6MiniMaxfrom 38 crComplete songs with singing and arrangement from a style description and your own lyrics, or an instrumental.Text to music
- ACE-StepACE Studiofrom 2 crFast, affordable songs from a style and optional lyrics, 30 seconds to 4 minutes.Text to music
- Stable Audio 3Stability AIfrom 10 crInstrumental tracks and soundscapes cleared for commercial use, from a few seconds to about six minutes.Text to music
- Stem SplitterMetafrom 1 cr / sSplits a song into six tracks: vocals, drums, bass, guitar, piano and the rest.Stem separation
- ACE-Step RemixACE Studiofrom 1 cr / sSings or plays your track again in a new style, keeping its melody, or changes only its lyrics.Music editing
- ACE-Step ExtendACE Studiofrom 1 crContinues your track for up to 90 more seconds in the style you describe.Music editing
- ACE-Step ReplaceACE Studiofrom 1 cr / sGenerates one stretch of your track again, from and to the second you choose, keeping the rest.Music editing