Des modèles d'image, de vidéo, de 3D, de voix et d'audio issus des meilleurs laboratoires. Comparez les prix et essayez-les tous avec un seul solde.
PhotoPas cherOur own fast text-to-image renderer: a 0.5K JPEG draft in seconds, at the lowest price in the catalog. Text in, picture out, no reference images or prompt enhancement.
PhotoGoogle's Nano Banana 2.1 is the latest Nano Banana text-to-image model, with gains in visual design, subject consistency and prompt adherence, 1K to 4K output and optional web search grounding.
PhotoGoogle Nano Banana 2.1 Edit is the latest Nano Banana image editing model, with gains in visual design, subject consistency and prompt adherence, up to 14 reference images and 1K to 4K output.
PhotoOpenAI's GPT Image 2.5 Flare Text-to-Image generates high-quality images from natural-language prompts, with five quality tiers up to 4K. Flare is the fast, balanced GPT Image 2.5 tier for everyday generation at low latency.
PhotoOpenAI's GPT Image 2.5 Flare Edit edits one or more reference images from natural-language instructions, with five quality tiers up to 4K. Flare is the fast, balanced GPT Image 2.5 tier for everyday generation at low latency.
PhotoOpenAI's GPT Image 2.5 Sunburst Text-to-Image generates high-quality images from natural-language prompts, with five quality tiers up to 4K. Sunburst is the precision-focused GPT Image 2.5 tier that spends more time per image for extra fidelity on intricate detail.
PhotoOpenAI's GPT Image 2.5 Sunburst Edit edits one or more reference images from natural-language instructions, with five quality tiers up to 4K. Sunburst is the precision-focused GPT Image 2.5 tier that spends more time per image for extra fidelity on intricate detail.
VidéoAnimate a portrait image from an audio recording with Seedance 2.5. Generate talking-avatar videos in 480p or 720p, processing up to the first 120 seconds of audio.
VidéoSeedance 2.5 (Image-to-Video) generates Hollywood-grade cinematic videos from reference images and text prompts with native audio-visual synchronization, director-level camera and lighting control, and exceptional motion stability.
VidéoTransfer the motion of a reference video onto a character with Seedance 2.5. Your character, from a picture or a short description, performs the same movements, gestures and camera motion as the video, in 480p, 720p or 1080p for up to 30 seconds.
VidéoSeedance 2.5 (Video-Edit) edits an input video from a natural-language prompt. The reference video drives subject identity, composition, and motion while the model rewrites lighting, style, weather, environment, or specific elements as instructed.
VidéoSeedance 2.5 (Video-Edit Turbo) is the turbo tier for editing an input video from a natural-language prompt - faster, more affordable high-resolution output while preserving subject identity, composition, and motion.
VidéoSeedance 2.5 (Video-Extend) extends an input video with a new cinematic continuation generated from its last frame and a natural-language prompt.
VidéoSeedance 2.5 (Text-to-Video) generates Hollywood-grade cinematic videos from text prompts with native audio-visual synchronization, director-level camera and lighting control, and exceptional motion stability.
VidéoAlibaba WAN 3.0 Prime Reference-to-Video combines reference images, videos, and audio with prompts to create coherent videos with flexible 2-30 second duration, resolution, aspect ratio, audio, and deep-thinking controls.
VidéoWan 3.0 Prime Video Extend continues a video from its final frame and appends a newly generated 2-30 second segment. Inputs longer than 120 seconds retain their last 120 seconds. Supports 480p, 720p, and 1080p output.
VidéoAlibaba WAN 3.0 Prime Image-to-Video converts a first-frame image into a video with optional last-frame guidance, flexible 2-30 second duration, resolution, aspect ratio, audio, and deep-thinking controls.
VidéoWan 3.0 Prime Video-Edit edits an input video using a text prompt and optional reference images and audio. Inputs longer than 15 seconds are trimmed to the first 15 seconds. Output aspect ratio is explicitly selected from the input display dimensions automatically.
VidéoAlibaba WAN 3.0 Prime Text-to-Video generates videos from text prompts with flexible 2-30 second duration, resolution, aspect ratio, audio, and deep-thinking controls.
VidéoAlibaba WAN 3.0 Prime Spicy Image-to-Video converts a first-frame image into a video with optional last-frame guidance, flexible 2-30 second duration, resolution, aspect ratio, audio, and deep-thinking controls.
VidéoSeedance 2.5 Spicy (Image-to-Video) generates unlimited high-quality cinematic clips from a reference image and prompt, optimized for scalable content generation with smooth animations and stable aesthetics.
VidéoAlibaba WAN 3.0 Image-to-Video converts a first-frame image into a video with optional last-frame guidance, flexible 2-30 second duration, resolution, aspect ratio, audio, and deep-thinking controls.
VidéoWan 3.0 Video-Edit edits an input video using a text prompt and optional reference images and audio. Inputs longer than 15 seconds are trimmed to the first 15 seconds. Output aspect ratio is explicitly selected from the input display dimensions automatically.
VidéoAlibaba WAN 3.0 Text-to-Video generates videos from text prompts with flexible 2-30 second duration, resolution, aspect ratio, audio, and deep-thinking controls.
VidéoAlibaba WAN 3.0 Reference-to-Video combines reference images, videos, and audio with prompts to create coherent videos with flexible 2-30 second duration, resolution, aspect ratio, audio, and deep-thinking controls.
VidéoWan 3.0 Video Extend continues a video from its final frame and appends a newly generated 2-30 second segment. Inputs longer than 120 seconds retain their last 120 seconds. Supports 480p, 720p, and 1080p output.
VidéoAlibaba WAN 3.0 Spicy Image-to-Video converts a first-frame image into a video with optional last-frame guidance, flexible 2-30 second duration, resolution, aspect ratio, audio, and deep-thinking controls.
VidéoSeedance 2.5 (Image-to-Video Turbo) generates cinematic 720p/1080p videos from reference images and text prompts - a faster, more affordable high-resolution tier with native audio-visual synchronization, director-level control, and exceptional motion stability.
VidéoSeedance 2.5 (Text-to-Video Turbo) generates cinematic videos from text prompts at 720p and 1080p with native audio-visual synchronization, director-level camera and lighting control, and exceptional motion stability - optimized for turbo output.
PhotoSeedream 5.0 Pro API Preview Edit is ByteDance's advanced image editing model for single-image and multi-reference image generation.
PhotoSeedream 5.0 Pro API Preview is ByteDance's advanced image generation model for text-to-image and reference-image generation.
PhotoSeedream 5.0 Flash Edit is ByteDance's fast, lower-cost image editing model for single-image and multi-reference image generation.
PhotoSeedream 5.0 Flash is ByteDance's fast, lower-cost image generation model for text-to-image generation.
PhotoQwen Image 3.0 text-to-image model with high-quality image generation and advanced prompt understanding.
PhotoQwen Image 3.0 Pro text-to-image model with professional-grade quality and advanced prompt understanding.
VidéoGenerate a short video from a text prompt with xAI Grok Imagine Video v1.5.
VidéoGenerate a short video from up to seven reference images with xAI Grok Imagine Video v1.5.
PhotoQwen Image 3.0 Pro edit model with professional-grade editing quality and advanced instruction understanding.
VidéoTransform an input image into a short video with xAI Grok Imagine Video v1.5.
PhotoQwen Image 3.0 edit model with high-quality image editing and advanced instruction understanding.
PhotoGrok Imagine Image V2.0 Edit transforms up to three input images according to a text prompt with configurable resolution and quality.
PhotoGrok Imagine Image V2.0 Text to Image generates images from text prompts with configurable aspect ratio, resolution, and quality.
VidéoText-to-image generation with FLUX.3 is Black Forest Labs' frontier video model. This endpoint generates video directly from a text prompt, translating a written description into motion, composition, and scene. .
VidéoText-to-image generation with FLUX.3 is Black Forest Labs' frontier video model. This endpoint generates video directly from a text prompt, translating a written description into motion, composition, and scene. .
VidéoText-to-image generation with FLUX.3 is Black Forest Labs' frontier video model. This endpoint generates video directly from a text prompt, translating a written description into motion, composition, and scene. .
VidéoText-to-image generation with FLUX.3 is Black Forest Labs' frontier video model. This endpoint generates video directly from a text prompt, translating a written description into motion, composition, and scene. .
VidéoMiniMax H3 is a 2K image-to-video model that animates a first-frame image with natural-language motion and scene instructions, with optional last-frame control.
VidéoMiniMax H3 is a 2K reference-to-video model that combines reference images, videos, and audio with natural-language instructions to create coherent video scenes.
VidéoMiniMax H3 is a 2K text-to-video model that generates coherent videos from natural-language prompts with flexible duration and aspect-ratio controls.
VidéoSeedance 2.0 Mini is ByteDance's faster, lower-cost tier of Seedance 2.0 for cinematic multi-shot video - narrative sequences, AI camera control (zoom/pan/tracking), and consistent characters across scenes, from text or image prompts. 720p-1080p, 5-12s, aspect ratios 16:9 / 4:3 / 1:1 / 3:4 / 9:16.
VidéoPruna P-Video-2-Pro text-to-video generation at 480p or 768p, with generated audio.
VidéoReference-guided video generation with images, videos, and audio, at 480p or 768p.
VidéoSeedance 2.0 Mini is ByteDance's faster, lower-cost tier of Seedance 2.0 for cinematic multi-shot video - narrative sequences, AI camera control (zoom/pan/tracking), and consistent characters across scenes, from text or image prompts. 480p-4k, 4-15s, aspect ratios 16:9 / 4:3 / 1:1 / 3:4 / 9:16.
VidéoPruna P-Video-2 text-to-video generation with explicit duration, resolution, draft mode, and audio output.
VidéoPruna P-Video-2 image-to-video generation with explicit duration, resolution, draft mode, and audio output.
VidéoSeedance 2.0 Mini is ByteDance's faster, lower-cost tier of Seedance 2.0 for cinematic multi-shot video - narrative sequences, AI camera control (zoom/pan/tracking), and consistent characters across scenes, from text or image prompts. 480p-4k, 4-15s, aspect ratios 16:9 / 4:3 / 1:1 / 3:4 / 9:16.
VidéoPruna P-Video-2-Pro image-to-video with optional last-frame guidance generation at 480p or 768p, with generated audio.
VidéoSeedance 2.0 Mini is ByteDance's faster, lower-cost tier of Seedance 2.0 for cinematic multi-shot video - narrative sequences, AI camera control (zoom/pan/tracking), and consistent characters across scenes, from text or image prompts. 720p-1080p, 5-12s, aspect ratios 16:9 / 4:3 / 1:1 / 3:4 / 9:16.
VidéoAlibaba Happy Horse 1.0 (Reference-to-Video) generates new video scenes guided by reference images, maintaining consistent characters, styles, and visual identity. Smooth camera movement and expressive, stable motion.
VidéoAlibaba Happy Horse 1.0 (Video Edit) performs prompt-driven video editing with multi-image reference support, supporting 720p/1080p output. Smooth, context-aware edits while preserving motion and temporal consistency.
Les prix s'entendent par rendu et ne sont prélevés sur votre solde que si le rendu aboutit. Les rendus échoués sont remboursés automatiquement. Le prix exact s'affiche avant la génération.