About MiniMax Models
MiniMax is a leading provider of advanced AI media models, featuring Hailuo for high-fidelity multimodal video generation and editing.
All MiniMax Models
Image to Video
minimax/minimax-s2v-01
[Core Function] MiniMax S2V-01 is a Subject-to-Video generation model. [Strengths] It excels at maintaining strict identity consistency of a specific subject (provided via reference images) while generating a video of that subject performing actions described in a text prompt. [Best For] Highly recommended for: character-consistent storytelling, generating multiple videos with the same actor, and brand mascot animation. [Limitations] Do NOT use this model if you just want to animate the provided image exactly as it is (use standard I2V). This model generates *new* scenes featuring the referenced subject. [Routing] Use this model when the user provides reference images of a character/subject and wants a video of them doing a specific new action based on a text prompt.
minimax/hailuo-02-fl2v
[Core Function] Hailuo 02 FL2V is a First-Last frame transition video model. [Strengths] It excels at generating a logical, physically accurate video transition that bridges a provided starting frame and an ending frame. [Best For] Highly recommended for: visual morphing, before-and-after transitions, and precise narrative storyboard completion. [Limitations] Do NOT use this model if you only have one image (use standard I2V instead). Note that Hailuo 2.3 does not support FL2V, so this is the primary transition model. [Routing] Use this model exclusively when the user provides BOTH a first frame and a last frame for a transition.
minimax/minimax-i2v-01
[Core Function] MiniMax I2V-01 is a legacy image-to-video model. [Strengths] Standard image-to-video generation maintained for backward compatibility. [Best For] Recommended only for: maintaining existing integrations. [Limitations] Do NOT use this model for new creations. It is superseded by the Hailuo series. [Routing] Only use this if the user explicitly requests the legacy 'I2V-01' model.
minimax/minimax-i2v-01-live
[Core Function] MiniMax I2V-01-Live is a legacy image-to-video model optimized for anime and stylized art. [Strengths] Originally designed for fast, stylized animation, particularly for 2D illustration and anime styles. [Best For] Recommended for: specific legacy integrations that relied on the 'Live' anime aesthetics. [Limitations] Do NOT use this model for general generation. The new Hailuo 2.3 model has fully absorbed and improved upon these stylization capabilities. [Routing] Only use this if the user explicitly requests the 'Live' model. For anime/stylized art, use Hailuo 2.3 I2V instead.
minimax/minimax-i2v-01-director
[Core Function] MiniMax I2V-01-Director is a legacy image-to-video model with explicit camera controls. [Strengths] It allows direct manipulation of virtual camera movements (pan, zoom, tilt) applied to a starting image. [Best For] Recommended for: legacy systems requiring explicit camera parameter inputs. [Limitations] Do NOT use this model for general video generation; it is an older architecture with lower physical realism than the Hailuo series. [Routing] Only use this if the user explicitly requests the 'Director' model or legacy 'I2V-01' generation. Otherwise, default to Hailuo 2.3 I2V.
minimax/hailuo-02-i2v
[Core Function] Hailuo 02 I2V is an image-to-video model optimized for physical realism and sustained high resolution. [Strengths] It excels at animating broad scenes, maintaining complex physics, and supporting native 1080p generation for up to 10 seconds. [Best For] Highly recommended for: animating product photography, bringing landscape/nature photos to life, and generating physically accurate motion. [Limitations] Do NOT use this model for animating complex human facial micro-expressions or highly stylized anime art, where Hailuo 2.3 is superior. [Routing] Use this model when the user needs to animate a landscape/product, or explicitly requires 10 seconds of 1080p video. Otherwise, default to Hailuo 2.3 I2V.
minimax/hailuo-2.3-fast-i2v
[Core Function] Hailuo 2.3 Fast I2V is a high-speed, cost-effective image-to-video generation model. [Strengths] It excels at generating videos from images much faster and at roughly 50% lower cost than the standard 2.3 model, while still maintaining the 2.3 architecture's strength in human motion. [Best For] Highly recommended for: rapid prototyping, batch social media creation, and cost-sensitive video generation pipelines. [Limitations] Do NOT use this model for text-to-video (it only accepts image inputs). Do NOT use when absolute maximum visual fidelity is the primary requirement. [Routing] Choose this model when the user emphasizes 'fast', 'quick', or 'cost-effective' image-to-video generation. For maximum quality, use the standard Hailuo 2.3 I2V.
minimax/hailuo-2.3-i2v
[Core Function] Hailuo 2.3 I2V is a flagship image-to-video generation model optimized for character animation. [Strengths] It excels at animating human characters from a single image, maintaining consistent facial features, producing natural micro-expressions, and handling stylized artwork seamlessly. [Best For] Highly recommended for: animating character concept art, bringing portraits to life, and creating stylized/anime motion sequences. [Limitations] Do NOT use this model for last-frame conditioning (it does not support FL2V). Do NOT use if you need 1080p resolution for 10 seconds (1080p is capped at 6s). [Routing] Use this model by default for high-quality image-to-video tasks involving people or art. For physical realism or 10s at 1080p, route to Hailuo 02 I2V. For cost-effective/faster generation, route to Hailuo 2.3 Fast I2V.
Text to Video
minimax/minimax-t2v-01
[Core Function] MiniMax T2V-01 is a legacy text-to-video model. [Strengths] Standard text-to-video generation maintained for backward compatibility. [Best For] Recommended only for: maintaining existing integrations that specifically require the T2V-01 endpoint. [Limitations] Do NOT use this model for new creations. It lacks the physical realism of Hailuo 02 and the human performance/stylization of Hailuo 2.3. [Routing] Only use this if the user explicitly requests the legacy 'T2V-01' model. Otherwise, default to Hailuo 2.3.
minimax/minimax-t2v-01-director
[Core Function] MiniMax T2V-01-Director is a legacy text-to-video model with explicit camera controls. [Strengths] It natively accepts explicit camera movement commands (pan, zoom, tilt) alongside the text prompt. [Best For] Recommended for: legacy workflows that specifically rely on the Director-mode camera parameters. [Limitations] Do NOT use this model for general video generation, as it is an older architecture superseded by Hailuo 2.3 and 02. [Routing] Only use this if the user explicitly requests the 'Director' model or legacy 'T2V-01' generation. Otherwise, default to Hailuo 2.3.
minimax/hailuo-02-t2v
[Core Function] Hailuo 02 T2V is a text-to-video generation model optimized for physical realism. [Strengths] It excels at complex physics simulation, fluid dynamics, broad cinematic scenes, and natively rendering 1080p video up to 10 seconds without downscaling. [Best For] Highly recommended for: product commercials, high-speed sports action, nature documentaries, and sweeping landscapes. [Limitations] Do NOT use this model for highly stylized anime/art or nuanced human micro-expressions, where Hailuo 2.3 performs better. [Routing] Route to this model when the user requests '1080p for 10 seconds', complex physical action (like splashing water or crashes), or broad landscapes. For human characters and stylization, use Hailuo 2.3 T2V.
minimax/hailuo-2.3-t2v
[Core Function] Hailuo 2.3 T2V is a flagship text-to-video generation model optimized for human performance and stylization. [Strengths] It excels at capturing intricate human motion, nuanced facial micro-expressions, prompt adherence, and applying highly stylized aesthetics (e.g., anime, ink wash, game CG) to video. [Best For] Highly recommended for: character-driven storytelling, close-up emotional shots, stylized artistic videos, and dialogue scenes. [Limitations] Do NOT use this model if you need native 1080p resolution for 10 full seconds (1080p is capped at 6 seconds; generating 10s forces 768p resolution). [Routing] Use this model by default for text-to-video requests involving humans, faces, or specific art styles. If the user requires strict physical realism/world dynamics or native 1080p for 10 seconds, route to Hailuo 02 T2V instead.
Image Editing
minimax/minimax-image-01-live-i2i
[Core Function] MiniMax Image-01-Live I2I is a fast image-to-image generation model. [Strengths] It is optimized for rapid generation and style variations, particularly suited for stylized art and anime workflows. [Best For] Highly recommended for: quick style iterations, anime variations, and fast prototyping. [Limitations] Do NOT use this model if you need the absolute highest fidelity or complex physical reasoning, where the standard Image-01 model performs better. [Routing] Choose this model when speed or stylized/anime aesthetics are the primary priority for an image-to-image task.
minimax/minimax-image-01-i2i
[Core Function] MiniMax Image-01 I2I is an image-to-image editing and variation model. [Strengths] It excels at generating new images based on a text prompt while structurally referencing one or more input images. [Best For] Highly recommended for: style transfer, generating variations of existing artwork, and structurally guided image creation. [Limitations] Do NOT use this model if you want to generate video or if you do not have a reference image. [Routing] Use this model when the user provides a reference image and a text prompt to generate a new image.
