SuperAPI AI Directory
Partner with us中文AI newsFavorites

AI video

2,204 results · Page 31 of 62

PicMovi

AI video

PicMovi is an AI photo-to-video tool that converts static photos into MP4 video clips in about 60 seconds. Users upload a photo and enter a prompt to generate short videos with camera movement and action effects. The platform integrates multiple video generation models such as Seedance 2.5, Veo 3.1, Kling 2.5, Wan 2.7, MiniMax H3, and Hailuo, which can be selected based on speed, realism, or style. It supports workflows such as image-to-video and picture-to-video, and can complete photo animation within the same workflow. The generated videos can be exported in aspect ratios suited for TikTok, Reels, Shorts, and product pages, making them suitable for scenarios such as social media content, marketing ads, YouTube B-roll, and e-commerce product videos. Registration comes with starter credits, and paid plans provide larger generation volumes.

Read more

Pixo

AI video

DanseAI is an AI video generation tool that turns two photos of people into the "Alors on Danse" white studio keyboard meme video. Upload two photos, each containing one person: Photo 1 replaces the performer on the left playing the mini keyboard, and Photo 2 replaces the performer on the right responsible for hyping up the crowd and the close-up shots. No prompt writing is needed. The video length is 5 to 30 seconds, supports vertical 9:16 or horizontal 16:9, up to 1080p, includes the soundtrack from the original reference clip, and outputs an MP4 with audio. Optional Seedance 2.0 Mini / 2.0 Fast / 2.0 / 2.5 and MiniMax H3 models are available; different models differ in duration, resolution, likeness, and credit consumption. Generation usually takes a few minutes. Free accounts carry a moving watermark, and any paid plan removes the watermark.

Read more

Pixo

AI video

Pixo is an online Opus 5.5 video generator where users simply enter a text prompt, and Claude Opus 5.5 handles storyboard planning, animation code writing, and preview frame checking, ultimately rendering a 1080p MP4 video with sound, with a duration of 15, 30, or 60 seconds. No software installation or API key is required, and it supports three aspect ratios: 16:9, 9:16, and 1:1, with up to 15 images (such as logos, product images, screenshots, or photos) attachable for the model to reference. For audio, it supports music, uploaded audio, optional narration, or silence. Billing uses a pay-as-you-go model, with charges incurred only during the actual generation process, and failed videos are refunded. This tool is suitable for creating product launch videos, motion graphics, explainer animations, kinetic typography, animated charts, and short social ad videos, among other motion graphics content centered on the precise presentation of text, numbers, and typography.

Read more

Pixo

AI video

Pixo (Bulin 47 AI) is a browser-based AI face-swap video tool that replaces a single photo uploaded by the user into the viral freestyle videos of Bulin 47 and Kevin Wai. After the user uploads a clear frontal photo, the AI model follows the original footage frame by frame, preserving the rap movements, handheld camera work, crowd, and original dembow sound effects. It supports 5, 10, 15 seconds and the full 19 seconds, 9:16 vertical format, 480p to 1080p, and can be used in the browser on iPhone, Android, or a laptop without installing an app. It uses one-time credit packs, starting at $4.99, and credits are refunded for failed videos.

Read more

Pixo

AI video

Pixo (TryH3) is a standalone AI video creation workflow built around the MiniMax H3 model. Users can generate videos of 4–15 seconds, up to native 2K resolution, with synchronized audio, via text prompts, first-frame images, or multimodal reference materials. The platform offers multiple creation paths including text-to-video, image-to-video, reference-to-video, video continuation, video editing, and beat-synced video, supports six aspect ratios: 16:9, 9:16, 1:1, 4:3, 3:4, and 21:9, and emphasizes character consistency. It also aggregates models such as MiniMax H3, Seedance, Kling, Grok, Gemini Omni, and Wan, sharing a single credit balance. Generation typically takes 1–3 minutes, failed tasks automatically refund credits, and videos generated with paid or credit packs include commercial licensing.

Read more

Pixo

AI video

Genjutsu AI is a reference-image-guided video-to-video editing tool that, based on an existing clip, replaces characters, clothing, products, or backgrounds in the video, or redraws the overall visual style, by uploading up to nine reference images and describing the desired changes in one sentence, while preserving the original motion, camera movement, and duration as much as possible. It is powered by Seedance 2.5, Seedance 2.0 (Standard, Fast, Mini), and MiniMax H3, supports uploading or using built-in clips, offers MP4 output from 480p to 1080p, and preserves the source audio. This tool is an independent product, not affiliated with Higgsfield; you must use footage you have the right to edit, new accounts receive 3 free credits, and videos made without purchasing a plan carry a watermark.

Read more

Pixo

AI video

Genjutsu AI is a standalone AI video generation tool, mainly used to create cinematic videos, vertical short videos, and product ads. Users can generate videos from text descriptions, or upload a single photo or reference video for character replacement and motion transfer: after selecting an effect, the system replaces the person in the photo into the original video scene, maintaining the same motion, background, and camera movement, and a publish-ready final clip can be obtained within minutes. The tool supports text-to-video, first-and-last-frame video, and character replacement. All modes share one prepaid balance, billed by model, duration, and resolution, with no subscription required. Videos are output in 9:16 vertical format by default, suitable for TikTok, Reels, and Shorts, and can be switched to 16:9 or 1:1 with one click. Registration, browsing templates, and opening examples are free; generation requires using prepaid balance, with first-time packages starting at $4.90, and failed generations automatically refund the deducted balance.

Read more

Pixo

AI video

Pixo is an online AI video generation tool, featuring the Hotel Lobby AI video template. Users upload two clear portrait photos to generate a video of two people singing "Hotel Lobby" together in an orange COLORS studio. The video retains the original song's audio, requires no prompt writing, and needs no green screen. It supports three durations: 5, 10, and 15 seconds, offers different model outputs at 720p and 1080p, and allows downloading MP4 files for publishing on platforms such as TikTok, Reels, or Shorts. New accounts receive trial credits, free videos come with a watermark, paid plans can remove the watermark, and credits are automatically refunded if generation fails.

Read more

Pixo

AI video

Pixo is a Raindance AI video generation tool that turns two separate photos into a two-person performance video set on a seaside pier. Users upload two photos, corresponding to the two characters: one seated at the opening and one who walks into frame and appears in most of the close-ups, with no filming or prompt writing required. You can choose the duration, model (Seedance 2.5 or MiniMax H3), and resolution, and the required credits are shown before generation. The finished MP4 includes a reference audio track. The tool provides template scenes, camera moves, and performances, supports 5, 10, and 15 seconds (Seedance 2.5 supports 30 seconds), is billed using site credits, has a dynamic watermark for free accounts, unlocks the watermark-free original after purchase, and refunds credits for failed tasks.

Read more

Plot Party

AI video

Plot Party is an AI-generated interactive story and series video creation tool provided by Plot Party. Users can use it to turn ideas into cinematic reality and create, share, and explore interactive stories, worlds, and series. The platform focuses on AI micro-drama and story video generation, capable of generating high-quality storyboards with consistent characters, style, scenes, and assets in under 5 minutes. Built-in AI agents help users choose the right model for their ideas, and canvas creation tools are provided for continuously building and adjusting stories. The built-in editor supports trimming, adding subtitles, and video polishing. Users can generate a fully visualized storyboard from an idea in 10 minutes, including AI-generated scenes, characters, and dialogue; they can also build and publish series works while maintaining character consistency across multiple stories. Users can also share stories, build communities, and let audiences explore the worlds they create. Entering "/" can attach a skill (only one per run), and Canvas Copilot will confirm with the user step by step until the final film is completed.

Read more

Poko Motion

AI video

Poko Motion (Poko) is an AI video production tool that turns code repositories, websites, documents, slides, and raw recordings with narration into finished motion videos. It reads real source materials, automatically builds the storyline, generates storyboards, and preserves the user's original voice while adding product proof, intelligent recomposition, and motion graphics. The project's script, scenes, voiceover, and editing all remain editable locally, and the final MP4 is rendered on the user's own macOS or Windows computer with no cloud queue. Users can direct the edit directly in natural language, for example adjusting the pace of the opening, showing product footage earlier, or changing the ending. Poko supports multiple model access methods including GPT models (via Poko credits), bring your own API key (BYOK), and local gateways, and offers plans for different needs such as free starter, personal, creator/freelancer, and team/agency, with the free plan including 2 active projects and $10 in AI credits, no credit card required.

Read more

PoseVid

AI video

PoseVid is an AI visual creation workshop, focused on turning text into images, generating cinematic videos, and performing refined editing and processing on photos. The platform offers generation features such as text-to-image, text-to-video, image-to-video, and text-to-image then to video, and includes more than 14 built-in image tools, including background removal, AI object eraser, watermark removal, color adjustment, image expansion, old photo restoration, black-and-white colorization, AI outfit change, hairstyle change, expression modification, age change, gender swap, AI makeup, ID photo creation, and more. In addition, it offers more than 437 style templates that can transform photos into artistic styles such as cartoon, 3D, Pixar, Van Gogh, and more. The tools are aimed at content creators, graphic designers, character design, brands, and animation and game practitioners, and are claimed to be one-click operations requiring no design skills. The official offering includes free account registration and a free usage tier, while paid plans are tiered according to creative needs; specific prices and benefits must be checked on the official pricing page, and subscriptions can be canceled at any time.

Read more