OpenAI · Image
GPT Image 2.5
Create and edit images with GPT Image 2.5 in the KiwiMotion Studio.
- Text to Image
- Image to Image
Flare · Sunburst
Opening KiwiMotion…
KiwiMotion
Explore the AI image, video, voice and avatar models available in KiwiMotion. Open any model directly in its supported Studio, compare workflows, and discover examples, prompts and guides for models with dedicated KiwiMotion content.
OpenAI · Image
A precision-focused image family for both prompt generation and multi-reference editing, especially when the instruction has several constraints that must remain coherent.
Image model
A flexible everyday image family that moves naturally between text creation and reference-guided transformations in the unified Create Image workspace.
Image model
Create detailed images from text or edit an uploaded reference in KiwiMotion.
Image model
A fast text-to-image option for turning concise art direction into visual drafts without waiting on a heavier reference-edit workflow.
Image model
A detailed prompt-aware image family with both generation and edit paths, useful when scene structure and written direction need to stay explicit.
Image model
A quick expressive image family for both fresh generations and reference edits, with a useful balance between speed and visual experimentation.
Image model
Kling's current image family combines V3 text generation with an O3 reference-edit path for detailed scenes and image-led transformations.
Video model
A cinematic video family exposed as Standard and Pro tiers in both text-to-video and image-to-video workflows.
Kling 3.0 Standard · Kling 3.0 Pro
Featured Fashion Walk · 10 seconds · 16:9
Explore real pairs covering human motion, hair and mirror detail, and cat-and-phone interaction. The posters below are from the verified Fashion Walk pair.
Compare Standard vs Pro →Video model
A polished cinematic Kling option available in current text-to-video and image-to-video selectors.
Video model
A fast Pro image-to-video model for turning a source frame into cinematic movement.
Video model
A reference-oriented Kling family spanning the current keyframes/reference workflow and Kling O3 video editing.
Kling O3 Standard Reference · Kling O3 Pro Edit
Video model
KiwiMotion's higher-quality Veo option across text, image, and keyframe video workflows, with audio controls where the active mode supports them.
Video model
A faster Veo 3.1 tier for text-to-video and image-to-video work when iteration speed matters.
Video model
A current Seedance family with synchronized-audio text generation and a separate reference/keyframe mode, grouped into one useful family page.
Seedance 2.5 Text to Video · Seedance 2.5 Reference to Video
Video model
A fast social-video model available in KiwiMotion's current Text to Video selector.
Video model
A value-oriented Seedance option available in both text-to-video and image-to-video workflows.
Video model
A creative video family available from both text and image inputs, with distinct style and edit/extend paths elsewhere in the Studio.
PixVerse V6 Generation · PixVerse V6 Extend
Video model
A coherent prompt-video family that spans current text, image, and WAN Remix video-edit workflows.
WAN 2.7 Generation · WAN Remix
Video model
An image-led cinematic video family with current keyframe, edit, and extend options represented in KiwiMotion's video workflows.
Grok Imagine Video 1.5 · Grok Imagine Edit · Grok Imagine Extend
Video model
An audio-ready Alibaba video family available from text, image, and keyframe/reference workflows, with a separate source-video edit mode.
Happy Horse 1.1 Generation · Happy Horse Video Edit
Video model
A prompt-directed Google video family exposed across text, image, and keyframe workflows, with a separate conversational edit action.
Gemini Omni Flash Generation · Gemini Omni Flash Edit
Video model
A Pro image-to-video model with audio and high-resolution options in the current KiwiMotion selector.
Video model
A focused image-to-video option for turning a still into short 5- or 10-second motion clips.
Video model
An image-to-video family grouped around Fast Pro and Pro variants for efficient or higher-quality 1080p motion.
Hailuo 2.3 Fast Pro · Hailuo 2.3 Pro
AI image models create from text or edit user-provided references when supported.
AI video models generate motion from a prompt, an image, or other supported source media.
Voice workflows turn text into speech or create a reusable voice from authorized audio.
Avatar workflows create a reusable identity or animate a selected avatar with audio.
Start with the workflow: image or video, new creation or editing. Check whether your task needs references, then compare the available speed, fidelity, and model-specific settings inside Studio. The controls shown for the selected model are the source of truth for supported inputs and output options.
