wan-2-5/image-to-video
Generate clips with fluid motion and audios for creatives
Happy Horse 1.1 reference to video is the reference-driven mode of Alibaba's natively multimodal video model. Instead of starting from a blank prompt, you hand it one or more reference images and a text description, and the model generates a short clip that carries the subject, style, or composition you provided while adding motion and synchronized sound in a single pass.
This mode shares the same architecture as the rest of the Happy Horse 1.1 family, so it keeps believable, physically grounded motion, rich light and shadow, and cinematic camera work such as push-ins, pull-outs, and rack-focus shifts. It holds character identity across the clip and renders a range of looks, from photoreal footage to stylized animation.
This release refines the earlier 1.0 generation: action that used to feel sluggish now carries more pace and weight, and the model handles a wider range of subjects, including Asian faces, with steadier likeness and fewer morphing artifacts.
Output format: Resolution: 720P or 1080P / fps: 24 / duration: 3-15s / aspect ratio: 16:9, 9:16, 1:1 / audio: included
Generate clips with fluid motion and audios for creatives
Edit a precise segment of an audio track while preserving the rest
Text-driven video transformation keeping motion and style consistent across edits.
Unified AI model for refined scene editing, style match, and smooth video refits
Transform one video into another style with Tencent Hunyuan Video.
Generate cinematic videos from text prompts with Wan 2.1.
Happy Horse 1.1 reference to video generates a short clip built around reference images you supply, so the subject, style, or composition you provide carries into the result. It suits character-consistent scenes, product reveals, and brand-style clips where you need motion that stays faithful to a specific look rather than starting from a text prompt alone.
The text-to-video mode builds a clip from a prompt only, while Happy Horse 1.1 reference to video lets you anchor the output with up to 9 reference images before adding motion. This makes it the better choice when identity, product appearance, or a particular visual style needs to stay consistent across the video.
Compared with the earlier 1.0 release, Happy Horse 1.1 reference to video delivers livelier motion pacing, fewer morphing artifacts, and steadier likeness across a wider range of subjects, including Asian faces. Based on publicly available information, action that previously felt sluggish now carries more weight and momentum.
Yes. Happy Horse 1.1 reference to video produces synchronized audio, such as dialogue, ambient sound, and Foley, jointly with the picture in a single pass. This removes the need for a separate sound design step and keeps the audio aligned with on-screen action.
You can supply up to 9 reference images, with the first one acting as the primary anchor. Add more only when each contributes something distinct, such as a second subject or a style cue; check the current RunComfy parameter panel for the exact accepted formats and limits.
Happy Horse 1.1 reference to video outputs 720P or 1080P clips between 3 and 15 seconds, at 16:9, 9:16, or 1:1 aspect ratio. Pick 720P to iterate cheaply and 1080P for final delivery; limits may vary by mode or provider settings.
Yes. You can prototype Happy Horse 1.1 reference to video in the RunComfy AI Playground Web UI, then call the same model via the RunComfy API with identical parameters for automation and production. This keeps your tested settings consistent between prototyping and integration.
Happy Horse 1.1 reference to video is billed by output duration and resolution: $0.13 per second for 720P and $0.16 per second for 1080P. A 5-second 720P clip is about $0.65 and a 5-second 1080P clip is about $0.80; generations draw from your RunComfy credits, and new users typically start with a free trial amount.
RunComfy is the premier ComfyUI platform, offering ComfyUI online environment and services, along with ComfyUI workflows featuring stunning visuals. RunComfy also provides AI Models, enabling artists to harness the latest AI tools to create incredible art.
