HappyHorse 1.1 Image to Video: Full Model Guide
HappyHorse 1.1 image-to-video (happyhorse-1.1-i2v) animates a still image into a smooth HD clip. Your upload becomes the exact first frame; a short motion prompt steers what happens next. It's the model behind the txtovid image-to-video generator.
Specifications at a glance
- Model ID: happyhorse-1.1-i2v (first-frame image-to-video)
- Image input: JPEG, JPG, PNG, BMP, WEBP — max 20 MB
- Image size: every edge ≥ 300 px; aspect ratio between 2:5 and 5:2
- Output: 720P ($0.14/s list) and 1080P ($0.18/s list) + flat $0.05/s platform fee
- Output aspect ratio follows the input image
- Durations: 3, 5, 8, 10 or 15 seconds — renders in 1–5 minutes
First-frame animation, explained
Unlike text-to-video, where the model invents everything, i2v anchors generation to your image: subject identity, framing, palette and lighting are preserved while the model synthesizes coherent motion forward in time. That makes it the precision tool for brand assets, portraits and artwork where the look is non-negotiable.
The output resolution tier (720P/1080P) sets the total pixel budget; the model picks the closest valid render size to your image's aspect ratio, so a 4:5 portrait stays a 4:5 portrait.
Getting the best results
Use sharp source images with a clear subject and describe only the motion in your prompt — camera movement, subject action, atmosphere. If your image violates the size rules, txtovid's upload editor crops (16:9, 9:16 or 1:1), scales and compresses it client-side before upload, so nothing gets rejected.