Overview
What is Fabric 1.0?
Fabric 1.0 is a VEED model available in Starpop. Turn any image into a talking video with lip-synced audio. A portrait-animation model for creating talking-head video from a still image and an audio track.
Provide a clear, front-facing source image and clean speech audio, then select the resolution that fits the publishing destination. Starpop keeps the model, input mode, duration, format, resolution, and credit choices in one workspace so a team can move from a first test to a publishable asset without rebuilding the brief in another tool.
Specifications
Available in Starpop
These values come from Starpop’s live model configuration and can change as providers add or remove capabilities.
- Inputs
- Image, Audio
- Durations
- Determined by source media
- Aspect ratios
- Determined by source media
- Output options
- 480p, 720p
- Estimated credits
- 1–2 credits
- Typical generation time
- About 20 minutes
Best uses
When to choose Fabric 1.0
Provide a clear, front-facing source image and clean speech audio, then select the resolution that fits the publishing destination.
- 01Talking-head content from a single portrait
- 02Localized spokesperson variations
- 03Audio-led creator and education clips
Considerations
Plan the tradeoffs
The source portrait should have a visible mouth and minimal obstruction around the face.
The standard queue favors credit efficiency over the faster Fabric route.
FAQs
Common questions
What is Fabric 1.0 best used for?
Fabric 1.0 is particularly useful for talking-head content from a single portrait, localized spokesperson variations, audio-led creator and education clips. The right choice still depends on the input assets, delivery format, turnaround, and credit budget for the job.
What inputs does Fabric 1.0 support in Starpop?
Fabric 1.0 supports image, audio input workflows in Starpop. Available controls are shown in the workspace after the model is selected, so unsupported combinations are not presented as options.
How many credits does Fabric 1.0 use?
The currently configured estimate is 1–2 credits. The exact amount shown in Starpop follows the selected resolution, format, duration, or quality option, so review the workspace estimate before generating.
Prompt tips
Get a more useful first result
- 1Use a sharp portrait with even facial lighting.
- 2Keep the face large enough to read clearly in the final format.
- 3Supply clean audio without overlapping speakers.
- 4Match the portrait’s expression to the tone of the audio.
Similar video models
Compare another approach
Reviewed 2026-07-30 against Starpop configuration and VEED source material.
Developer source