Apache-Labs/ApacheXT-1.1

ApacheXT 1.1 Image-to-Video Model Card

(Above samples are from the original SVD1.1 Repo) ApacheXT-1.1 1.1 Image-to-Video is a diffusion model that takes in a still image as a conditioning frame, and generates a video from it.

Model Description

(ApacheXT 1.1) Image-to-video is a latent diffusion model finetuned on the existing stabilityai/stable-video-diffusion-img2vid-xt-1-1 to generate short video clips from image conditioning.

This model was trained to generate 25 frames at resolution 1024x576 given a context frame of the same size, finetuned from SVD Image-to-Video [25 frames].

• Base Model by: Stability AI
• Finetuned by: Apache Labs
• Model type: Generative image-to-video model

Model Sources

For research purposes, we recommend downloading all our files and using them accordingly (UNDER APACHE LABS's LICENCE)

Uses

Direct Use

The model is intended for both non-commercial and commercial usage. You can use this model for non-commercial or research purposes under the following license. Possible research areas and tasks include

• Research on generative models.
• Safe deployment of models which have the potential to generate harmful content.
• Probing and understanding the limitations and biases of generative models.
• Generation of artworks and use in design and other artistic processes.
• Applications in educational or creative tools.

For commercial use, please email us.

Excluded uses are described below.

Out-of-Scope Use

The model was not trained to be factual or true representations of people or events, and therefore using the model to generate such content is out-of-scope for the abilities of this model. The model should not be used in any way that violates Apache Labs's policy

Limitations and Bias

Limitations

• The generated videos are rather short (<= 4sec), and the model does not achieve perfect photorealism.
• The model may generate videos without motion, or very slow camera pans.
• The model cannot be controlled through text.
• The model cannot render legible text.
• Faces and people in general may not be generated properly.
• The autoencoding part of the model is lossy.

Recommendations

The model is intended for both non-commercial and commercial usage.