animate-diff
30 +
Percs
High quality
9:16 vertical
About
AnimateDiff transforms static text-to-image models into video generators by applying motion modules and LoRA adapters. It supports dynamic camera effects including panning, zooming, and other movements without requiring model fine-tuning. Output is short-form video animation with customizable motion characteristics.
Settings
Negative Prompt- Content to avoid in the generated output.
Base Model- Select a base model (DreamBooth checkpoint)
Inference Steps- Number of inference steps
Guidance Scale- How closely to adhere to the prompt
Frames- Length of the video in frames (8 fps)
Width- Width in pixels
Height- Height in pixels
Output Format- Output format of the video. Can be 'mp4' or 'gif'
Seed- Seed for different images and reproducibility. Use -1 to randomise seed