animatediff-illusions
30 +
Percs
High quality
9:16 vertical
About
This model combines AnimateDiff's motion capabilities with ControlNet QR code generation to create animated video sequences from text descriptions. It leverages the SD 1.5 motion module for smooth frame transitions and supports prompt-based control over animation direction and style. Ideal for creating motion graphics, animated illustrations, and stylized video content.
Settings
Negative Prompt- Content to avoid in the generated output.
Frames- Length of the video in frames (8 fps)
Width- Width of generated video in pixels, must be divisable by 8
Height- Height of generated video in pixels, must be divisable by 8
Base Model- Choose the base model for animation generation. If 'CUSTOM' is selected, provide a custom model URL in the next parameter
Scheduler- Diffusion scheduler
Inference Steps- Number of inference steps
Guidance Scale- Guidance Scale. How closely do we want to adhere to the prompt and its contents
ControlNet Strength- Strength of ControlNet. The outputs of the ControlNet are multiplied by `controlnet_conditioning_scale` before they are added to the residual in the original UNet
Loop- Flag to loop the video. Use when you have an 'infinitely' repeating video/gif ControlNet video
Output Format- Output format of the video. Can be 'mp4' or 'gif'
Seed- Seed for different images and reproducibility. Leave blank to randomise seed