Re-animate your videos with evolved consistency!

AnimateDiff Video-to-Video Evolved

Base model to use for animation generation.

Base Model


            The CFG (Classifier Free Guidance) scale is a measure of how close you want
            the model to stick to your prompt when looking for a related image to show you.
        

Guidance scale (CFG)

Loras


            The negative prompt to use. Use it to address details that you don't want
            in the image. This could be colors, objects, scenery and even the small details
            (e.g. moustache, blurry, low resolution).
        

Negative Prompt


            Increasing the amount of steps tells Stable Diffusion that it should take more steps
            to generate your final result which can increase the amount of detail in your image.
        

Number of inference steps

The prompt to use for generating the image. Be as descriptive as possible for best results.

Prompt


            The same seed and the same prompt given to the same version of Stable Diffusion
            will output the same image every time.
        

Seed


            Select every Nth frame from the video.
            This can be used to reduce the number of frames to process, which can reduce the time and the cost.
            However, it can also reduce the quality of the final video.
        

Select Every Nth Frame

Video Url

AnimateDiffV2VInput

Timings

Video

AnimateDiffV2VOutput

AnimateDiffV2VTurboInput

AnimateDiffV2VTurboOutput

Content Type

File Data

The name of the file. It will be auto-generated if not provided.

File Name

File Size

The URL where the file can be downloaded from.

File

Detail

HTTPValidationError

URL or the path to the LoRA weights. Or HF model name.

Path


            The scale of the LoRA weight. This is used to scale the LoRA weight
            before merging it with the base model.
        

AnimateDiff Video-to-Video Evolved

Input

Result

Logs