chigozienri / animate-diff-sdxl

Animate Your Personalized Text-to-Image Diffusion Models (Long boot times!)

  • Public
  • 965 runs
  • A100 (80GB)
  • GitHub
  • Paper
  • License

Input

string

Select a Motion Model (currently only one available)

Default: "mm_sdxl_v10_beta"

string

Select a model checkpoint

Default: "dynavision"

boolean

Default: false

string

Aspect ratio

Default: "1:1"

integer
(minimum: 16)

Video length

Default: 16

string
Shift + Return to add a new line

Input prompt

Default: "A panda standing on a surfboard in the ocean in sunset, 4k, high resolution. Realistic, Cinematic, high resolution"

string
Shift + Return to add a new line

Negative prompt

Default: ""

integer
(minimum: 1, maximum: 100)

Number of inference steps

Default: 25

number
(minimum: 1, maximum: 10)

guidance scale

Default: 8.5

integer
(minimum: 0, maximum: 2147483647)

Seed (0 = random, maximum: 2147483647)

boolean

Returns .mp4 if true or .gif if false

Default: true

Output

Generated in

This output was created using a different version of the model, chigozienri/animate-diff-sdxl:2f38ae1b.

Run time and cost

This model runs on Nvidia A100 (80GB) GPU hardware. We don't yet have enough runs of this model to provide performance information.

Readme

https://github.com/guoyww/AnimateDiff/tree/sdxl/

A beta-version of motion module for SDXL Now you can generate high-resolution videos on SDXL with/without personalized models. Checkpoint with better quality would be available soon. Stay tuned.

This takes a really long time to cold boot, sorry!