These are mirrors for the official AnimateDiff v3 models released by guoyww on huggingface https://github.com/guoyww/animatediff/
An explaination of the improvements introduced with v3 can be found on this github https://github.com/guoyww/animatediff/#202312-animatediff-v3-and-sparsectrl
Some resources for starters
https://education.civitai.com/beginners-guide-to-animatediff/
https://education.civitai.com/new-animatediff-motion-modules/
In addition to that i can also recommend our Thursday's office hours with team member Tyler (jboogx.creative) which focus on creating animations with stable diffusion.
Alternate AnimateDiff v3 Adapter (FP16) for SD1.5 and Automatic1111 provided by the dev of the animatediff extension here. Thanks for pointing this out, 8f8281 :)
Description
AnimateDiff v3 SparseControl-Encoder Scribble (FP32) for SD1.5
FAQ
Comments (3)
very good, it looks promising, I'll wait for the tutorial for people with IQ below 90 to come out
Does anyone know if we can use camera movement models that worked for V2 also for V3. If yes, how? I can't seem to run the camera motion modules with this version?
pure speculation, but i guess they would need to be retrained for v3. though only the original author could tell you for sure, you might try contacting them on github.
Details
Files
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.