Add video-to-video #1469
Add video-to-video #1469
Conversation
merveenoyan
requested review from
SBrandeis,
gary149,
Wauplin,
julien-c,
pcuenca and
ngxson
as code owners
packages/tasks/src/tasks/index.ts
Outdated
| @@ -111,6 +111,7 @@ export type { | |||
| } from "./zero-shot-object-detection/inference.js"; | |||
|
|
|||
| import type { ModelLibraryKey } from "../model-libraries.js"; | |||
| import { get } from "http"; | |||
There was a problem hiding this comment.
is this supposed to be here?
There was a problem hiding this comment.
idk where it came from lol thx for pointing out, fixed
There was a problem hiding this comment.
Looks good to me! Do we have a list of models where this would already apply?
IIRC @linoytsaban had 10-12 models she was tracking!
|
@Vaibhavs10 this yields 62 models https://huggingface.co/search/full-text?q=video-to-video&type=model I'll open PRs |
|
@Vaibhavs10 I opened the PRs, we can merge when some are merged |
|
merged main to this branch, it broke one test ^_^ |
|
Cool work! |
|
awesome 🤗 opened PRs for the VACE models too |
|
Could also be relevant for datasets, e.g. Gemini added it here: https://huggingface.co/datasets/Iceclear/SeedVR_VideoDemos. |
|
opened PRs for SeedVR. the moon one can't be merged without this one being merged (it will fail) this one errors come from mcp client and not this PR, can someone review and we can merge |
|
I think node and browser error isn't related to this PR |
Adding video-to-video as task for models like following (h/t @NielsRogge)
https://github.com/alonzoleeeooo/stablev2v
https://huggingface.co/spaces/fffiloni/Pix2Pix-Video
https://huggingface.co/chestnutlzj/WF-VAE-L-16Chn
also cc @sayakpaul