-
Notifications
You must be signed in to change notification settings - Fork 0
Chore: Add Lucy Edit fast #29
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Conversation
commit: |
src/shared/model.ts
Outdated
| num_inference_steps: z | ||
| .number() | ||
| .optional() | ||
| .describe("The number of inference steps"), |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I was just informed that num_inference_steps isn't available in lucy-fast-v2v so let's remove it
src/shared/model.ts
Outdated
| name: "lucy-fast-v2v" as const, | ||
| fps: 25, | ||
| width: 1280, | ||
| height: 704, |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
| height: 704, | |
| height: 720, |
tests/unit.test.ts
Outdated
| model: models.video("lucy-fast-v2v"), | ||
| prompt: "Change the car to a motorcycle", | ||
| data: testVideo, | ||
| resolution: "480p", |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
We removed 480p from Lucy Pro V2V in an earlier PR (#28) so it's best to pull the latest changes from main and update the PR accordingly
src/shared/model.ts
Outdated
| "The video data to use for generation (File, Blob, ReadableStream, URL, or string URL)", | ||
| ), | ||
| seed: z.number().optional().describe("The seed to use for the generation"), | ||
| resolution: proResolutionSchema(), |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Needs to be proV2vResolutionSchema so it'll be aligned with the v2v models
No description provided.