Readme
By specifying image_seed, this overrides the “image embed” (clip) with torch.randn of the same shape of the clip embedding
anotherjesse
/
llava-lies
LLaVA injecting randomness into the image
- Public
- 2.9K runs
- Paper
Input
Output
Run time and cost
This model costs approximately $0.0044 to run on Replicate, or 227 runs per $1, but this varies depending on your inputs. It is also open source and you can run it on your own computer with Docker.
This model runs on Nvidia A40 (Large) GPU hardware. Predictions typically complete within 7 seconds.