Looking Ahead: Modeling Future Evolution in Autoregressive Video Generation
Fix a typo.
HELLORPG21b0c271aaa6
diff --git a/README.md b/README.mdindex 3be3c87..87dbc07 100644--- a/README.md+++ b/README.md@@ -166,7 +166,7 @@ By default, inference selects the longest valid tail segment of the input videoas the prefix. Use `--v2v_context_latents` to set the prefix length manually.See the [inference documentation](docs/inference.md) for details.-### General Text-and-Image-to-Video Generation+### Text-and-Image-to-Video GenerationRun the following single-GPU example from the repository root. It generates a 5-second video using the 1.3B FCP model, the provided sailboat image and its matching prompt file: