happynear commited on
Commit
3db9562
•
1 Parent(s): 7c67027

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -58,7 +58,7 @@ Ruyi-Mini-7B is an advanced image-to-video model with about 7.1 billion paramete
58
  - Phase 1: Pre-training from scratch with ~200M video clips and ~30M images at a 256-resolution, using a batch size of 4096 for 350,000 iterations to achieve full convergence.
59
  - Phase 2: Fine-tuning with ~60M video clips for multi-scale resolutions (384–512), with a batch size of 1024 for 60,000 iterations.
60
  - Phase 3: High-quality fine-tuning with ~20M video clips and ~8M images for 384–1024 resolutions, with dynamic batch sizes based on memory and 10,000 iterations.
61
- - Phase 4: Final video training with ~10M curated high-quality video clips, using a batch size of 1024 for ~10,000 iterations.
62
 
63
  ## Hardware Requirements
64
  The VRAM cost of Ruyi depends on the resolution and duration of the video. Here we list the costs for some typical video size. Tested on single A100.
 
58
  - Phase 1: Pre-training from scratch with ~200M video clips and ~30M images at a 256-resolution, using a batch size of 4096 for 350,000 iterations to achieve full convergence.
59
  - Phase 2: Fine-tuning with ~60M video clips for multi-scale resolutions (384–512), with a batch size of 1024 for 60,000 iterations.
60
  - Phase 3: High-quality fine-tuning with ~20M video clips and ~8M images for 384–1024 resolutions, with dynamic batch sizes based on memory and 10,000 iterations.
61
+ - Phase 4: Image-to-video training with ~10M curated high-quality video clips, with dynamic batch sizes based on memory for ~10,000 iterations.
62
 
63
  ## Hardware Requirements
64
  The VRAM cost of Ruyi depends on the resolution and duration of the video. Here we list the costs for some typical video size. Tested on single A100.