FastVideo
/

FastMetal-1.3B-QAD

video-generation

Model card Files Files and versions

wlsaidhi commited on 9 days ago

Commit

2dac015

·

verified ·

1 Parent(s): a5123ea

Update tier claim: 16 GB-class Macs

Files changed (1) hide show

README.md +4 -4

README.md CHANGED Viewed

@@ -21,7 +21,7 @@ pipeline_tag: text-to-video
 The entry-tier FastMetal model — a DMD2-distilled 1.3B Wan video model with
 a quantization-aware-trained INT8 DiT. Pre-quantized: no startup
-quantization, tiny download, runs on 8 GB-class Macs.
 ## What's inside
@@ -66,6 +66,6 @@ group 64). Training corpus: `FastVideo/Wan-Syn_77x448x832_600k`.
 | Model | Tier |
 |---|---|
-| [FastMetal-1.3B-QAD](https://huggingface.co/FastVideo/FastMetal-1.3B-QAD) | Entry — 16 GB+ class Macs |
-| [FastMetal-5B-QAD] | Mid — 720p | 16 GB+ class Macs |
-| [FastMetal-14B-QAD](https://huggingface.co/FastVideo/FastMetal-14B-QAD) | Quality — 24 GB+/ Ideally 36 Macs |

 The entry-tier FastMetal model — a DMD2-distilled 1.3B Wan video model with
 a quantization-aware-trained INT8 DiT. Pre-quantized: no startup
+quantization, tiny download, runs on 16 GB-class Macs.
 ## What's inside
 | Model | Tier |
 |---|---|
+| **FastMetal-1.3B-QAD** | Entry — 16 GB+ Macs |
+| [FastMetal-5B-QAD](https://huggingface.co/FastVideo/FastMetal-5B-QAD) | Mid — 720p |
+| [FastMetal-14B-QAD](https://huggingface.co/FastVideo/FastMetal-14B-QAD) | Quality — 16 GB+ Macs |