From 2afcdf81aaf94170b717ddc1390b0ba2598f93d5 Mon Sep 17 00:00:00 2001 From: RhymesAI Date: Fri, 18 Oct 2024 08:47:36 +0000 Subject: [PATCH] Update README.md --- README.md | 63 ++++++++++++++++++++++++++++++++++++++++++------------- 1 file changed, 48 insertions(+), 15 deletions(-) diff --git a/README.md b/README.md index 7916fc5..f7e732a 100644 --- a/README.md +++ b/README.md @@ -21,22 +21,55 @@ Allegro is capable of producing high-quality, 6-second videos at 30 frames per s # Model info -| **Model** | Allegro | -|-------------------------------|------------------------------------------------| -| **Description** | Text-to-Video Diffusion Transformer | -| **Download** | | -| **Parameter** | VAE: 175M
DiT: 2.8B | -| **Inference Precision** | VAE: FP32/TF32/BF16/FP16 (best in FP32/TF32)
DiT/T5: BF16/FP32/TF32 | -| **Context Length** | 79.2k | -| **Resolution** | 720 x 1280 | -| **Frames** | 88 | -| **Video Length** | 6 seconds @ 15 fps | -| **Single GPU Memory Usage** | 9.3G BF16 (with cpu_offload) | + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
ModelAllegro
DescriptionText-to-Video Diffusion Transformer
Download<HF link - TBD>
ParameterVAE: 175M
DiT: 2.8B
Inference PrecisionVAE: FP32/TF32/BF16/FP16 (best in FP32/TF32)
DiT/T5: BF16/FP32/TF32
Context Length79.2k
Resolution720 x 1280
Frames88
Video Length6 seconds @ 15 fps
Single GPU Memory Usage9.3G BF16 (with cpu_offload)
-| Name | Parameter | Context Length | Download | -|-----------|-----------|-----------------|------------------------------------------------------------------| -| Allegro | 3B | 80K | [🤗 Hugging Face](https://huggingface.co/rhymes-ai/Allegro) | -| | # Quick start