erwann commited on
Commit
d47e09c
·
1 Parent(s): 369c7ad

update readme

Browse files
Files changed (1) hide show
  1. README.md +7 -0
README.md CHANGED
@@ -13,6 +13,13 @@ Krea Realtime 14B is distilled from the [Wan 2.1 14B text-to-video model](https:
13
 
14
  Inference code can be found [here](https://github.com/krea-ai/realtime-video).
15
 
 
 
 
 
 
 
 
16
  - Our model is over **10x larger than existing realtime video models**
17
  - We introduce **novel techniques for mitigating error accumulation,** including **KV Cache Recomputation** and **KV Cache Attention Bias**
18
  - We develop **memory optimizations specific to autoregressive video diffusion models** that facilitate training large autoregressive models
 
13
 
14
  Inference code can be found [here](https://github.com/krea-ai/realtime-video).
15
 
16
+
17
+ <video width="100%" controls>
18
+ <source src="https://cdn-uploads.huggingface.co/production/uploads/62a2712903bf94c3ac3ae004/NI1qn109PHVeO_LvBQIr8.mp4" type="video/mp4">
19
+ Your browser does not support the video tag.
20
+ </video>
21
+
22
+
23
  - Our model is over **10x larger than existing realtime video models**
24
  - We introduce **novel techniques for mitigating error accumulation,** including **KV Cache Recomputation** and **KV Cache Attention Bias**
25
  - We develop **memory optimizations specific to autoregressive video diffusion models** that facilitate training large autoregressive models