Update README.md

README.md

@@ -3,14 +3,14 @@ license: apache-2.0
 ---
 Diffusers formation for mochi-1-preview model. 
 
-Use following code to inference
+##Use following code to inference
 
 ```bash
 import torch 
 from diffusers import MochiPipeline
 from diffusers.utils import export_to_video
 
-pipe = MochiPipeline.from_pretrained('HanLiii/mochi-1-preview-diffusers', torch_dtype=torch.float16)
+pipe = MochiPipeline.from_pretrained('HanLiii/mochi-1-preview-diffusers', torch_dtype=torch.bfloat16)
 pipe.to("cuda")
 prompt = """
 A hand with delicate fingers picks up a bright yellow lemon from a wooden bowl 
@@ -30,8 +30,10 @@ frames = pipe(prompt,
 
 export_to_video(frames, "mochi_test.mp4")
 ```
-Some generated results:
-<video controls autoplay src="https://cdn-uploads.huggingface.co/production/uploads/62e34a12c9bece303d146af8/Cm3I6kidy2YP5nu3un7XP.mp4"></video>
+fp16 diffusers version result:
+<video controls autoplay src="https://cdn-uploads.huggingface.co/production/uploads/647d3f9683cdb93baf76f963/0YoDABzUbfErx2McV4LA6.mp4"></video>
+github version result:
+<video controls autoplay src="https://cdn-uploads.huggingface.co/production/uploads/647d3f9683cdb93baf76f963/OY29N7HQK2TVSZcAXQAPx.mp4"></video>
 
 ---
 license: apache-2.0