Update diffusion forcing in README.md

Author: RoseRollZhu

README.md

@@ -212,10 +212,10 @@ python3 generate_video_df.py \
 ```
 
 > **Note**: 
-> - If you want to run the **image-to-video (I2V)** task, add `--image ${image_path}` to your command and it is also better to use **text-to-video (T2V)** prompt including the description of the first-frame image.
-> - For long video generation, you can just switch the `--num_frames`, e.g., `--num_frames 257` for 10s video, `--num_frames 377` for 15s video, `--num_frames 737` for 30s video, `--num_frames 1457` for 60s video. The number is not strictly algined with the logical frame number for specified time duration, but it is aligned with some training parameters, which means it may perform better.
-> - You can use `--ar_step 5` to enable asynchronous inference. When asynchronous inference, `--causal_block_size 5` is recommanded while it is not supposed to be set for synchronous generation, and remember that your base frame latent number (e.g., (97-1)//4+1=25 for base_num_frames=97) must be divided by causal_block_size. Asynchronous inference will take more steps to diffuse the whole sequence which means it will be slower than synchronous mode. 
-> - To reduce peak VRAM, just lower the `--base_num_frames`, e.g., to 77 or 57, while keeping the same generative length `--num_frames` you want to generate. This may slightly reduce video quality.
+> - If you want to run the **image-to-video (I2V)** task, add `--image ${image_path}` to your command and it is also better to use **text-to-video (T2V)**-like prompt which includes some descriptions of the first-frame image.
+> - For long video generation, you can just switch the `--num_frames`, e.g., `--num_frames 257` for 10s video, `--num_frames 377` for 15s video, `--num_frames 737` for 30s video, `--num_frames 1457` for 60s video. The number is not strictly aligned with the logical frame number for specified time duration, but it is aligned with some training parameters, which means it may perform better. When you use asynchronous inference with causal_block_size > 1, the `--num_frames` should be carefully set.
+> - You can use `--ar_step 5` to enable asynchronous inference. When asynchronous inference, `--causal_block_size 5` is recommanded while it is not supposed to be set for synchronous generation. REMEMBER that the frame latent number inputted into the model in every iteration, e.g., base frame latent number (e.g., (97-1)//4+1=25 for base_num_frames=97) and (e.g., (237-97-(97-17)x1+17-1)//4+1=20 for base_num_frames=97, num_frames=237, overlap_history=17) for the last iteration, MUST be divided by causal_block_size. If you find it too hard to calculate and set proper values, just use our recommanded setting above :). Asynchronous inference will take more steps to diffuse the whole sequence which means it will be SLOWER than synchronous mode. In our experiments, asynchronous inference may improve the instruction following and visual consistent performance.
+> - To reduce peak VRAM, just lower the `--base_num_frames`, e.g., to 77 or 57, while keeping the same generative length `--num_frames` you want to generate. This may slightly reduce video quality, and it should not be set too small.
 > - `--addnoise_condition` is used to help smooth the long video generation by adding some noise to the clean condition. Too large noise can cause the inconsistency as well. 20 is a recommended value, and you may try larger ones, but it is recommended to not exceed 50.
 > - Generating a 540P video using the 1.3B model requires approximately 14.7GB peak VRAM, while the same resolution video using the 14B model demands around 51.2GB peak VRAM.