Skip to content

​​Unlimited-length talking video generation​​ that supports image-to-video and video-to-video generation

Python

Update README.md

Zhe Kong006e1d3080f8
diff --git a/README.md b/README.md
index b4af0e4..aaffa47 100644
--- a/README.md
+++ b/README.md
@@ -186,7 +186,7 @@ Our model is compatible with both 480P and 720P resolutions.
> - FusionX: While it enables faster inference and higher quality, FusionX LoRA exacerbates color shift over 1 minute and reduces ID preservation in videos.
> - V2V generation: Enables unlimited length generation. The model mimics the original video's camera movement, though not identically. Using SDEdit improves camera movement accuracy significantly but introduces color shift and is best suited for short clips. Improvements for long video camera control are planned.
> - I2V generation: Generates good results from a single image for up to 1 minute. Beyond 1 minute, color shifts become more pronounced. One trick for the high-quailty generation beyond 1 min is to copy the image to a video by translating or zooming in the image.
-
+> - Quantization model: If your inference process is killed due to insufficient memory, we suggest using the quantization model, which can help **reduce memory usage**.
#### Usage of InfiniteTalk
```
@@ -199,6 +199,8 @@ Our model is compatible with both 480P and 720P resolutions.
--teacache_thresh: A coefficient used for TeaCache acceleration
—-sample_text_guide_scale: When not using LoRA, the optimal value is 5. After applying LoRA, the recommended value is 1.
—-sample_audio_guide_scale: When not using LoRA, the optimal value is 4. After applying LoRA, the recommended value is 2.
+—-sample_audio_guide_scale: When not using LoRA, the optimal value is 4. After applying LoRA, the recommended value is 2.
+--max_frame_num: The max frame length of the generated video.
```
#### 1. Inference