Hugging Face's logo

Phr00t
/
HunyuanVideo-1.5-Rapid-AIO

Text-to-Video
t2v
i2v
hunyuan
rapid
aio
Model card Files
xet
Community
9
Phr00t commited on
Commit
cfd8ac6
·
verified ·
1 Parent(s): 6cf4363

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -1
README.md CHANGED
@@ -18,7 +18,9 @@ Supports both T2V and I2V in 1 model. 1 CFG, 4 steps (although more should work)
18
 
19
  ![image](https://cdn-uploads.huggingface.co/production/uploads/631be8402ea8535ea48abbc6/V7b5nlo4kZ06-mqw8uMRX.png)
20
 
21
- If you are doing I2V, you will need the "clip vision" model: https://huggingface.co/Comfy-Org/HunyuanVideo_1.5_repackaged/tree/main/split_files/clip_vision
 
 
22
 
23
  **V1:** 50/50 mix of the 720p I2V and T2V models. Lightx2v 480p T2V 4-step LORA added at 0.5 strength. **er_sde/beta recommended** at 4 steps. Please experiment with other steps, samplers and schedulers!
24
 
 
18
 
19
  ![image](https://cdn-uploads.huggingface.co/production/uploads/631be8402ea8535ea48abbc6/V7b5nlo4kZ06-mqw8uMRX.png)
20
 
21
+ **I2V usage:** you will need the "clip vision" model: https://huggingface.co/Comfy-Org/HunyuanVideo_1.5_repackaged/tree/main/split_files/clip_vision
22
+
23
+ **T2V usage:** bypass the "input image" optional group.
24
 
25
  **V1:** 50/50 mix of the 720p I2V and T2V models. Lightx2v 480p T2V 4-step LORA added at 0.5 strength. **er_sde/beta recommended** at 4 steps. Please experiment with other steps, samplers and schedulers!
26