CiaraRowles commited on
Commit
170b079
1 Parent(s): 522db09

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +10 -1
README.md CHANGED
@@ -13,5 +13,14 @@ inference: true
13
 
14
  # controlnet-CiaraRowles/TemporalNetXL
15
 
16
- These are controlnet weights trained on stabilityai/stable-diffusion-xl-base-1.0 with new type of conditioning.
17
 
 
 
 
 
 
 
 
 
 
 
13
 
14
  # controlnet-CiaraRowles/TemporalNetXL
15
 
16
+ This is TemporalNet1XL, it is a retrain of the controlnet TemporalNet1 with Stable Diffusion XL.
17
 
18
+ This does not use the control mechanism of TemporalNet2 as it would require some additional work to adapt the diffusers pipeline to work with a 6 channel input.
19
+
20
+ In order to run, simply use the script "runtemporalnetxl.py" after installing the normal diffusers requirements and specify the following command line arguments:
21
+
22
+ --prompt does what it says on the tin
23
+ --video_path the path to your input video, this will split the frames out if the frames are not already there, if you want a different resolution or frame rate, you'll want to preprocess them and put them into the ./frames folder
24
+ --frames_dir (optional) if you want a different path for the frames input
25
+ --output_frames_dir (optional) the output directory
26
+ --init_image_path (optional) it is recommended you get the first frame, modify it to a good starting look with stable diffusion, and use that as the first generated frame, if unspecified it will use the first video frame (not reccomened)