Update README.md

README.md

@@ -8,23 +8,30 @@ base_model: runwayml/stable-diffusion-v1-5
 ---
 Introducing the Beta Version of TemporalNet
 
-TemporalNet is a ControlNet model designed to enhance the temporal consistency of generated outputs, as demonstrated in this example: https://twitter.com/CiaraRowles1/status/1637486561917906944. While it does not eliminate all flickering, it significantly reduces it, particularly at higher denoise levels. For optimal results, it is recommended to use TemporalNet in combination with other methods.
+TemporalNet is a ControlNet model designed to enhance the temporal consistency of generated outputs
 
-Instructions for Use:
+TemporalNet 2 is an evolution on the concept, where the generated outputs are guided by both the last frame *and* an optical flow map between the frames, improving generation consistency.
 
-1) Add the model "diff_control_sd15_temporalnet_fp16.safetensors" to your models folder in the ControlNet extension in Automatic1111's Web UI.
+This took some modification of the original controlnet code so you'll have to do some extra things. If you just want to run a gradio example or look at the modified controlnet code,
+that's here: https://github.com/CiaraStrawberry/TemporalNet  Just drop the model from this directory into that model folder and make sure the gradio_temporalnet.py script poitns at the model.
 
-2) Create a folder that contains:
+To use with stable diffusion, you can either use it with TemporalKit, or use it just by accessing the base api through the temporalvideo.py script:
 
-- A subfolder named "Input_Images" with the input frames
+1) move your controlnet webui install to this branch: https://github.com/CiaraStrawberry/sd-webui-controlnet-TemporalNet-API
+
+2) Add the model "diff_control_sd15_temporalnet_fp16.safetensors" to your models folder in the ControlNet extension in Automatic1111's Web UI.
+
+3) Check you have:
+
+- A folder named "Input_Images" with the input frames
 - A PNG file called "init.png" that is pre-stylized in your desired style
 - The "temporalvideo.py" script
 
-3) Customize the "temporalvideo.py" script according to your preferences, such as the image resolution, prompt, and control net settings.
+4) Customize the "temporalvideo.py" script according to your preferences, such as the image resolution, prompt, and control net settings.
 
-4) Launch Automatic1111's Web UI with the --api setting enabled.
+5) Launch Automatic1111's Web UI with the --api setting enabled.
 
-5) Execute the Python script.
+6) Execute the Python script.
 
 *Please note that the "init.png" image will not significantly influence the style of the output video. Its primary purpose is to prevent a drastic change in aesthetics during the first few frames.*