Spaces:
Runtime error
Runtime error
update
Browse files
prompts/alignment.txt
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
<Vision><ModalityHere></Vision> Describe this image in detail.
|
| 2 |
+
<Vision><ModalityHere></Vision> Take a look at this image and describe what you notice.
|
| 3 |
+
<Vision><ModalityHere></Vision> Please provide a detailed description of the picture.
|
| 4 |
+
<Vision><ModalityHere></Vision> Could you describe the contents of this image for me?
|
prompts/alignment_audio.txt
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
<Audio><ModalityHere></Audio> Describe this audio in detail.
|
| 2 |
+
<Audio><ModalityHere></Audio> Pay attention to this audio and describe what you notice.
|
| 3 |
+
<Audio><ModalityHere></Audio> Please provide a detailed description of the sound.
|
| 4 |
+
<Audio><ModalityHere></Audio> Could you describe the contents of this audio for me?
|
prompts/alignment_audio_image_neg.txt
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
<Audio><ModalityHere></Audio> <Vision><ModalityHere></Vision> Please describe the image and audio respectively.
|
| 2 |
+
<Audio><ModalityHere></Audio> <Vision><ModalityHere></Vision> What is the audio and the image?
|
| 3 |
+
<Audio><ModalityHere></Audio> <Vision><ModalityHere></Vision> Please provide a detailed description of the sound and the image.
|
| 4 |
+
<Audio><ModalityHere></Audio> <Vision><ModalityHere></Vision> Could you tell the contents of this audio and photo for me?
|
| 5 |
+
<Audio><ModalityHere></Audio> <Vision><ModalityHere></Vision> Are the audio and image related to each other? What are they?
|
prompts/alignment_audio_image_region.txt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
<Audio><ModalityHere></Audio> <Vision><ModalityHere></Vision> Please find the source that emits the given sound in this image.
|
| 2 |
+
<Audio><ModalityHere></Audio> <Vision><ModalityHere></Vision> Pay attention to the given audio and image, and tell me where is the sound coming from in this picture.
|
| 3 |
+
<Audio><ModalityHere></Audio> <Vision><ModalityHere></Vision> Which part of this scene is the source of the given sound?
|