Spaces:
Running
on
Zero
Running
on
Zero
update description
Browse files
app.py
CHANGED
|
@@ -787,12 +787,16 @@ def run_for_examples(
|
|
| 787 |
|
| 788 |
description = """
|
| 789 |
### 💡 Quick Tips for Best Results (see our [github](https://github.com/VectorSpaceLab/OmniGen2?tab=readme-ov-file#-usage-tips) for more details)
|
| 790 |
-
- Image Quality: Use high-resolution images (at least 512x512 recommended).
|
| 791 |
- Be Specific: Instead of "Add bird to desk", try "Add the bird from image 1 to the desk in image 2".
|
| 792 |
- Use English: English prompts currently yield better results.
|
| 793 |
-
-
|
| 794 |
- Image Editing: 1.3 - 2.0
|
| 795 |
- In-context Generation: 2.0 - 3.0
|
|
|
|
|
|
|
|
|
|
|
|
|
| 796 |
"""
|
| 797 |
|
| 798 |
article = """
|
|
|
|
| 787 |
|
| 788 |
description = """
|
| 789 |
### 💡 Quick Tips for Best Results (see our [github](https://github.com/VectorSpaceLab/OmniGen2?tab=readme-ov-file#-usage-tips) for more details)
|
| 790 |
+
- Image Quality: Use high-resolution images (**at least 512x512 recommended**).
|
| 791 |
- Be Specific: Instead of "Add bird to desk", try "Add the bird from image 1 to the desk in image 2".
|
| 792 |
- Use English: English prompts currently yield better results.
|
| 793 |
+
- Increase image_guidance_scale for better consistency with the reference image:
|
| 794 |
- Image Editing: 1.3 - 2.0
|
| 795 |
- In-context Generation: 2.0 - 3.0
|
| 796 |
+
- For in-context edit (edit based multiple images), we recommend using the following prompt format: "Edit the first image: add/replace (the [object] with) the [object] from the second image. [descripton for your target image]."
|
| 797 |
+
For example: "Edit the first image: add the man from the second image. The man is talking with a woman in the kitchen"
|
| 798 |
+
|
| 799 |
+
Compared to OmniGen 1.0, although OmniGen2 has made some improvements, some issues still remain. It may take multiple attempts to achieve a satisfactory result.
|
| 800 |
"""
|
| 801 |
|
| 802 |
article = """
|