Update README.md
Browse files
README.md
CHANGED
|
@@ -73,6 +73,16 @@ python setup.py develop
|
|
| 73 |
|
| 74 |
### Run Image Editing
|
| 75 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 76 |
```python
|
| 77 |
import torch
|
| 78 |
from PIL import Image
|
|
|
|
| 73 |
|
| 74 |
### Run Image Editing
|
| 75 |
|
| 76 |
+
> [!TIP]
|
| 77 |
+
> Leveraging a stronger LLM for prompt refinement can further enhance image generation quality. Please refer to [inference_t2i.py](https://github.com/meituan-longcat/LongCat-Image/blob/main/scripts/inference_t2i.py#L28) for detailed usage instructions.
|
| 78 |
+
|
| 79 |
+
> [!CAUTION]
|
| 80 |
+
> **Special Handling for Text Rendering**
|
| 81 |
+
>
|
| 82 |
+
> For both Text-to-Image and Image Editing tasks involving text generation, **you must enclose the target text within quotes (`""`)**.
|
| 83 |
+
>
|
| 84 |
+
> **Reason:** The tokenizer applies **character-level encoding** specifically to content found inside quotes. Failure to use explicit quotation marks will result in a significant degradation of text rendering quality.
|
| 85 |
+
|
| 86 |
```python
|
| 87 |
import torch
|
| 88 |
from PIL import Image
|