ByteDanceThe Beanbag Big Model team announced a generic image editing model yesterday SeedEditThe user only needs to input simple natural language to perform diverse editing operations on the image, including retouching, dressing, beautifying, style transformation, and adding or deleting elements in the designated area.
Officially, the model has been opened for testing on the PC side of Doubao and the web side of Dream.
Officially, SeedEdit is able to adapt to the diversified editing needs of different users, with strong controllability, good editing effect and no sticker sense, which is mainly reflected in three aspects:
- High-precision instruction comprehension: "no problem" with Chinese, English, and proper nouns
- High-quality editing results: focusing on the target without "mistreating" the original image
- Highly efficient and innovative models: multiple styles can be realized, beautiful and natural looking
statement:The content is collected from various media platforms such as public websites. If the included content infringes on your rights, please contact us by email and we will deal with it as soon as possible.