BytePlus Seedream 5.0 Pro text-to-image, a flagship image generator with excellent Chinese prompt understanding and strong photo-realism. Describe the scene you want in Chinese or English and receive a high-quality render. Compared with the previous generation it adds precise editing control, so you can point at a region or element and adjust only that part, and it renders text and layout more reliably. Supply reference images, up to ten per request, to work from an existing picture. If the result is not quite right, there is no need to re-upload anything: just type another instruction in the same conversation, such as "change the sign text to English" or "switch to a night scene", and the previously generated image is reused automatically for continuous refinement; uploading a new picture starts from that picture instead. Especially good at Asian faces, Chinese cultural motifs, and local environments. Generated images are rendered at the 2K resolution tier (about 2048x2048 pixels at 1:1); the aspect ratio is adjusted automatically from your prompt and reference images. Maximum total upload size per request: 256MB (all files and message content combined). Accepted image formats: bmp, gif, heic, heif, jpeg, jpg, png, tif, tiff, webp. Maximum number of images: 10. Maximum size per image: 30MB. Image dimensions: at least 15 pixels per side. Maximum image resolution: 36,000,000 pixels in total. Image aspect ratio: 1/16 to 16. Output content formats: Image Image output size: 2K class (about 2048x2048 pixels at 1:1; the aspect ratio is decided by the model from the prompt or reference image). This module supports continuous conversations. AI can make mistakes. Please verify important information.