Ernie Turbo text-to-image enhancement

This is a text-to-image application powered by ERNIE-Image Turbo.

After the user inputs a prompt, the workflow first creates an empty latent based on the set resolution, enters the sampler with the prompt, and finally outputs the image via VAE decoding. Compared to standard text-to-image, this flow additionally includes a Prompt Enhancement structure, which automatically expands a brief description into richer, more detailed visual prompts before feeding them into the main model for generation. It is ideal for users who don't know how to write long prompts yet want high-quality images directly. Suitable for posters, cover art, illustrations, stylized single images, and more.

Recommended usage:
Directly enter a short scene description; enable Prompt Enhancement if you want the system to automatically complete the details; or disable enhancement and generate images directly if you already have a fairly complete prompt. Using clear, intuitive subject descriptions is recommended to improve generation stability.

🎁Claim RH Coins first, then try out the workflow! Avatar in top right corner → Invitation Code → Enter [rh-v1111] to instantly get 1000 RH Coins, and log in daily to claim another 100 RH Coins~ For more ComfyUI workflows, tutorials, and gameplay, welcome to follow our WeChat Official Account (AIKSK), with simultaneous updates on Douyin / Bilibili / Xiaohongshu / YouTube (AI-KSK) ✨