Recent text-to-image generation methods provide a sim- ple yet exciting conversion capability between text and im- age domains. While these methods have incrementally im- proved the generated image fidelity and text relevancy, sev- eral pivotal gaps remain unanswered, limiting applicabil- ity and quality. We propose a novel text-to-image method that addresses these gaps by (i) enabling a simple control mechanism complementary to text in the form of a scene, (ii) introducing elements that substantially improve the tok- enization process by employing domain-specific knowledge over key image regions (faces and salient objects), and (iii) adapting classifier-free guidance for the transformer use case. Our model achieves state-of-the-art FID and human evaluation results, unlocking the ability to generate high fi- delity images in a resolution of 512 × 512 pixels, signifi- cantly improving visual quality. Through scene controlla- bility, we introduce several new capabilities: (i) Scene edit- ing, (ii) text editing with anchor scenes, (iii) overcoming out-of-distribution text prompts, and (iv) story illustration generation, as demonstrated in the story we wrote.