Text-to-Image
تحويل النص إلى صورة
مهمة توليدية يُنشئ فيها النموذج صورة انطلاقاً من وصف نصي، باستخدام التوجيه بالانتباه التبادلي لربط المعنى اللغوي بالمحتوى البصري.
A generative task where the model creates an image from a text description, using cross-attention conditioning to link linguistic meaning with visual content.
Also translated asالتوليد النصّي البصري، التوليد من نص إلى صورة
First appears in this corpus in: DALL·E: Zero-Shot Text-to-Image Generation (2021)
Appears in these papers
- DALL·E: Zero-Shot Text-to-Image Generation2021in the sky ✦
- DALL·E: Zero-Shot Text-to-Image Generation2021in the sky ✦
- GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models2021in the sky ✦
- GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models2021in the sky ✦
- Imagen: Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding2022in the sky ✦
- Imagen: Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding2022in the sky ✦
- High-Resolution Image Synthesis with Latent Diffusion Models2022in the sky ✦
- Video Generation Models as World Simulators2024in the sky ✦