Research map / Image generation / Text-to-image diffusion
GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use classifier-free guidance instead of CLIP guidance | GLIDE text-to-image sampling · MS-COCO validation prompts 256×256 | photorealism Elo: -73.2 -> 82.7 | Helped |
| Use classifier-free guidance instead of CLIP guidance | GLIDE text-to-image sampling · MS-COCO validation prompts 256×256 | caption Elo: 29.3 -> 110.9 | Helped |
| Add classifier-free guidance (ablation) | GLIDE · MS-COCO prompts | photorealism Elo: -23.9 -> 133.0 | Helped |
| Add classifier-free guidance (ablation) | GLIDE · MS-COCO prompts | caption Elo: -27.1 -> 140.5 | Helped |
| Add classifier-free guidance (ablation) | GLIDE small · MS-COCO prompts | photorealism Elo: -131.8 -> 28.2 | Helped |
| Add classifier-free guidance (ablation) | GLIDE small · MS-COCO prompts | caption Elo: -136.4 -> 70.9 | Helped |
| Evaluate on a validation subset purged of images similar to training images | GLIDE · MS-COCO 256×256 validation | zero-shot FID: 12.24 -> 12.89 | Hurt |
| Scale the model from 300M to 3.5B parameters (ablation) | GLIDE with classifier-free guidance · MS-COCO prompts | photorealism Elo: 28.2 -> 133.0 | Helped |
| Use classifier-free guidance rather than increasing model size (ablation) | GLIDE · MS-COCO prompts | photorealism Elo: -23.9 -> 133.0 | Helped |
Closest papers by meaning
- RealCompo: Balancing Realism and Compositionality Improves Text-to-Image Diffusion Models (NeurIPS 2024 · similarity 0.90)
- Image Regeneration: Evaluating Text-to-Image Model via Generating Identical Image with Multimodal Large Language Models (AAAI 2025 · similarity 0.89)
- Precise Parameter Localization for Textual Generation in Diffusion Models (ICLR 2025 · similarity 0.89)
- Towards Efficient Diffusion-Based Image Editing with Instant Attention Masks (AAAI 2024 · similarity 0.89)
- Localizing and Editing Knowledge In Text-to-Image Generative Models (ICLR 2024 · similarity 0.89)
- PixArt-$\alpha$: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis (ICLR 2024 · similarity 0.89)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.