{"url":"/method/glide","slug":"glide","name":"GLIDE","full_name":"Guided Language to Image Diffusion for Generation and Editing","full_name_withheld":false,"description_markdown":"GLIDE is a generative model based on text-guided diffusion models for more photorealistic image generation. Guided diffusion is applied to text-conditional image synthesis and the model is able to handle free-form prompts. The diffusion model uses a text encoder to condition on natural language descriptions. The model is provided with editing capabilities in addition to zero-shot generation, allowing for iterative improvement of model samples to match more complex prompts. The model is fine-tuned to perform image inpainting.","description_state":"present","introduced_year":null,"introduced_by":{"title":"GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models","paper":"/paper/glide-towards-photorealistic-image-generation","first_author":"Alex Nichol","n_authors":8,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/glide-towards-photorealistic-image-generation"},"source":{"url":"https://arxiv.org/abs/2112.10741v3","title":"GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"Computer Vision","area_id":"computer-vision","collection":"Image Generation Models","url":"/methods/category/image-generation-models","pwc_aliases":[]},{"area":"Computer Vision","area_id":"computer-vision","collection":"Multi-Modal Methods","url":"/methods/category/multi-modal-methods","pwc_aliases":[]}],"n_papers_tagged":28,"archive_num_papers":28,"papers_newest_first":[{"paper":null,"title":"Target-Date Funds: A State-of-the-Art Review with Policy Applications to Chile's Pension Reform","date":"2025-04-24","arxiv_id":"2504.17713","n_code_links":0,"syntology":null},{"paper":null,"title":"Three-dimensional chiral active Ornstein-Uhlenbeck model for helical motion of microorganisms","date":"2025-01-31","arxiv_id":"2501.18927","n_code_links":0,"syntology":null},{"paper":null,"title":"Deep-Learning Based Docking Methods: Fair Comparisons to Conventional Docking Workflows","date":"2024-12-03","arxiv_id":"2412.02889","n_code_links":0,"syntology":null},{"paper":"/paper/draft-model-knows-when-to-stop-a-self","title":"Draft Model Knows When to Stop: A Self-Verification Length Policy for Speculative Decoding","date":"2024-11-27","arxiv_id":"2411.18462","n_code_links":1,"syntology":null},{"paper":null,"title":"Sensor-Based Safety-Critical Control Using an Incremental Control Barrier Function Formulation via Reduced-Order Approximate Models","date":"2024-10-10","arxiv_id":"2410.08096","n_code_links":0,"syntology":null},{"paper":"/paper/perco-sd-open-perceptual-compression","title":"PerCo (SD): Open Perceptual Compression","date":"2024-09-30","arxiv_id":"2409.20255","n_code_links":1,"syntology":{"ran":2,"of":2,"unverified":0,"pointer_only":1}},{"paper":null,"title":"Visual Verity in AI-Generated Imagery: Computational Metrics and Human-Centric Analysis","date":"2024-08-22","arxiv_id":"2408.12762","n_code_links":0,"syntology":null},{"paper":"/paper/benchmarking-structure-based-three","title":"Benchmarking structure-based three-dimensional molecular generative models using GenBench3D: ligand conformation quality matters","date":"2024-07-05","arxiv_id":"2407.04424","n_code_links":1,"syntology":{"ran":3,"of":3,"unverified":0,"pointer_only":0}},{"paper":null,"title":"EvolvED: Evolutionary Embeddings to Understand the Generation Process of Diffusion Models","date":"2024-06-25","arxiv_id":"2406.17462","n_code_links":0,"syntology":null},{"paper":null,"title":"GliDe with a CaPE: A Low-Hassle Method to Accelerate Speculative Decoding","date":"2024-02-03","arxiv_id":"2402.02082","n_code_links":0,"syntology":null},{"paper":null,"title":"Unraveling the Temporal Dynamics of the Unet in Diffusion Models","date":"2023-12-17","arxiv_id":"2312.14965","n_code_links":0,"syntology":null},{"paper":null,"title":"Synthetic Shifts to Initial Seed Vector Exposes the Brittle Nature of Latent-Based Diffusion Models","date":"2023-11-24","arxiv_id":"2312.11473","n_code_links":0,"syntology":null},{"paper":"/paper/hypernymy-understanding-evaluation-of-text-to","title":"Hypernymy Understanding Evaluation of Text-to-Image Models via WordNet Hierarchy","date":"2023-10-13","arxiv_id":"2310.09247","n_code_links":1,"syntology":null},{"paper":null,"title":"Kernel-Elastic Autoencoder for Molecular Design","date":"2023-10-12","arxiv_id":"2310.08685","n_code_links":0,"syntology":null},{"paper":null,"title":"Altitude-Loss Optimal Glides in Engine Failure Emergencies -- Accounting for Ground Obstacles and Wind","date":"2023-04-13","arxiv_id":"2304.06499","n_code_links":0,"syntology":null},{"paper":null,"title":"Using neuronal models to capture burst and glide motion and leadership in fish","date":"2023-04-03","arxiv_id":"2304.00727","n_code_links":0,"syntology":null},{"paper":"/paper/detecting-images-generated-by-diffusers","title":"Detecting Images Generated by Diffusers","date":"2023-03-09","arxiv_id":"2303.05275","n_code_links":1,"syntology":null},{"paper":null,"title":"TeTIm-Eval: a novel curated evaluation data set for comparing text-to-image models","date":"2022-12-15","arxiv_id":"2212.07839","n_code_links":0,"syntology":null},{"paper":"/paper/towards-practical-plug-and-play-diffusion","title":"Towards Practical Plug-and-Play Diffusion Models","date":"2022-12-12","arxiv_id":"2212.05973","n_code_links":1,"syntology":null},{"paper":null,"title":"Arbitrary Style Guidance for Enhanced Diffusion-Based Text-to-Image Generation","date":"2022-11-14","arxiv_id":"2211.07751","n_code_links":0,"syntology":null},{"paper":"/paper/laion-5b-an-open-large-scale-dataset-for-1","title":"LAION-5B: An open large-scale dataset for training next generation image-text models","date":"2022-10-16","arxiv_id":"2210.08402","n_code_links":5,"syntology":{"ran":4,"of":18,"unverified":14,"pointer_only":3}},{"paper":null,"title":"DE-FAKE: Detection and Attribution of Fake Images Generated by Text-to-Image Generation Models","date":"2022-10-13","arxiv_id":"2210.06998","n_code_links":0,"syntology":null},{"paper":"/paper/on-distillation-of-guided-diffusion-models","title":"On Distillation of Guided Diffusion Models","date":"2022-10-06","arxiv_id":"2210.03142","n_code_links":2,"syntology":null},{"paper":null,"title":"Exploring the GLIDE model for Human Action-effect Prediction","date":"2022-08-01","arxiv_id":"2208.01136","n_code_links":0,"syntology":null},{"paper":"/paper/assessing-and-comparing-fixed-target","title":"Assessing and Comparing Fixed-Target Forecasts of Arctic Sea Ice: Glide Charts for Feature-Engineered Linear Regression and Machine Learning Models","date":"2022-06-21","arxiv_id":"2206.10721","n_code_links":1,"syntology":null},{"paper":null,"title":"Comparison of CoModGANs, LaMa and GLIDE for Art Inpainting- Completing M.C Escher's Print Gallery","date":"2022-05-03","arxiv_id":"2205.01741","n_code_links":0,"syntology":null},{"paper":"/paper/vqgan-clip-open-domain-image-generation-and","title":"VQGAN-CLIP: Open Domain Image Generation and Editing with Natural Language Guidance","date":"2022-04-18","arxiv_id":"2204.08583","n_code_links":1,"syntology":{"ran":4,"of":5,"unverified":1,"pointer_only":0}},{"paper":"/paper/glide-towards-photorealistic-image-generation","title":"GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models","date":"2021-12-20","arxiv_id":"2112.10741","n_code_links":2,"syntology":{"ran":9,"of":15,"unverified":6,"pointer_only":0}}],"papers_shown":28,"tasks":[{"task":"/task/image-generation","name":"Image Generation","papers":10},{"task":"/task/attribute","name":"Attribute","papers":3},{"task":"/task/diversity","name":"Diversity","papers":3},{"task":"/task/text-to-image-generation","name":"Text-to-Image Generation","papers":3},{"task":"/task/denoising","name":"Denoising","papers":2},{"task":"/task/text-to-image-generation-1","name":"Text to Image Generation","papers":2},{"task":null,"name":"valid","papers":2},{"task":null,"name":"8k","papers":1},{"task":"/task/benchmarking","name":"Benchmarking","papers":1},{"task":"/task/depth-estimation","name":"Depth Estimation","papers":1},{"task":"/task/dimensionality-reduction","name":"Dimensionality Reduction","papers":1},{"task":"/task/fake-image-detection","name":"Fake Image Detection","papers":1},{"task":"/task/image-compression","name":"Image Compression","papers":1},{"task":"/task/image-inpainting","name":"Image Inpainting","papers":1},{"task":"/task/knowledge-distillation","name":"Knowledge Distillation","papers":1},{"task":"/task/ms-ssim","name":"MS-SSIM","papers":1},{"task":"/task/prediction","name":"Prediction","papers":1},{"task":"/task/preference-mapping","name":"Preference Mapping","papers":1},{"task":"/task/reranking","name":"Reranking","papers":1},{"task":"/task/ssim","name":"SSIM","papers":1}],"tasks_shown":20,"n_tasks":29,"usage_by_year":[{"year":"2021","papers":1},{"year":"2022","papers":10},{"year":"2023","papers":7},{"year":"2024","papers":8},{"year":"2025","papers":2}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/glide"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}