openai/glide-text2im
glide-text2im
GLIDE: a diffusion-based text-conditional image synthesis model
Builder
OpenAI
openai • ai-lab
Stars
3,692
Using upstream star count
Forks
500
Using upstream fork count
Open Issues
0
Activity Score
0/100
0 commits in 30d
Created
Dec 10, 2021
Project creation date
README Summary
GLIDE is OpenAI's diffusion-based model for generating images from text descriptions, offering both a smaller filtered model for public use and a larger unfiltered model for research. The repository provides pre-trained checkpoints and inference code for text-to-image synthesis using classifier-free guidance and CLIP guidance techniques.
AI Dev Skills
Unmapped
Diffusion ModelsText-to-Image GenerationCLIP IntegrationMultimodal Deep LearningComputer VisionNatural Language ProcessingGenerative AITransformer ArchitectureImage SynthesisGradient-based Guidance
Tags
Diffusion ModelsText-to-Image GenerationCLIP IntegrationMultimodal Deep LearningComputer VisionNatural Language ProcessingGenerative AITransformer ArchitectureImage SynthesisGradient-based GuidanceMultimodal AIDigital Art GenerationMarketing Asset CreationImageText-to-Image SynthesisCloud ComputingSelf-hostedGPU-accelerated InfrastructurePrototype Image GenerationCreative Content CreationTextMultimodalConcept VisualizationPython
Taxonomy
Deployment Context
Modalities
Skill Areas
Recent Activity
Updated 2 years ago
7 Days
0
30 Days
0
90 Days
0
Quality
research- Quality
- medium
- Maturity
- research
Categories
Foundation ModelsPrimaryML Platform & InfrastructureInference & ServingNLP & TextData Science & AnalyticsMultimodal AIOther AI / MLGenerative MediaComputer Vision
PM Skills
Scale & Reliability
Languages
Python100.0%
Timeline
- Project created
- Dec 10, 2021
- Forked
- Mar 14, 2026
- Your last push
- 2 years ago
- Upstream last push
- 2 years ago
- Tracked since
- Mar 8, 2024
Similar Repos
pgvector cosine similarity · $0
Loading…