mlsanityData to 7 Oct 2026

Development and Enhancement of Text-to-Image Diffusion Models

arXiv 2503.05149 ↗First posted 7 Mar 2025cs.CV cs.AIcited by 0

On the map: Diffusion models → Image generation, text-to-image and editing

Abstract (arXiv)

This research focuses on the development and enhancement of text-to-image denoising diffusion models, addressing key challenges such as limited sample diversity and training instability. By incorporating Classifier-Free Guidance (CFG) and Exponential Moving Average (EMA) techniques, this study significantly improves image quality, diversity, and stability. Utilizing Hugging Face's state-of-the-art text-to-image generation model, the proposed enhancements establish new benchmarks in generative AI. This work explores the underlying principles of diffusion models, implements advanced strategies to overcome existing limitations, and presents a comprehensive evaluation of the improvements achieved. Results demonstrate substantial progress in generating stable, diverse, and high-quality images from textual descriptions, advancing the field of generative artificial intelligence and providing new foundations for future applications. Keywords: Text-to-image, Diffusion model, Classifier-free guidance, Exponential moving average, Image generation.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Image generation, text-to-image and editing, one of 14 directions in Diffusion models. Builds on 13 of its 26 references that are in the map. First posted on arXiv 7 Mar 2025.

Builds on

13 of 26 references.

Closest ancestors · 1

Same direction, newest first

  1. 2021GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models20 Dec

Other references · 12

  1. 2017Attention Is All You Needcited by 59,932
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  3. 2020Language Models are Few-Shot Learnerscited by 32,199
  4. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  5. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  6. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  7. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  8. 2022Classifier-Free Diffusion Guidancecited by 5,717
  9. 2021Zero-Shot Text-to-Image Generationcited by 4,276
  10. 2021Improved Denoising Diffusion Probabilistic Modelscited by 3,736
  11. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,609
  12. 2021Vector-quantized Image Modeling with Improved VQGANcited by 656

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2023Text-to-image Diffusion Models in Generative AI: A Survey
  2. 2024Controllable Generation with Text-to-Image Diffusion Models: A Survey
  3. 2024Generative AI in Vision: A Survey on Models, Metrics and Applications
  4. 2025How Much To Guide: Revisiting Adaptive Guidance in Classifier-Free Guidance Text-to-Vision Diffusion Models
  5. 2025Dynamic Classifier-Free Diffusion Guidance via Online Feedback
  6. 2022eDiff-I: Text-to-Image Diffusion Models with an Ensemble of Expert Denoisers
  7. 2025Classifier-free Guidance with Adaptive Scaling
  8. 2023MagicFusion: Boosting Text-to-Image Generation Performance by Fusing Diffusion Models