mlsanityData to 7 Oct 2026

Guidance Free Image Editing via Explicit Conditioning

arXiv 2503.17593 ↗First posted 22 Mar 2025cs.CVcited by 3

On the map: Diffusion models → Diffusion foundations and sampling

Abstract (arXiv)

Current sampling mechanisms for conditional diffusion models rely mainly on Classifier Free Guidance (CFG) to generate high-quality images. However, CFG requires several denoising passes in each time step, e.g., up to three passes in image editing tasks, resulting in excessive computational costs. This paper introduces a novel conditioning technique to ease the computational burden of the well-established guidance techniques, thereby significantly improving the inference time of diffusion models. We present Explicit Conditioning (EC) of the noise distribution on the input modalities to achieve this. Intuitively, we model the noise to guide the conditional diffusion model during the diffusion process. We present evaluations on image editing tasks and demonstrate that EC outperforms CFG in generating diverse high-quality images with significantly reduced computations.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models. Builds on 29 of its 29 references that are in the map. First posted on arXiv 22 Mar 2025.

Builds on

29 of 29 references.

Closest ancestors · 15

Same direction, newest first

  1. 2024Simpler Diffusion (SiD2): 1.5 FID on ImageNet512 with pixel-space diffusion25 Oct
  2. 2024Classifier-Free Guidance is a Predictor-Corrector16 Aug
  3. 2024No Training, No Problem: Rethinking Classifier-Free Guidance for Diffusion Models2 Jul
  4. 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesis5 Mar
  5. 2023Analyzing and Improving the Training Dynamics of Diffusion Models5 Dec
  6. 2023Denoising Diffusion Bridge Models29 Sep
  7. 2023Understanding Diffusion Objectives as the ELBO with Simple Data Augmentation1 Mar
  8. 2022On Distillation of Guided Diffusion Models6 Oct
  9. 2022Understanding Diffusion Models: A Unified Perspective25 Aug
  10. 2022Classifier-Free Diffusion Guidance26 Jul
  11. 2022Elucidating the Design Space of Diffusion-Based Generative Models1 Jun
  12. 2021High-Resolution Image Synthesis with Latent Diffusion Models20 Dec
3 more
  1. 2020Score-Based Generative Modeling through Stochastic Differential Equations26 Nov
  2. 2020Denoising Diffusion Implicit Models6 Oct
  3. 2020Denoising Diffusion Probabilistic Models19 Jun

Other references · 14

  1. 2022Flow Matching for Generative Modelingcited by 5,426
  2. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,067
  3. 2022InstructPix2Pix: Learning to Follow Image Editing Instructionscited by 2,591
  4. 2014Conditional Generative Adversarial Netscited by 2,152
  5. 2016Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Networkcited by 1,199
  6. 2023Improving and generalizing flow-based generative models with minibatch optimal transportcited by 835
  7. 2024Flow Matching Guide and Codecited by 291
  8. 2021StyleGAN-NADA: CLIP-Guided Domain Adaptation of Image Generatorscited by 164
  9. 2023Guided Flows for Generative Modeling and Decision Makingcited by 99
  10. 2025The GAN is dead; long live the GAN! A Modern GAN Baselinecited by 57
  11. 2024Rethinking Score Distillation as a Bridge Between Image Distributionscited by 36
  12. 2023CoDi: Conditional Diffusion Distillation for Higher-Fidelity and Faster Image Generationcited by 26
2 more
  1. 2024Edify Image: High-Quality Image Generation with Pixel Space Laplacian Diffusion Modelscited by 22
  2. 2020Self-labeled Conditional GANscited by 8

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 1; 2026: 2.

3 papers.

  1. 2026Continuous Control of Editing Models via Adaptive-Origin Guidancecited by 5
  2. 2025FraQAT: Quantization Aware Training with Fractional bitscited by 2
  3. 2026RFDM: Residual Flow Diffusion Model for Efficient Causal Video Editingcited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2023Adaptive Guidance: Training-free Acceleration of Conditional Diffusion Models
  2. 2022On Conditioning the Input Noise for Controlled Image Generation with Diffusion Models
  3. 2025Learn to Guide Your Diffusion Model
  4. 2024EP-CFG: Energy-Preserving Classifier-Free Guidance
  5. 2025Unconditional Priors Matter! Improving Conditional Generation of Fine-Tuned Diffusion Models
  6. 2024Rectified Diffusion Guidance for Conditional Generation
  7. 2025TCFG: Tangential Damping Classifier-free Guidance
  8. 2025Conditional Diffusion Models with Classifier-Free Gibbs-like Guidance