stanislavfort / Direct_Ascent_SynthesisLinks
A demo for the Direct Ascent Synthesis: Hidden Generative Capabilities in Discriminative Models paper (https://arxiv.org/abs/2502.07753)
☆39Updated 3 months ago
Alternatives and similar repositories for Direct_Ascent_Synthesis
Users that are interested in Direct_Ascent_Synthesis are comparing it to the libraries listed below
Sorting:
- ☆33Updated 7 months ago
- ☆23Updated last year
- RS-IMLE☆40Updated 6 months ago
- Official codebase for Margin-aware Preference Optimization for Aligning Diffusion Models without Reference (MaPO).☆78Updated last year
- Sparse Autoencoders for Stable Diffusion XL models.☆65Updated this week
- WIP Pytorch code for stably training single-step, mode-dropping, deterministic autoencoders☆29Updated last week
- Official implementation of "Art-Free Generative Models: Art Creation Without Graphic Art Knowledge"☆31Updated 2 months ago
- ☆24Updated last month
- ☆27Updated last year
- ☆47Updated 4 months ago
- ☆20Updated 8 months ago
- ☆13Updated last year
- Focused on fast experimentation and simplicity☆74Updated 6 months ago
- SliderSpace: Decomposing the Visual Capabilities of Diffusion Models☆94Updated 3 months ago
- ☆39Updated last year
- CLIP Guided Diffusion☆65Updated last year
- A JAX implementation of the continuous time formulation of Consistency Models☆85Updated 2 years ago
- Official implementation of "Divide & Bind Your Attention for Improved Generative Semantic Nursing" (BMVC 2023 Oral)☆36Updated last year
- ☆51Updated last year
- ☆73Updated 2 years ago
- ☆17Updated 7 months ago
- Official Implementation of weights2weights☆143Updated 3 months ago
- Train transformer language models with reinforcement learning.☆19Updated last year
- ☆60Updated 2 weeks ago
- ☆31Updated last year
- The implementation for Accelerating Guided Diffusion Sampling with Splitting Numerical Methods (2023)☆48Updated 2 years ago
- Train VAE like a boss☆281Updated 8 months ago
- Official implementation of "Is This Loss Informative? Faster Text-to-Image Customization by Tracking Objective Dynamics" (NeurIPS 2023)☆38Updated last year
- ☆70Updated 7 months ago
- ☆116Updated 8 months ago