stanislavfort / Direct_Ascent_SynthesisLinks
A demo for the Direct Ascent Synthesis: Hidden Generative Capabilities in Discriminative Models paper (https://arxiv.org/abs/2502.07753)
☆41Updated 5 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:
- ☆32Updated 9 months ago
- ☆23Updated last year
- RS-IMLE☆41Updated 8 months ago
- Sparse Autoencoders for Stable Diffusion XL models.☆69Updated last week
- Train VAE like a boss☆287Updated 9 months ago
- ☆39Updated last year
- CLIP Guided Diffusion☆68Updated last year
- Focused on fast experimentation and simplicity☆76Updated 7 months ago
- ☆47Updated 5 months ago
- Official codebase for Margin-aware Preference Optimization for Aligning Diffusion Models without Reference (MaPO).☆79Updated last year
- ☆13Updated last year
- ☆27Updated last year
- Code for NeurIPS 2023 paper "Restart Sampling for Improving Generative Processes"☆150Updated last year
- Official Implementation of weights2weights☆147Updated 4 months ago
- [NeurIPS'2024] Invertible Consistency Distillation for Text-Guided Image Editing in Around 7 Steps☆98Updated last year
- ☆24Updated 3 months ago
- ☆24Updated last year
- SliderSpace: Decomposing the Visual Capabilities of Diffusion Models☆98Updated 4 months ago
- ☆73Updated 2 years ago
- This package introduces a perceptual loss implementation based on the modern ConvNeXt architecture.☆19Updated 8 months ago
- ☆53Updated last year
- Inference-time scaling of diffusion-based image and video generation models.☆161Updated last month
- [ECCV 2024, Oral] FMBoost: Boosting Latent Diffusion with Flow Matching☆241Updated 8 months ago
- UniDisc: A discrete diffusion model for joint multimodal generation, enabling controllable and efficient text-image synthesis, editing, a…☆112Updated 4 months ago
- WIP Pytorch code for stably training single-step, mode-dropping, deterministic autoencoders☆34Updated last week
- A JAX implementation of the continuous time formulation of Consistency Models☆85Updated 2 years ago
- PyTorch implementation of CLIP Maximum Mean Discrepancy (CMMD) for evaluating image generation models.☆139Updated last year
- Minimal Differentiable Image Reward Functions☆79Updated 2 weeks ago
- [ICCV 2025] Official Implementation of Contrastive Flow Matching☆84Updated last month
- ☆21Updated 9 months ago