Lens is a 3.8B-parameter text-to-image diffusion model that achieves quality competitive with and in several cases surpassing models like FLUX and SD3, while requiring significantly less training compute. Key ideas include maximizing data information density per batch and accelerating convergence.
☆233May 25, 2026Updated 3 weeks ago
Alternatives and similar repositories for Lens
Users that are interested in Lens are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- [CVPR 2026] Implementation for ”Bringing Your Portrait to 3D Presence“☆40Dec 4, 2025Updated 6 months ago
- [CVPR 2025] Official repo for "FATE: Full-head Gaussian Avatar with Textural Editing from Monocular Video"☆118Sep 7, 2025Updated 9 months ago
- A simple pipeline for face editing☆27Dec 20, 2024Updated last year
- Awesome Remote Sensing Vision-Language Datasets☆86Jun 8, 2026Updated last week
- RLHF for Video Diffusion Models☆26Jul 30, 2025Updated 10 months ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- ☆12Sep 11, 2024Updated last year
- ☆168Jan 31, 2026Updated 4 months ago
- ☆34Dec 12, 2024Updated last year
- AI Voice Cloning Desktop Application that runs locally on your computer and doesn't cost anything to run☆62Mar 31, 2026Updated 2 months ago
- Official pytorch implementation of "AlphaFlow: Understanding and Improving MeanFlow Models"☆121Oct 24, 2025Updated 7 months ago
- [ICML 2025] Diff-MoE: Diffusion Transformer with Time-Aware and Space-Adaptive Experts☆34Nov 10, 2025Updated 7 months ago
- A select subset of shaders included in the GShade project modified for use with ReShade.☆14May 3, 2025Updated last year
- Draw ALL Your Imagine: A Holistic Benchmark and Agent Framework for Complex Instruction-based Image Generation☆23Sep 24, 2025Updated 8 months ago
- [ICLR 2026] Adapting Self-Supervised Representations as a Latent Space for Efficient Generation☆60Apr 24, 2026Updated last month
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- The official pytorch implementation of “Diffusion Model as a Noise-Aware Latent Reward Model for Step-Level Preference Optimization”.☆19May 22, 2025Updated last year
- ForeHOI: Feed-forward 3D Object Reconstruction from Daily Hand-Object Interaction Videos☆54Mar 6, 2026Updated 3 months ago
- Tutorials for learning Ruby☆13May 11, 2020Updated 6 years ago
- ☆70May 31, 2026Updated 2 weeks ago
- [ICCV 2025] Prompt-A-Video☆24Feb 2, 2025Updated last year
- Official Implementation for paper: Negative Token Merging: Image-based Adversarial Feature Guidance☆74Jun 23, 2025Updated 11 months ago
- ☆53Jun 13, 2025Updated last year
- Bag of Design Choices for Inference of High-Resolution Masked Generative Transformer☆16Nov 21, 2024Updated last year
- ☆24Jan 14, 2026Updated 5 months ago
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- [CVPR 2026] An official implementation of Adv-GRPO. The Image as Its Own Reward: Reinforcement Learning with Adversarial Reward for Image…☆84Feb 26, 2026Updated 3 months ago
- [CVPR 2026 Oral, Best Paper Finalist] SeaCache: Spectral-Evolution-Aware Cache for Accelerating Diffusion Models☆68Jun 5, 2026Updated last week
- ☆18Dec 2, 2025Updated 6 months ago
- DoyenTalker uses deep learning techniques to generate personalized avatar videos that speak user-provided text in a specified voice. The …☆14Sep 20, 2024Updated last year
- Face Animation from Text☆18Aug 1, 2024Updated last year
- Implementation of Negative-aware Finetuning (NFT) algorithm for "Bridging Supervised Learning and Reinforcement Learning in Math Reasonin…☆84Sep 8, 2025Updated 9 months ago
- Google will omit the title of the web page. With this add-on, the original title is used as much as possible.☆19Jun 1, 2026Updated 2 weeks ago
- This is a sample application of SQLQL☆15Mar 21, 2019Updated 7 years ago
- SR-DiT Speedrunning ImageNet Diffusion☆138Apr 6, 2026Updated 2 months ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- Semantic Map Learning of Traffic Light to Lane Assignment based on Motion Data☆11Mar 30, 2024Updated 2 years ago
- ☆41Mar 19, 2025Updated last year
- [NeurIPS 2025]SyncHuman: Synchronizing 2D and 3D Generative Models for Single-view Human Reconstruction.☆73Jan 21, 2026Updated 4 months ago
- An hardware-aware Efficient Implementation for "Mixture-of-Depths Attention".☆267May 6, 2026Updated last month
- ☆15May 6, 2016Updated 10 years ago
- 🏙️🌆🌃 Try Infinite and Controllable 3D City Layout Generation!☆43Dec 10, 2023Updated 2 years ago
- Unofficial Implementation of Latent Diffusion Models for Layout-to-image Generation☆12Nov 10, 2022Updated 3 years ago