ethansmith2000 / clip-text-directionsLinks
☆20Updated 11 months ago
Alternatives and similar repositories for clip-text-directions
Users that are interested in clip-text-directions are comparing it to the libraries listed below
Sorting:
- ☆11Updated 11 months ago
- ☆28Updated 10 months ago
- ☆24Updated last month
- Recaption large (Web)Datasets with vllm and save the artifacts.☆52Updated 6 months ago
- Focused on fast experimentation and simplicity☆73Updated 5 months ago
- ☆23Updated 11 months ago
- A demo for the Direct Ascent Synthesis: Hidden Generative Capabilities in Discriminative Models paper (https://arxiv.org/abs/2502.07753)☆39Updated 3 months ago
- Let's try and finetune the OpenAI consistency decoder to work for SDXL☆24Updated last year
- ☆33Updated 7 months ago
- ☆27Updated last year
- ☆30Updated 8 months ago
- ☆24Updated last year
- Real-time latent exploration of diffusion models☆29Updated last year
- ☆47Updated 3 months ago
- ☆38Updated last year
- ☆20Updated 7 months ago
- RS-IMLE☆39Updated 6 months ago
- CLIP Guided Diffusion☆65Updated last year
- A minimalistic, hackable code base to finetune Wan video generation model☆40Updated last month
- A streamlined implementation of Grounding DINO and SAM for advanced image segmentation. This lightweight solution simplifies the integrat…☆64Updated 8 months ago
- ☆13Updated last year
- SliderSpace: Decomposing the Visual Capabilities of Diffusion Models☆94Updated 2 months ago
- Synthetic Alphabet Dataset☆18Updated 2 months ago
- Utilities for PyTorch distributed☆24Updated 3 months ago
- WIP Pytorch code for stably training single-step, mode-dropping, deterministic autoencoders☆27Updated last year
- ☆66Updated 7 months ago
- ☆33Updated 5 months ago
- Fine-tune of Florence-2 for shot categorization.☆24Updated 3 months ago
- Official implementation of "Art-Free Generative Models: Art Creation Without Graphic Art Knowledge"☆31Updated last month
- Lightweight package that tracks and summarizes code changes using LLMs (Large Language Models)☆34Updated 3 months ago