-
Stability.ai, Eleuther.ai
- Seattle, WA
- http:https://dmarx.github.io
- @DigThatData
Block or Report
Block or report dmarx
Contact GitHub support about this user’s behavior. Learn more about reporting abuse.
Report abuseLists (31)
Sort Name ascending (A-Z)
agentic
data visualization
Generative Art
image processing
Knowledge Management
Liked
linux-tweaks
ml audio
ML Depth
ML diffusion
ML Explainability
ML finetune
ML image segmentation
ML Implicit Representations
ML Performance
ML Research
ML super resolution
ML Tools
ML Tools - Non-Python languages
ML Video
MLOps - tools
Multi-modal
needs-attention
highlighting projects that aren't integrated into tools I like (e.g. ComfyUI) and would benefit from community attentionNLP
Pedagogical
prompting
Python Tools
scene synthesis
SD Public Projects
swarm intelligence
TTIv2.0 wishlist
Language
Sort by: Recently starred
Starred repositories
Deforum ComfyUI Nodes - ai animation node package
TextGrad: Automatic ''Differentiation'' via Text -- using large language models to backpropagate textual gradients.
DiffFacto: Controllable Part-Based 3D Point Cloud Generation with Cross Diffusion, ICCV 2023
Make PyTorch models up to 40% faster! Thunder is a source to source compiler for PyTorch. It enables using different hardware executors at once; across one or thousands of GPUs.
InternLM-XComposer-2.5: A Versatile Large Vision Language Model Supporting Long-Contextual Input and Output
[ECCV 2024] Be-Your-Outpainter https://arxiv.org/abs/2403.13745
Official implementation of the paper "Gaussian in the Wild: 3D Gaussian Splatting for Unconstrained Image Collections"
Separate audio stems (vocals, bass, drums) from song, recombine, tempo match, slice/crop audio
Controllable video and image Generation, SVD, Animate Anyone, ControlNet, LoRA
AuraSR: GAN-based Super-Resolution for real-world
Pytorch implementation of preconditioned stochastic gradient descent (affine group preconditioner, low-rank approximation preconditioner and more)
[ECCV 2024] AnyControl, a multi-control image synthesis model that supports any combination of user provided control signals. 一个支持用户自由输入控制信号的图像生成模型,能够根据多种控制生成自然和谐的结果!
code for "Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion"
Agentless🐱: an agentless approach to automatically solve software development problems
Odysseus: Playground of LLM Sequence Parallelism
implementation of https://arxiv.org/pdf/2312.09299
[ICML 2024] Compositional Image Decomposition with Diffusion Models
[ECCV 2024] The official repo for "Texture-GS: Disentangling the Geometry and Texture for 3D Gaussian Splatting Editing"
Tools needed for training B-LoRA method with sd-scripts.
Gemma 2 optimized for your local machine.