Radamés Ajna's picture

Radamés Ajna PRO

radames

·

https://observablehq.com/@radames

AI & ML interests

None yet

Recent Activity

liked a Space 5 days ago

mistralai/Ministral_3B_WebGPU

upvoted a collection 5 days ago

Mistral Large 3

liked a model 5 days ago

alibaba-pai/Z-Image-Turbo-Fun-Controlnet-Union

View all activity

Organizations

upvoted a collection 5 days ago

Mistral Large 3

A state-of-the-art, open-weight, general-purpose multimodal model with a granular Mixture-of-Experts architecture. • 4 items • Updated 5 days ago • 70

upvoted 2 articles 12 days ago

Article

Continuous batching from first principles

+1

13 days ago

•

248

Article

Diffusers welcomes FLUX-2

+6

13 days ago

•

157

upvoted an article 23 days ago

Article

We’re open-sourcing our text-to-image model and the process behind it

26 days ago

•

73

upvoted an article 3 months ago

Article

Make your ZeroGPU Spaces go brrr with ahead-of-time compilation

+2

Sep 2

•

70

upvoted a collection 4 months ago

gpt-oss

Open-weight models designed for powerful reasoning, agentic tasks, and versatile developer use cases. • 2 items • Updated Aug 7 • 390

upvoted an article 5 months ago

Article

cocogold: training Marigold for text-grounded segmentation

Jul 8

•

31

upvoted an article 6 months ago

Article

KV Cache from scratch in nanoVLM

+3

Jun 4

•

103

upvoted a paper 6 months ago

Chain-of-Zoom: Extreme Super-Resolution via Scale Autoregression and Preference Alignment

Paper • 2505.18600 • Published May 24 • 48

upvoted an article 6 months ago

Article

Tiny Agents in Python: a MCP-powered agent in ~70 lines of code

+2

May 23

•

170

upvoted 7 collections 7 months ago

VACE

VACE: All-in-One Video Creation and Editing • 7 items • Updated May 15 • 34

FramePack Video Generation

fast & compact video generation with FramePack - a next-frame prediction neural network structure that generates videos progressively • 9 items • Updated May 26 • 6

HiDream-I1

A collections of HiDream-I1 models. • 4 items • Updated Apr 8 • 32

HiDream-E1

A collections of HiDream-E1 models. • 3 items • Updated Jul 22 • 6

Qwen3

Qwen's new Qwen3 models. In Unsloth Dynamic 2.0, GGUF, 4-bit and 16-bit Safetensor formats. Includes 128K Context Length variants. • 79 items • Updated 5 days ago • 240

Perception LM

7 items • Updated Apr 17 • 63

ReflectionFlow release

https://diffusion-cot.github.io/reflection2perfection/ • 6 items • Updated Apr 23 • 13

upvoted an article 8 months ago

Article

Tiny Agents: an MCP-powered agent in 50 lines of code

Apr 25

•

303

upvoted 2 papers 9 months ago

InfiniteYou: Flexible Photo Recrafting While Preserving Your Identity

Paper • 2503.16418 • Published Mar 20 • 36

SANA-Sprint: One-Step Diffusion with Continuous-Time Consistency Distillation

Paper • 2503.09641 • Published Mar 12 • 41