Radamés Ajna's picture

Radamés Ajna PRO

radames

·

https://observablehq.com/@radames

AI & ML interests

None yet

Recent Activity

liked a Space 4 days ago

multimodalart/FLUX.2-dev-turbo

liked a model 4 days ago

fal/FLUX.2-dev-Turbo

liked a model 14 days ago

Qwen/Qwen3-4B

View all activity

Organizations

upvoted a collection 15 days ago

FunctionGemma

3 items • Updated 15 days ago • 30

upvoted a collection 17 days ago

sam-audio

11 items • Updated 17 days ago • 107

upvoted a collection about 1 month 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 Dec 2, 2025 • 81

upvoted 2 articles about 1 month ago

Article

Continuous batching from first principles

+1

Nov 25, 2025

•

291

Article

Diffusers welcomes FLUX-2

+6

Nov 25, 2025

•

167

upvoted an article about 2 months ago

Article

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

Nov 12, 2025

•

76

upvoted an article 4 months ago

Article

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

+2

Sep 2, 2025

•

71

upvoted a collection 5 months ago

gpt-oss

Open-weight models designed for powerful reasoning, agentic tasks, and versatile developer use cases. • 2 items • Updated Aug 7, 2025 • 396

upvoted an article 6 months ago

Article

cocogold: training Marigold for text-grounded segmentation

Jul 8, 2025

•

31

upvoted an article 7 months ago

Article

KV Cache from scratch in nanoVLM

+3

Jun 4, 2025

•

107

upvoted a paper 7 months ago

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

Paper • 2505.18600 • Published May 24, 2025 • 48

upvoted an article 7 months ago

Article

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

+2

May 23, 2025

•

170

upvoted 7 collections 8 months ago

VACE

VACE: All-in-One Video Creation and Editing • 7 items • Updated May 15, 2025 • 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, 2025 • 6

HiDream-I1

A collections of HiDream-I1 models. • 4 items • Updated Apr 8, 2025 • 32

HiDream-E1

A collections of HiDream-E1 models. • 3 items • Updated Jul 22, 2025 • 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 9 days ago • 250

Perception LM

7 items • Updated Apr 17, 2025 • 63

ReflectionFlow release

https://diffusion-cot.github.io/reflection2perfection/ • 6 items • Updated Apr 23, 2025 • 13

upvoted an article 8 months ago

Article

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

Apr 25, 2025

•

304