Join the conversation

Join the community of Machine Learners and AI enthusiasts.

Sign Up

All HF Hub posts

ginipickย 
posted an update 1 day ago
view post
Post
3035
๐Ÿš€ FLUX Workflow Canvas

Welcome to Workflow Canvas, your ultimate AI-driven platform for crafting stunning design concepts and intricate workflow diagrams that empower your business! ๐Ÿค–โœจ

ginigen/Workflow-Canvas

Features
Product Design ๐Ÿ› ๏ธ
Transform your ideas into reality with sleek, industrial product designs that blend modern aesthetics with advanced technology.

Mindmap ๐Ÿง 
Generate vibrant, educational mind maps that outline your strategies and processes in a clear, visually engaging layout.

Mockup ๐Ÿ“ฑ
Quickly prototype intuitive app interfaces and web designs using clean, hand-drawn wireframes that capture your vision.

Infographic ๐Ÿ“Š
Build polished, data-rich infographics that communicate complex corporate metrics and trends with style and clarity.

Diagram ๐Ÿ“ˆ
Illustrate comprehensive, end-to-end business workflowsโ€”from market analysis to implementationโ€”with detailed and organized diagrams.

Flowchart ๐Ÿ”„
Design easy-to-follow, hand-drawn style flowcharts that map out your operational processes using vibrant colors and minimalistic icons.

How It Works
Set Your Parameters:
Customize your creative process by adjusting the seed, dimensions, inference steps, and guidance scale through the intuitive sidebar.

Choose Your Visual Style:
Explore our diverse range of tabsโ€”from Product Design and Mindmap to Flowchartโ€”each tailored to a unique creative output.

Get Inspired:
Dive into our rich library of example prompts featuring detailed lists and tree structures to instantly populate your design ideas.

Generate Your Masterpiece:
Click the โ€œGenerateโ€ button and watch as your ideas come to life in beautifully rendered images! ๐ŸŽจ

Experience the fusion of art and technology with Workflow Canvas โ€“ where your business ideas transform into dynamic, visual masterpieces. Get started today and revolutionize the way you design! ๐Ÿš€
Jawardย 
posted an update 2 days ago
view post
Post
2915
Finally here it is: a faster, custom, scalable GRPO trainer for smaller models with < 500M params, can train on 8gb ram cpu, also supports gpu for sanity sake (includes support for vllm + flash attention). Using smolLM2-135M/360M-instructs as ref & base models. Experience your own โ€œahaโ€ moment ๐Ÿณ on 8gb ram.
Code: https://github.com/Jaykef/ai-algorithms/blob/main/smollm2_360M_135M_grpo_gsm8k.ipynb
  • 2 replies
ยท
prithivMLmodsย 
posted an update 2 days ago
view post
Post
4217
The last week of Impression Craft Arts and sketches from strangerzonehf๐ŸŽจ๐Ÿง‘๐Ÿปโ€๐ŸŽจ

- Collection : strangerzonehf/Flux-Ultimate-LoRA-Collection

Adapters:
+ Ld-Art : strangerzonehf/Ld-Art
+ Animeopix-Flux : strangerzonehf/Animeopix-Flux
+ Flux-Super-Paint-LoRA : strangerzonehf/Flux-Super-Paint-LoRA
+ CinematicShot-Pics-Flux : strangerzonehf/cinematicShot-Pics-Flux
+ Oil-Wall-Art-Flux : strangerzonehf/Oil-Wall-Art-Flux
+ Pixelo-Flux : strangerzonehf/Pixelo-Flux
+ Abstract-Shattered : strangerzonehf/Abstract-Shattered
+ Neon-Impressionism-Flux : strangerzonehf/Neon-Impressionism-Flux
+ NewG-Art : strangerzonehf/NewG-Art

๐ŸชงDemo : prithivMLmods/FLUX-LoRA-DLC
๐Ÿค—Page : https://huggingface.co./strangerzonehf
tianchezย 
posted an update 4 days ago
view post
Post
3543
Introducing VLM-R1!

GRPO has helped DeepSeek R1 to learn reasoning. Can it also help VLMs perform stronger for general computer vision tasks?

The answer is YES and it generalizes better than SFT. We trained Qwen 2.5 VL 3B on RefCOCO (a visual grounding task) and eval on RefCOCO Val and RefGTA (an OOD task).

https://github.com/om-ai-lab/VLM-R1
clemย 
posted an update 1 day ago
view post
Post
2045
We crossed 1B+ tokens routed to inference providers partners on HF, that we released just a few days ago.

Just getting started of course but early users seem to like it & always happy to be able to partner with cool startups in the ecosystem.

Have you been using any integration and how can we make it better?

https://huggingface.co./blog/inference-providers
schulerย 
posted an update 2 days ago
view post
Post
3031
๐Ÿ”ฎ GPT-3 implemented in pure Free Pascal!
https://github.com/joaopauloschuler/gpt-3-for-pascal

This implementation follows the GPT-3 Small architecture from the landmark paper "Language Models are Few-Shot Learners":
โ”Œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”
โ”‚     Input Layer       โ”‚
โ”œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ค
โ”‚ Token & Positional    โ”‚
โ”‚     Embedding         โ”‚
โ”œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ค
โ”‚   12x Transformer     โ”‚
โ”‚      Blocks           โ”‚
โ”‚  - 12 heads           โ”‚
โ”‚  - 768 hidden dims    โ”‚
โ”‚  - 3072 intermediate  โ”‚
โ”œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ค
โ”‚   Output Layer        โ”‚
โ””โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”˜

Clean Pascal Implementation
for CntLayer := 1 to {Layers=}12 do
begin
  Result.AddTransformerBlockCAI(
    {Heads=}12, 
    {intermediate dimensions=}4*768, 
    {NoForward=}true, 
    {HasNorm=}true, 
    false
  );
end;

jasoncorkillย 
posted an update 1 day ago
view post
Post
1636
This dataset was collected in roughly 4 hours using the Rapidata Python API, showcasing how quickly large-scale annotations can be performed with the right tooling!

All that at less than the cost of a single hour of a typical ML engineer in Zurich!

The new dataset of ~22,000 human annotations evaluating AI-generated videos based on different dimensions, such as Prompt-Video Alignment, Word for Word Prompt Alignment, Style, Speed of Time flow and Quality of Physics.

Rapidata/text-2-video-Rich-Human-Feedback
burtenshawย 
posted an update 1 day ago
view post
Post
2067
NEW COURSE! Weโ€™re cooking hard on Hugging Face courses, and itโ€™s not just agents. The NLP course is getting the same treatment with a new chapter on Supervised Fine-Tuning!

๐Ÿ‘‰ Follow to get more updates https://huggingface.co./nlp-course

The new SFT chapter will guide you through these topics:

1๏ธโƒฃ Chat Templates: Master the art of structuring AI conversations for consistent and helpful responses.

2๏ธโƒฃ Supervised Fine-Tuning (SFT): Learn the core techniques to adapt pre-trained models to your specific outputs.

3๏ธโƒฃ Low Rank Adaptation (LoRA): Discover efficient fine-tuning methods that save memory and resources.

4๏ธโƒฃ Evaluation: Measure your model's performance and ensure top-notch results.

This is the first update in a series, so follow along if youโ€™re upskilling in AI.
sayakpaulย 
posted an update 1 day ago
view post
Post
1491
Inference-time scaling meets Flux.1-Dev (and others) ๐Ÿ”ฅ

Presenting a simple re-implementation of "Inference-time scaling diffusion models beyond denoising steps" by Ma et al.

I did the simplest random search strategy, but results can potentially be improved with better-guided search methods.

Supports Gemini 2 Flash & Qwen2.5 as verifiers for "LLMGrading" ๐Ÿค—

The steps are simple:

For each round:

1> Starting by sampling 2 starting noises with different seeds.
2> Score the generations w.r.t a metric.
3> Obtain the best generation from the current round.

If you have more compute budget, go to the next search round. Scale the noise pool (2 ** search_round) and repeat 1 - 3.

This constitutes the random search method as done in the paper by Google DeepMind.

Code, more results, and a bunch of other stuff are in the repository. Check it out here: https://github.com/sayakpaul/tt-scale-flux/ ๐Ÿค—
AdinaYย 
posted an update about 8 hours ago
view post
Post
570
๐Ÿš€ StepFun้˜ถ่ทƒๆ˜Ÿ่พฐ is making BIG open moves!

Last year, their GOT-OCR 2.0 took the community by storm ๐Ÿ”ฅbut many didnโ€™t know they were also building some amazing models. Now, theyโ€™ve just dropped something huge on the hub!

๐Ÿ“บ Step-Video-T2V: a 30B bilingual open video model that generates 204 frames (8-10s) at 540P resolution with high information density & consistency.
stepfun-ai/stepvideo-t2v

๐Ÿ”Š Step-Audio-TTS-3B : a TTS trained with the LLM-Chat paradigm on a large synthetic dataset, capable of generating RAP & Humming
stepfun-ai/step-audio-67b33accf45735bb21131b0b