Goku: Flow Based Video Generative Foundation Models
Paper
ā¢
2502.04896
ā¢
Published
ā¢
65
NFTCID
NFTCID
Ā·
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
2 days ago
Goku: Flow Based Video Generative Foundation Models
liked
a dataset
2 days ago
saiyan-world/Goku-MovieGenBench
Organizations
None yet
NFTCID's activity
upvoted
a
paper
2 days ago
liked
a
dataset
2 days ago
reacted to
ginipick's
post with š„
4 days ago
Post
5010
š 3D Llama Studio - AI 3D Generation Platform
š Project Overview
3D Llama Studio is an all-in-one AI platform that generates high-quality 3D models and stylized images from text or image inputs.
āØ Key Features
Text/Image to 3D Conversion šÆ
Generate 3D models from detailed text descriptions or reference images
Intuitive user interface
Text to Styled Image Generation šØ
Customizable image generation settings
Adjustable resolution, generation steps, and guidance scale
Supports both English and Korean prompts
š ļø Technical Features
Gradio-based web interface
Dark theme UI/UX
Real-time image generation and 3D modeling
š« Highlights
User-friendly interface
Real-time preview
Random seed generation
High-resolution output support (up to 2048x2048)
šÆ Applications
Product design
Game asset creation
Architectural visualization
Educational 3D content
š Try It Now!
Experience 3D Llama Studio:
ginigen/3D-LLAMA
#AI #3DGeneration #MachineLearning #ComputerVision #DeepLearning
š Project Overview
3D Llama Studio is an all-in-one AI platform that generates high-quality 3D models and stylized images from text or image inputs.
āØ Key Features
Text/Image to 3D Conversion šÆ
Generate 3D models from detailed text descriptions or reference images
Intuitive user interface
Text to Styled Image Generation šØ
Customizable image generation settings
Adjustable resolution, generation steps, and guidance scale
Supports both English and Korean prompts
š ļø Technical Features
Gradio-based web interface
Dark theme UI/UX
Real-time image generation and 3D modeling
š« Highlights
User-friendly interface
Real-time preview
Random seed generation
High-resolution output support (up to 2048x2048)
šÆ Applications
Product design
Game asset creation
Architectural visualization
Educational 3D content
š Try It Now!
Experience 3D Llama Studio:
ginigen/3D-LLAMA
#AI #3DGeneration #MachineLearning #ComputerVision #DeepLearning
reacted to
Xenova's
post with š
4 days ago
Post
5314
We did it. Kokoro TTS (v1.0) can now run 100% locally in your browser w/ WebGPU acceleration. Real-time text-to-speech without a server. ā”ļø
Generate 10 seconds of speech in ~1 second for $0.
What will you build? š„
webml-community/kokoro-webgpu
The most difficult part was getting the model running in the first place, but the next steps are simple:
āļø Implement sentence splitting, allowing for streamed responses
š Multilingual support (only phonemization left)
Who wants to help?
Generate 10 seconds of speech in ~1 second for $0.
What will you build? š„
webml-community/kokoro-webgpu
The most difficult part was getting the model running in the first place, but the next steps are simple:
āļø Implement sentence splitting, allowing for streamed responses
š Multilingual support (only phonemization left)
Who wants to help?
- 7 replies
liked
a
model
16 days ago
reacted to
m-ric's
post with š
26 days ago
Post
1350
š š¶š»š¶š š®š
'š š»š²š š š¼š ššš šæš²š®š°šµš²š šš¹š®šš±š²-š¦š¼š»š»š²š š¹š²šš²š¹ šš¶ššµ š°š šš¼šøš²š»š š°š¼š»šš²š
š š¹š²š»š“ššµ š„
This work from Chinese startup @MiniMax-AI introduces a novel architecture that achieves state-of-the-art performance while handling context windows up to 4 million tokens - roughly 20x longer than current models. The key was combining lightning attention, mixture of experts (MoE), and a careful hybrid approach.
šš²š š¶š»šš¶š“šµšš:
šļø MoE with novel hybrid attention:
ā£ Mixture of Experts with 456B total parameters (45.9B activated per token)
ā£ Combines Lightning attention (linear complexity) for most layers and traditional softmax attention every 8 layers
š Outperforms leading models across benchmarks while offering vastly longer context:
ā£ Competitive with GPT-4/Claude-3.5-Sonnet on most tasks
ā£ Can efficiently handle 4M token contexts (vs 256K for most other LLMs)
š¬ Technical innovations enable efficient scaling:
ā£ Novel expert parallel and tensor parallel strategies cut communication overhead in half
ā£ Improved linear attention sequence parallelism, multi-level padding and other optimizations achieve 75% GPU utilization (that's really high, generally utilization is around 50%)
šÆ Thorough training strategy:
ā£ Careful data curation and quality control by using a smaller preliminary version of their LLM as a judge!
Overall, not only is the model impressive, but the technical paper is also really interesting! š
It has lots of insights including a great comparison showing how a 2B MoE (24B total) far outperforms a 7B model for the same amount of FLOPs.
Read it in full here š MiniMax-01: Scaling Foundation Models with Lightning Attention (2501.08313)
Model here, allows commercial use <100M monthly users š MiniMaxAI/MiniMax-Text-01
This work from Chinese startup @MiniMax-AI introduces a novel architecture that achieves state-of-the-art performance while handling context windows up to 4 million tokens - roughly 20x longer than current models. The key was combining lightning attention, mixture of experts (MoE), and a careful hybrid approach.
šš²š š¶š»šš¶š“šµšš:
šļø MoE with novel hybrid attention:
ā£ Mixture of Experts with 456B total parameters (45.9B activated per token)
ā£ Combines Lightning attention (linear complexity) for most layers and traditional softmax attention every 8 layers
š Outperforms leading models across benchmarks while offering vastly longer context:
ā£ Competitive with GPT-4/Claude-3.5-Sonnet on most tasks
ā£ Can efficiently handle 4M token contexts (vs 256K for most other LLMs)
š¬ Technical innovations enable efficient scaling:
ā£ Novel expert parallel and tensor parallel strategies cut communication overhead in half
ā£ Improved linear attention sequence parallelism, multi-level padding and other optimizations achieve 75% GPU utilization (that's really high, generally utilization is around 50%)
šÆ Thorough training strategy:
ā£ Careful data curation and quality control by using a smaller preliminary version of their LLM as a judge!
Overall, not only is the model impressive, but the technical paper is also really interesting! š
It has lots of insights including a great comparison showing how a 2B MoE (24B total) far outperforms a 7B model for the same amount of FLOPs.
Read it in full here š MiniMax-01: Scaling Foundation Models with Lightning Attention (2501.08313)
Model here, allows commercial use <100M monthly users š MiniMaxAI/MiniMax-Text-01
liked
a
Space
28 days ago
liked
2
models
about 1 month ago
liked
a
dataset
about 1 month ago
liked
a
model
3 months ago
liked
a
model
6 months ago
liked
a
model
about 1 year ago
liked
a
dataset
about 1 year ago