Rajkumar rawal
AI & ML interests
Recent Activity
Organizations
- PausedFeatured809
Qwen Image Edit
✒809Edit and enhance images based on descriptive instructions
-
Qwen/Qwen-Image-Edit
Image-to-Image • Updated • 73.1k • • 2.31k -
black-forest-labs/FLUX.1-Kontext-dev
Image-to-Image • Updated • 79.2k • • 2.55k - Running on ZeroMCPFeatured1.56k
FLUX.1 Kontext
⚡1.56kKontext image editing on FLUX[dev]
- Runtime error63
DeepseekJanusPro
🚀63Deepseek AI's Janus-Pro-7B: Generate image from text
-
The Leaderboard Illusion
Paper • 2504.20879 • Published • 72 - PausedFeatured809
Qwen Image Edit
✒809Edit and enhance images based on descriptive instructions
- Running on ZeroFeatured897
Qwen Image
🖼897Generate detailed images from your text prompts
- Running2
Full-Stack Fine-Tuning for Q
🧠2Full-Stack Fine-Tuning for the Q Programming Language
-
nvidia/Llama-3_3-Nemotron-Super-49B-v1_5
Text Generation • 50B • Updated • 99.4k • 225 -
unsloth/gpt-oss-120b-GGUF
Text Generation • 117B • Updated • 82.2k • 218 -
unsloth/gpt-oss-20b-GGUF
Text Generation • 21B • Updated • 183k • 604
-
Wan-AI/Wan2.2-T2V-A14B-Diffusers
Text-to-Video • Updated • 138k • • 110 - Running on ZeroMCPFeatured505
Wan 2.2 5B
🚀505Generate videos from text prompts and optional images
-
FunAudioLLM/ThinkSound
Video-to-Video • Updated • 50 - Running on ZeroMCPFeatured318
ThinkSound
🔊318Generate audio for a video from a caption or description
- RunningFeatured28
HunyuanWorld Viewer
📊28Explore 3D worlds by selecting examples or uploading files
-
tencent/HunyuanWorld-1
Image-to-3D • Updated • 3.43k • 416 - Running on Zero3.22k
Hunyuan3D-2.0
🌍3.22kText-to-3D and Image-to-3D Generation
- Running on ZeroFeatured2.06k
Hunyuan3D-2.1
👻2.06kImage-to-3D Generation
-
The Leaderboard Illusion
Paper • 2504.20879 • Published • 72 -
SmolVLM: Redefining small and efficient multimodal models
Paper • 2504.05299 • Published • 205 -
Seedance 1.0: Exploring the Boundaries of Video Generation Models
Paper • 2506.09113 • Published • 107 -
Small Language Models are the Future of Agentic AI
Paper • 2506.02153 • Published • 24
- Running2
Full-Stack Fine-Tuning for Q
🧠2Full-Stack Fine-Tuning for the Q Programming Language
-
nvidia/Llama-3_3-Nemotron-Super-49B-v1_5
Text Generation • 50B • Updated • 99.4k • 225 -
unsloth/gpt-oss-120b-GGUF
Text Generation • 117B • Updated • 82.2k • 218 -
unsloth/gpt-oss-20b-GGUF
Text Generation • 21B • Updated • 183k • 604
-
Wan-AI/Wan2.2-T2V-A14B-Diffusers
Text-to-Video • Updated • 138k • • 110 - Running on ZeroMCPFeatured505
Wan 2.2 5B
🚀505Generate videos from text prompts and optional images
-
FunAudioLLM/ThinkSound
Video-to-Video • Updated • 50 - Running on ZeroMCPFeatured318
ThinkSound
🔊318Generate audio for a video from a caption or description
- RunningFeatured28
HunyuanWorld Viewer
📊28Explore 3D worlds by selecting examples or uploading files
-
tencent/HunyuanWorld-1
Image-to-3D • Updated • 3.43k • 416 - Running on Zero3.22k
Hunyuan3D-2.0
🌍3.22kText-to-3D and Image-to-3D Generation
- Running on ZeroFeatured2.06k
Hunyuan3D-2.1
👻2.06kImage-to-3D Generation
- PausedFeatured809
Qwen Image Edit
✒809Edit and enhance images based on descriptive instructions
-
Qwen/Qwen-Image-Edit
Image-to-Image • Updated • 73.1k • • 2.31k -
black-forest-labs/FLUX.1-Kontext-dev
Image-to-Image • Updated • 79.2k • • 2.55k - Running on ZeroMCPFeatured1.56k
FLUX.1 Kontext
⚡1.56kKontext image editing on FLUX[dev]
-
The Leaderboard Illusion
Paper • 2504.20879 • Published • 72 -
SmolVLM: Redefining small and efficient multimodal models
Paper • 2504.05299 • Published • 205 -
Seedance 1.0: Exploring the Boundaries of Video Generation Models
Paper • 2506.09113 • Published • 107 -
Small Language Models are the Future of Agentic AI
Paper • 2506.02153 • Published • 24
- Runtime error63
DeepseekJanusPro
🚀63Deepseek AI's Janus-Pro-7B: Generate image from text
-
The Leaderboard Illusion
Paper • 2504.20879 • Published • 72 - PausedFeatured809
Qwen Image Edit
✒809Edit and enhance images based on descriptive instructions
- Running on ZeroFeatured897
Qwen Image
🖼897Generate detailed images from your text prompts