AI Disruption
Subscribe
Sign in
Home
Podcast
Chat
Chip
Meta
Paper
Qwen
Agent
Robot
OpenAI
YouTube
AI Code
AI Video
AI Weekly
Elon Musk
AI Writing
AI Painting
AI Business
🎈 Guest Posts
AI Open Source
Machine Learning
Chinese Outbound
Foundation Model
Archive
About
AI Painting
Latest
Top
Discussions
Google Gemini's Native Image Output Launches First, Erasing OpenAI's One-Year Lead
Explore Gemini's game-changing text-to-image model with unmatched controllability. Discover tips for seamless edits, local modifications, and AI-driven…
2 hrs ago
Â
•
Â
Meng Li
2
Share this post
AI Disruption
Google Gemini's Native Image Output Launches First, Erasing OpenAI's One-Year Lead
Copy link
Facebook
Email
Notes
More
Llama Boosts Multimodal Performance by 30% with Diffusion's Attention Distribution
Boost Llama-3.2's multimodal performance by 30% with Stable Diffusion’s attention distribution. Achieve high accuracy with minimal data and training…
Feb 17
Â
•
Â
Meng Li
3
Share this post
AI Disruption
Llama Boosts Multimodal Performance by 30% with Diffusion's Attention Distribution
Copy link
Facebook
Email
Notes
More
MakeAnything Unlocks Multi-task Process Generation with Diffusion Transformer
MakeAnything combines Diffusion Transformer and asymmetric LoRA to unlock cross-domain, high-quality multi-task process generation, achieving…
Feb 16
Â
•
Â
Meng Li
2
Share this post
AI Disruption
MakeAnything Unlocks Multi-task Process Generation with Diffusion Transformer
Copy link
Facebook
Email
Notes
More
OpenAI Tests Sora Image Generator, Codename "Papaya" – Is DALL-E 4 Coming Soon?
OpenAI is testing Sora's image generation, codenamed "Papaya," with a new toggle for video and image creation. Could DALL-E 4 be coming soon?
Feb 9
Â
•
Â
Meng Li
Share this post
AI Disruption
OpenAI Tests Sora Image Generator, Codename "Papaya" – Is DALL-E 4 Coming Soon?
Copy link
Facebook
Email
Notes
More
DeepSeek Releases Image-Video Large Model Janus-Pro-7B, Competing with OpenAI DALL-E 3
DeepSeek’s multimodal tech revolutionizes AI, with Janus-Pro surpassing DALL-E 3 in performance. Explore efficient, open-source models for advanced…
Jan 28
Â
•
Â
Meng Li
2
Share this post
AI Disruption
DeepSeek Releases Image-Video Large Model Janus-Pro-7B, Competing with OpenAI DALL-E 3
Copy link
Facebook
Email
Notes
More
MetaMorph: Unified Visual Understanding and Generation by LeCun
Explore MetaMorph, a multimodal AI model merging visual understanding and generation. Discover insights from LeCun, Xie, Liu, and others.
Dec 21, 2024
Â
•
Â
Meng Li
1
Share this post
AI Disruption
MetaMorph: Unified Visual Understanding and Generation by LeCun
Copy link
Facebook
Email
Notes
More
Gemini 2.0: One-Sentence Image Editing Tool that Has Netizens Envious
Gemini 2.0 revolutionizes image editing with one-click commands. Transform objects, combine images, and create imaginative edits using just your voice.
Dec 16, 2024
Â
•
Â
Meng Li
2
Share this post
AI Disruption
Gemini 2.0: One-Sentence Image Editing Tool that Has Netizens Envious
Copy link
Facebook
Email
Notes
More
PaliGemma 2: Google's Multi-Scale Lightweight Vision-Language Model
Discover PaliGemma 2: Google's lightweight, multi-scale vision-language model, ideal for image-text tasks, content creation, and AI development…
Dec 8, 2024
Â
•
Â
Meng Li
2
Share this post
AI Disruption
PaliGemma 2: Google's Multi-Scale Lightweight Vision-Language Model
Copy link
Facebook
Email
Notes
More
IC-Light: A Perfect [10, 10, 10, 10] ICLR Paper by ControlNet Creator, Now with 6k Stars on GitHub
IC-Light improves illumination editing accuracy, preserving image details across diverse lighting conditions and applications like normal map…
Dec 1, 2024
Â
•
Â
Meng Li
2
Share this post
AI Disruption
IC-Light: A Perfect [10, 10, 10, 10] ICLR Paper by ControlNet Creator, Now with 6k Stars on GitHub
Copy link
Facebook
Email
Notes
More
DeepSeek Launches JanusFlow: A 1.3B Model Unifying Visual Understanding and Generation
JanusFlow unifies visual understanding and generation in a 1.3B LLM, integrating vision encoders and Rectified Flow for multimodal AI breakthroughs.
Nov 22, 2024
Â
•
Â
Meng Li
2
Share this post
AI Disruption
DeepSeek Launches JanusFlow: A 1.3B Model Unifying Visual Understanding and Generation
Copy link
Facebook
Email
Notes
More
OmniGen Unifies Image Generation with a Highly Simplified and User-Friendly Architecture
OmniGen unifies image generation tasks into a simplified, user-friendly model, supporting text-to-image, editing, and more without additional plugins.
Oct 29, 2024
Â
•
Â
Meng Li
1
Share this post
AI Disruption
OmniGen Unifies Image Generation with a Highly Simplified and User-Friendly Architecture
Copy link
Facebook
Email
Notes
More
Free Trial of Flux-1.1 Pro: The Most Advanced AI Art Model Has Just Launched!
Experience the speed and quality of Flux 1.1 Pro, the latest AI text-to-image model, delivering 6x faster results with stunning visuals. Free trials…
Oct 6, 2024
Â
•
Â
Meng Li
2
Share this post
AI Disruption
Free Trial of Flux-1.1 Pro: The Most Advanced AI Art Model Has Just Launched!
Copy link
Facebook
Email
Notes
More
Share
Copy link
Facebook
Email
Notes
More
This site requires JavaScript to run correctly. Please
turn on JavaScript
or unblock scripts