119 6 1509

Cross

dillfrescott

https://dill.moe

dillfrescott

AI & ML interests

AI, anime, computers

Recent Activity

liked a model 3 days ago

tencent/HunyuanVideo-I2V

liked a model 3 days ago

THUDM/CogView4-6B

liked a model 3 days ago

amd/Instella-3B-Instruct

View all activity

Organizations

dillfrescott's activity

liked 3 models 3 days ago

liked a model 4 days ago

Qwen/QwQ-32B

Text Generation • Updated about 2 hours ago • 132k • • 1.82k

liked a model 6 days ago

Qwen/Qwen2.5-32B-Instruct

Text Generation • Updated Sep 25, 2024 • 512k • • 232

liked a model 7 days ago

bartowski/qihoo360_TinyR1-32B-Preview-v0.1-GGUF

Text Generation • Updated 10 days ago • 3.75k • 6

liked 2 models 8 days ago

microsoft/Phi-4-multimodal-instruct

Automatic Speech Recognition • Updated 3 days ago • 303k • 1.06k

Wan-AI/Wan2.1-I2V-14B-480P

Image-to-Video • Updated 12 days ago • 257k • 111

liked 2 models 9 days ago

Wan-AI/Wan2.1-T2V-1.3B-Diffusers

Text-to-Video • Updated 7 days ago • 4.78k • 18

moonshotai/Moonlight-16B-A3B-Instruct

Text Generation • Updated 7 days ago • 4.21k • 127

reacted to jasoncorkill's post with ❤️🚀👍 10 days ago

Post

3812

Has OpenGVLab Lumina Outperformed OpenAI’s Model?

We’ve just released the results from a large-scale human evaluation (400k annotations) of OpenGVLab’s newest text-to-image model, Lumina. Surprisingly, Lumina outperforms OpenAI’s DALL-E 3 in terms of alignment, although it ranks #6 in our overall human preference benchmark.

To support further development in text-to-image models, we’re making our entire human-annotated dataset publicly available. If you’re working on model improvements and need high-quality data, feel free to explore.

We welcome your feedback and look forward to any insights you might share!

Rapidata/OpenGVLab_Lumina_t2i_human_preference