CREATIVE AI

Lumina-mGPT: Multimodal Generative Pretraining for Text-to-Image

By

–

06 August 2024 5h51

Lumina-mGPT Illuminate Flexible Photorealistic Text-to-Image Generation with Multimodal Generative Pretraining paper page: https://
huggingface.co/papers/2408.02
657
… We present Lumina-mGPT, a family of multimodal autoregressive models capable of various vision and language tasks, particularly

VidGen-1M: Large-Scale Dataset for Text-to-Video Generation

By

–

06 August 2024 5h34

VidGen-1M A Large-Scale Dataset for Text-to-video Generation paper page: https://
huggingface.co/papers/2408.02
629
… The quality of video-text pairs fundamentally determines the upper bound of text-to-video models. Currently, the datasets used for training these models suffer from significant

ProCreate: Propulsive Energy Diffusion for Creative Image Generation

By

–

06 August 2024 5h21

ProCreate, Dont Reproduce! Propulsive Energy Diffusion for Creative Generation https://
huggingface.co/papers/2408.02
226
… In this paper, we propose ProCreate, a simple and easy-to-implement method to improve sample diversity and creativity of diffusion-based image generative models and to

MeshAnything V2: Artist-Created Mesh Generation with Adjacent Tokenization

By

–

06 August 2024 5h05

MeshAnything V2

Artist-Created Mesh Generation with Adjacent Mesh Tokenization

demo: https://t.co/QXRUqBcyrI

Equipped with the newly proposed Adjacent Mesh Tokenization (AMT), MeshAnything V2 significantly surpasses MeshAnything in both performance and efficiency. MeshAnything… pic.twitter.com/hEnAlVhF8r
— AK (@_akhaliq) 6 août 2024

MeshAnything V2 Artist-Created Mesh Generation with Adjacent Mesh Tokenization demo: https://
huggingface.co/spaces/Yiwen-n
tu/MeshAnythingV2
… Equipped with the newly proposed Adjacent Mesh Tokenization (AMT), MeshAnything V2 significantly surpasses MeshAnything in both performance and efficiency. MeshAnything