Genius #design! Even in a world full of AI, human creativity is irreplaceable—it's what truly brings our biggest ideas to life. What do you think? Join the IRREPLACEABLE community and read the Book: http://
irreplaceable.ai
CREATIVE AI
-
Human creativity remains irreplaceable in AI-driven world
By
–
-
Lumina-mGPT: Multimodal Generative Pretraining for Text-to-Image
By
–
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
–
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
–
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
–
MeshAnything V2
— AK (@_akhaliq) 6 août 2024
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/hEnAlVhF8rMeshAnything 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 -
GEN-3 AI model creative results showcase
By
–
Se lo he pasado por GEN-3, disfrute del resultado buen hombre 🙂 pic.twitter.com/HQdMcI6sC8
— Carlos Santana (@DotCSV) 5 août 2024Se lo he pasado por GEN-3, disfrute del resultado buen hombre 🙂
-
The moment I became a FLUX 1.0 believer
By
–
Habéis podido comprobar en este vídeo el momento preciso en el que me he vuelto un believer de FLUX 1.0
-
CogVideoX: High Quality Text to Video Generation
By
–
CogVideoX
— AK (@_akhaliq) 5 août 2024
high quality text to video generationhttps://t.co/7tOM5KU3Ww pic.twitter.com/tInxbQg8fzCogVideoX high quality text to video generation https://
huggingface.co/spaces/THUDM/C
ogVideoX
… -
FLUX 1.0 Model Review: Major Image Generation Breakthrough
By
–
¡NUEVO VÍDEO de NOTICIAS! Y una de las noticias más importantes del año en el panorama de la generación de imágenes. Os hablo y probamos el nuevo modelo FLUX 1.0, que tan contento tiene a la comunidad estos días 🙂 (Link a continuación)
-
Runway Improves GEN-3 Video Generation with Final Frame Control
By
–
🔴 ¡RUNWAY mejora GEN-3!
— Carlos Santana (@DotCSV) 5 août 2024
Con otra funcionalidad más que suma control a las generaciones similar a Luma o Sora, y es el poder generar vídeos no sólo a partir de un fotograma inicial, sino también de uno final.
Atentos a los resultados 👇 https://t.co/RnkH5c2JFJ¡RUNWAY mejora GEN-3! Con otra funcionalidad más que suma control a las generaciones similar a Luma o Sora, y es el poder generar vídeos no sólo a partir de un fotograma inicial, sino también de uno final. Atentos a los resultados