Who is working on cogvideox-5b turbo
@_akhaliq
-
Daily Papers API Available on Hugging Face
By
–
Daily papers API: https://
huggingface.co/api/daily_pape
rs
… -
Testing FLUX-GIFs Space with SVD Keyframe Interpolation
By
–
can someone try this: https://t.co/CUijpb9yxw
— AK (@_akhaliq) 31 août 2024
with this: https://t.co/2HmLUr5765 pic.twitter.com/1qfC2yRAOHcan someone try this: https://
huggingface.co/spaces/dn6/FLU
X-GIFs
… with this: https://
svd-keyframe-interpolation.github.io -
Official Sapiens Demos Released on Gradio
By
–
official sapiens @Gradio demos are outhttps://t.co/JfwVsF9Nir https://t.co/AONAd6Hzzk
— AK (@_akhaliq) 30 août 2024official sapiens @Gradio demos are out https://
huggingface.co/collections/fa
cebook/sapiens-66d22047daa6402d565cb2fc
… -
Text-Guided Image Colorization Using Stable Diffusion and CLIP
By
–
Text-Guided-Image-Colorization github: https://
github.com/nick8592/Text-
Guided-Image-Colorization
… project utilizes the power of Stable Diffusion (SDXL/SDXL-Light) and the CLIP (Contrastive Language-Image Pre-Training) captioning model to provide an interactive image colorization experience. Users can influence -
CogVideox-5b Integration with Pallaidium and Blender
By
–
CogVideox-5b via Pallaidium and Blender by @tintwotin pic.twitter.com/bYSUqmkZDO
— AK (@_akhaliq) 30 août 2024CogVideox-5b via Pallaidium and Blender by @tintwotin
-
FLUX.1-schnell OpenVINO Support Released for CPU
By
–
FLUX.1-schnell OpenVINO support github: https://
github.com/rupeshs/fastsd
cpu
… -
WavTokenizer: Efficient Acoustic Discrete Codec for Audio Language Models
By
–
WavTokenizer an Efficient Acoustic Discrete Codec Tokenizer for Audio Language Modeling discuss: https://
huggingface.co/papers/2408.16
532
… Language models have been effectively applied to modeling natural signals, such as images, video, speech, and audio. A crucial component of these models is -
SAM2Point: Zero-shot 3D Segmentation Using Segment Anything Model 2
By
–
SAM2Point Segment Any 3D as Videos in Zero-shot and Promptable Manners discuss: https://
huggingface.co/papers/2408.16
768
… We introduce SAM2Point, a preliminary exploration adapting Segment Anything Model 2 (SAM 2) for zero-shot and promptable 3D segmentation. SAM2Point interprets any 3D data as -
Content-Style Composition in Text-to-Image Diffusion Models
By
–
CSGO Content-Style Composition in Text-to-Image Generation discuss: https://
huggingface.co/papers/2408.16
766
… The diffusion model has shown exceptional capabilities in controlled image generation, which has further fueled interest in image style transfer. Existing works mainly focus on training