Gwang-kim
Rank:Average Model Cost: $0.0090
Number of Runs: 4,661
Models by this creator
diffusionclip
DiffusionCLIP is a model that combines the power of diffusion models and Clip-based text embeddings to enable robust image manipulation. It takes text descriptions as input and generates corresponding images. This fusion of text-to-image generation allows for more precise and controlled image manipulation. The model uses a two-step approach, first generating latent noise, and then refining it to generate the final image. DiffusionCLIP improves on previous methods by mitigating mode collapse, allowing for diverse image outputs, and producing more accurate and coherent images. Overall, DiffusionCLIP provides a powerful tool for creating and manipulating images based on textual descriptions.
$0.045/run
4.7K
Replicate
datid3d-finetuned-eg3d-models
datid3d-finetuned-eg3d-models
DATID-3D: Diversity-Preserved Domain Adaptation Using Text-to-Image Diffusion for 3D Generative Model Gwanghyun Kim, Se Young Chun CVPR 2023 gwang-kim.github.io/datid_3d We propose DATID-3D, a novel pipeline of text-guided domain adaptation tailored for 3D generative models using text-to-image diffusion models that can synthesize diverse images per text prompt without collecting additional images and camera information for the target domain.** Unlike 3D extensions of prior text-guided domain adaptation methods, our novel pipeline was able to fine-tune the state-of-the-art 3D generator of the source domain to synthesize high resolution, multi-view consistent images in text-guided targeted domains without additional data, outperforming the existing text-guided domain adaptation methods in diversity and text-image correspondence. Furthermore, we propose and demonstrate diverse 3D image manipulations such as one-shot instance-selected adaptation and single-view manipulated 3D reconstruction to fully enjoy diversity in text. Fine-tuned 3D generative models Fine-tuned 3D generative models using DATID-3D pipeline are stored as *.pkl files. You can download the models in our Hugginface model pages. Citation ========================================================
$-/run
0
Huggingface
DiffusionCLIP-LSUN_Bedroom
DiffusionCLIP-LSUN_Bedroom
DiffusionCLIP: Text-Guided Diffusion Models for Robust Image Manipulation - Bedrooms Creators: Gwanghyun Kim, Taesung Kwon, Jong Chul Ye Paper: https://arxiv.org/abs/2110.02711 DiffusionCLIP is a diffusion model which is well suited for image manipulation thanks to its nearly perfect inversion capability, which is an important advantage over GAN-based models. This checkpoint was trained on the "Bedrooms" category of the LSUN Dataset. This checkpoint is most appropriate for manipulation, reconstruction, and style transfer on images of indoor locations, such as bedrooms. The weights should be loaded into the DiffusionCLIP model. Credits Code repository available at: https://github.com/gwang-kim/DiffusionCLIP Citation
$-/run
0
Huggingface
DiffusionCLIP-CelebA_HQ
DiffusionCLIP-CelebA_HQ
DiffusionCLIP: Text-Guided Diffusion Models for Robust Image Manipulation - Faces Creators: Gwanghyun Kim, Taesung Kwon, Jong Chul Ye Paper: https://arxiv.org/abs/2110.02711 DiffusionCLIP is a diffusion model which is well suited for image manipulation thanks to its nearly perfect inversion capability, which is an important advantage over GAN-based models. This checkpoint was trained on the CelebA-HQ Dataset, available on the Hugging Face Hub: https://huggingface.co/datasets/huggan/CelebA-HQ. This checkpoint is most appropriate for manipulation, reconstruction, and style transfer on images of human faces using the DiffusionCLIP model. To use ID loss for preserving Human face identity, you are required to download the pretrained IR-SE50 model from TreB1eN. Additional information is available on the GitHub repository. Credits Code repository available at: https://github.com/gwang-kim/DiffusionCLIP Citation
$-/run
0
Huggingface
dafasfasfa
$-/run
0
Huggingface