|
--- |
|
license: openrail |
|
pipeline_tag: text-to-image |
|
datasets: |
|
- HuggingFaceTB/everyday-conversations-llama3.1-2k |
|
language: |
|
- ab |
|
metrics: |
|
- bertscore |
|
base_model: microsoft/Phi-3.5-vision-instruct |
|
library_name: espnet |
|
tags: |
|
- art |
|
--- |
|
# ImageDream Model Card |
|
|
|
This model card focuses on the model associated with the [ImageDream paper](https://image-dream.github.io/) |
|
|
|
See also: https://github.com/ByteDance/ImageDream for code base. |
|
|
|
## Description of Files |
|
|
|
sd-v2.1-base-4view-ipmv.pt |
|
|
|
- the ImageDream-Pixel diffusion model fine-tuned from [MVDream v2.1](https://huggingface.co/MVDream/MVDream) |
|
|
|
sd-v2.1-base-4view-ipmv-local.pt |
|
|
|
- the ImageDream diffusion model without pixel-controller tuned from [MVDream v2.1](https://huggingface.co/MVDream/MVDream) |
|
|
|
## Citation |
|
|
|
``` |
|
@article{wang2023imagedream, |
|
title={ImageDream: Image-Prompt Multi-view Diffusion for 3D Generation}, |
|
author={Wang, Peng and Shi, Yichun}, |
|
journal={arXiv preprint arXiv:2312.02201}, |
|
year={2023} |
|
} |
|
``` |
|
|
|
## Misuse, Malicious Use, and Out-of-Scope Use |
|
|
|
The model should not be used to intentionally create or disseminate images that create hostile or alienating environments for people. This includes generating images that people would foreseeably find disturbing, distressing, or offensive; or content that propagates historical or current stereotypes. |
