Commit
•
cd703db
1
Parent(s):
9ebf9a0
Init readme
Browse files
README.md
CHANGED
|
@@ -1,5 +1,46 @@
|
|
| 1 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
license: other
|
| 3 |
-
license_name: other
|
| 4 |
-
license_link: LICENSE
|
| 5 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
+
datasets:
|
| 3 |
+
- Objaverse
|
| 4 |
+
tags:
|
| 5 |
+
- 3d
|
| 6 |
+
extra_gated_fields:
|
| 7 |
+
Name: text
|
| 8 |
+
Email: text
|
| 9 |
+
Country: text
|
| 10 |
+
Organization or Affiliation: text
|
| 11 |
+
I ALLOW Stability AI to email me about new model releases: checkbox
|
| 12 |
license: other
|
|
|
|
|
|
|
| 13 |
---
|
| 14 |
+
# `Zero123-SAI`
|
| 15 |
+
|
| 16 |
+
## Model Description
|
| 17 |
+
|
| 18 |
+
Zero123-SAI is a model for view-conditioned image generation based on [Zero123](https://github.com/cvlab-columbia/zero123). Following alterations in the dataset rendering procedures and model conditioning strategies, our model demonstrates improved performance when compared to the original Zero123 and its subsequent iteration, Zero123-XL.
|
| 19 |
+
|
| 20 |
+
**Insert nvs comparison image here**
|
| 21 |
+
|
| 22 |
+
## Usage
|
| 23 |
+
|
| 24 |
+
**Add threestudio link and usage here**
|
| 25 |
+
|
| 26 |
+
|
| 27 |
+
## Model Details
|
| 28 |
+
|
| 29 |
+
* **Developed by**: [Stability AI](https://stability.ai/)
|
| 30 |
+
* **Model type**: latent diffusion model.
|
| 31 |
+
* **Finetuned from model**: [lambdalabs/sd-image-variations-diffusers](https://huggingface.co/lambdalabs/sd-image-variations-diffusers)
|
| 32 |
+
* **License**: [StabilityAI Non-Commercial Research Community License](https://huggingface.co/stabilityai/zero123-sai/raw/main/LICENSE). If you want to use this model for your commercial products or purposes, please contact us [here](https://stability.ai/contact) to learn more.
|
| 33 |
+
|
| 34 |
+
### Training Dataset
|
| 35 |
+
|
| 36 |
+
We use renders from the [Objaverse](https://objaverse.allenai.org/objaverse-1.0) dataset, utilizing our enhanced rendering method
|
| 37 |
+
|
| 38 |
+
### Training Infrastructure
|
| 39 |
+
|
| 40 |
+
* **Hardware**: `Zeor123-SAI` was trained on the Stability AI cluster on a single node with 8 A100 80GBs GPUs.
|
| 41 |
+
* **Code Base**: We use our modified version of [the original zero123 repository](https://github.com/cvlab-columbia/zero123).
|
| 42 |
+
|
| 43 |
+
|
| 44 |
+
### Misuse, Malicious Use, and Out-of-Scope Use
|
| 45 |
+
|
| 46 |
+
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.
|