Commit
•
6f26790
1
Parent(s):
2db02cb
Update README.md
Browse files
README.md
CHANGED
|
@@ -18,10 +18,11 @@ widget:
|
|
| 18 |
- **Notebook Repository: https://colab.research.google.com/drive/1EnqpDiKOVYhR0c6f4CgmDg2zqcbYZJpB?usp=sharing**
|
| 19 |
- **Point of Contact: [email protected]**
|
| 20 |
|
|
|
|
| 21 |
|
| 22 |
-
# A DreamBooth model
|
| 23 |
|
| 24 |
-
|
| 25 |
|
| 26 |
This model was created as part of the DreamBooth Hackathon 🔥. Visit the [organisation page](https://huggingface.co/dreambooth-hackathon) for instructions on how to take part!
|
| 27 |
|
|
@@ -47,6 +48,19 @@ Overall, this dataset provides a rich source of visual data for machine learning
|
|
| 47 |
|
| 48 |
By using the golf course images as part of their training data, participants can fine-tune their models to recognize and classify specific features and elements commonly found on golf courses. The image training dataset is stored on decentralized cloud storage (like Storj DCS), increasing its accessibility, performance, and resilience by distributing across an edge of over 17,000 uncorrelated participants. You can find a link to the dataset [here](https://link.storjshare.io/s/juo7ynuvpe5svxj3hh454v6fnhba/golf-courses/)
|
| 49 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 50 |
|
| 51 |
# Examples of image output stored on Storj DCS
|
| 52 |
|
|
@@ -64,20 +78,6 @@ Prompt: "a photo of golf course with the Pyramids of Giza in the background"
|
|
| 64 |
|
| 65 |
|
| 66 |
|
| 67 |
-
### Languages
|
| 68 |
-
|
| 69 |
-
The language data in golf-courses is in English (BCP-47 en)
|
| 70 |
-
|
| 71 |
-
## Dataset Structure
|
| 72 |
-
|
| 73 |
-
The complete dataset is GBs and consists of 21 objects.
|
| 74 |
-
|
| 75 |
-
### Parallelized download using Decentralized Object Storage (Storj DCS)
|
| 76 |
-
|
| 77 |
-
A direct download for the dataset is located at https://link.storjshare.io/juo7ynuvpe5svxj3hh454v6fnhba/golf-courses.
|
| 78 |
-
|
| 79 |
-
In the future, Storj DCS will be used to download large datasets (exceeding 1TB) in a highly parallel, highly performant, and highly economical manner (by utilizing a network of over 17,000 diverse and economically incentivized datacenter node endpoints.
|
| 80 |
-
|
| 81 |
### Curation Rationale
|
| 82 |
|
| 83 |
This model was created as a sample by Kevin Leffew as part of the DreamBooth Hackathon.
|
|
@@ -91,21 +91,4 @@ The source data for the dataset is simply pulled from Unsplash
|
|
| 91 |
MIT License
|
| 92 |
|
| 93 |
## Thanks to John Whitaker and Lewis Tunstall
|
| 94 |
-
Thanks to [John Whitaker](https://github.com/johnowhitaker) and [Lewis Tunstall](https://github.com/lewtun)for writing out and describing the initial hackathon
|
| 95 |
-
|
| 96 |
-
|
| 97 |
-
## Example training images
|
| 98 |
-
|
| 99 |
-
|
| 100 |
-
|
| 101 |
-
|
| 102 |
-
|
| 103 |
-
|
| 104 |
-
|
| 105 |
-
|
| 106 |
-
|
| 107 |
-
|
| 108 |
-
|
| 109 |
-
|
| 110 |
-
|
| 111 |
-
|
|
|
|
| 18 |
- **Notebook Repository: https://colab.research.google.com/drive/1EnqpDiKOVYhR0c6f4CgmDg2zqcbYZJpB?usp=sharing**
|
| 19 |
- **Point of Contact: [email protected]**
|
| 20 |
|
| 21 |
+
|
| 22 |
|
| 23 |
+
# A DreamBooth model to power a historic/mythological golf-course image generator
|
| 24 |
|
| 25 |
+
Trained by bethecloud on the bethecloud/golf-courses dataset, this is a Stable Diffusion model fine-tuned on the golf concept with DreamBooth. It can be used by modifying the `instance_prompt`: **a photo of golf course**
|
| 26 |
|
| 27 |
This model was created as part of the DreamBooth Hackathon 🔥. Visit the [organisation page](https://huggingface.co/dreambooth-hackathon) for instructions on how to take part!
|
| 28 |
|
|
|
|
| 48 |
|
| 49 |
By using the golf course images as part of their training data, participants can fine-tune their models to recognize and classify specific features and elements commonly found on golf courses. The image training dataset is stored on decentralized cloud storage (like Storj DCS), increasing its accessibility, performance, and resilience by distributing across an edge of over 17,000 uncorrelated participants. You can find a link to the dataset [here](https://link.storjshare.io/s/juo7ynuvpe5svxj3hh454v6fnhba/golf-courses/)
|
| 50 |
|
| 51 |
+
### Languages
|
| 52 |
+
|
| 53 |
+
The language data in golf-courses is in English (BCP-47 en)
|
| 54 |
+
|
| 55 |
+
## Dataset Structure
|
| 56 |
+
|
| 57 |
+
The complete dataset is GBs and consists of 21 objects, representing 0.05GB of stored data across 21 in-line segments on Storj DCS.
|
| 58 |
+
|
| 59 |
+
### Parallelized download using Decentralized Object Storage (Storj DCS)
|
| 60 |
+
|
| 61 |
+
A direct download for the dataset is located at https://link.storjshare.io/juo7ynuvpe5svxj3hh454v6fnhba/golf-courses.
|
| 62 |
+
|
| 63 |
+
In the future, Storj DCS will be used to download large datasets (exceeding 1TB) in a highly parallel, highly performant, and highly economical manner (by utilizing a network of over 17,000 diverse and economically incentivized datacenter node endpoints.
|
| 64 |
|
| 65 |
# Examples of image output stored on Storj DCS
|
| 66 |
|
|
|
|
| 78 |
|
| 79 |
|
| 80 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 81 |
### Curation Rationale
|
| 82 |
|
| 83 |
This model was created as a sample by Kevin Leffew as part of the DreamBooth Hackathon.
|
|
|
|
| 91 |
MIT License
|
| 92 |
|
| 93 |
## Thanks to John Whitaker and Lewis Tunstall
|
| 94 |
+
Thanks to [John Whitaker](https://github.com/johnowhitaker) and [Lewis Tunstall](https://github.com/lewtun)for writing out and describing the initial hackathon parametersat https://huggingface.co/dreambooth-hackathon.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|