HugeFighter commited on
Commit
076b02e
1 Parent(s): 8f5f7ba

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +24 -3
README.md CHANGED
@@ -16,9 +16,9 @@ widget:
16
  environment) teeming with life and excitement.
17
  ---
18
 
19
- # DreamBooth model for the trex concept trained by HugeFighter on the HugeFighter/dreambooth-hackathon-images dataset.
20
-
21
- This is a Stable Diffusion model fine-tuned on the trex concept with DreamBooth. It can be used by modifying the `instance_prompt`: **a photo of trex dinosaur**
22
 
23
  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!
24
 
@@ -37,3 +37,24 @@ pipeline = StableDiffusionPipeline.from_pretrained('HugeFighter/trex-dinosaur')
37
  image = pipeline().images[0]
38
  image
39
  ```
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
16
  environment) teeming with life and excitement.
17
  ---
18
 
19
+ # A DreamBooth model capable of spectacular/cinematic visuals of Tyrannosaurus rex (the most famous and feared of all prehistoric predators) dinosaur image generator.
20
+ Trained by {api.whoami()["name"]} on the {dataset_id} dataset, This is a Stable Diffusion model fine-tuned on the {name_of_your_concept} concept with DreamBooth.
21
+ It can be used by modifying the `instance_prompt`: **{instance_prompt}**
22
 
23
  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!
24
 
 
37
  image = pipeline().images[0]
38
  image
39
  ```
40
+
41
+ ### Dataset Summary: T.Rex generator
42
+ This dataset includes 12 images of trex collected randomly from web.
43
+ The dataset contains unique photographs of trex with different backgrounds.
44
+ I won't recommend this using these images as your training data (small dataset), but you can still use it for sampling purpose.
45
+
46
+ The dataset is intended to be used in the context of the Hugging Face Dream Booth hackathon, a competition that challenges participants to build innovative applications using the Hugging Face transformers library. The submission is for the category of animal.
47
+
48
+ ## Dataset Structure
49
+
50
+ The complete dataset consists of 12 objects, representing 0.01GB of stored data across 12 rows in parquet format.
51
+
52
+ # Examples of output images generated by pipeline
53
+ prompt = "A photo of a trex dinosaur, wandering over Jurassic park with a big roar"
54
+ ![Jurassic.png](https://github.com/sivianil/diffusers/blob/6d2a6baf80aa44a81b1c165dc8915f8bc56f3dd5/Jurassic.png)
55
+
56
+ prompt = "Photorealistic trex dinosaur, (Jurassic Park) lush greenery, towering prehistoric ferns, dramatic lighting casting shadows, (intense expression), rugged texture of scales, ferocious stance, misty atmosphere, high-quality detail, 4K, (cinematic depth), vibrant colors of nature, embedding a sense of ancient history, (dynamic environment) teeming with life and excitement."
57
+ ![Trex_11.jpg](https://github.com/sivianil/diffusers/blob/539dc890840de9f65fba25a4beb82f4d31a8d2f2/Trex_11.jpg)
58
+
59
+
60
+