pearsonkyle commited on
Commit
3899770
·
1 Parent(s): 85f3ffc

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +16 -37
README.md CHANGED
@@ -10,62 +10,41 @@ model-index:
10
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
11
  should probably proofread and complete it, then remove this comment. -->
12
 
13
- # [ArtPrompter](https://pearsonkyle.github.io/Art-Prompter/)
14
 
15
- A [gpt2](https://huggingface.co/gpt2) powered predictive algorithm for making descriptive text prompts for A.I. image generators (e.g. MidJourney, Stable Diffusion, ArtBot, etc). The model was trained on a custom dataset containing 521K MidJourney images corresponding to 212K unique prompts. Simply start a prompt and let the algorithm suggest ways to finish it.
16
 
17
- ![](https://huggingface.co/pearsonkyle/ArtPrompter/resolve/main/starry_night.gif)
18
 
19
- [![Art Prompter Basic](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1HQOtD2LENTeXEaxHUfIhDKUaPIGd6oTR?usp=sharing)
20
-
21
-
22
-
23
- ```python
24
- from transformers import pipeline
25
-
26
- prompter = pipeline('text-generation',model='pearsonkyle/ArtPrompter', tokenizer='gpt2')
27
-
28
- texts = prompter('A portal to a galaxy, view with', max_length=30, num_return_sequences=5)
29
-
30
- for i in range(5):
31
- print(texts[i]['generated_text']+'\n')
32
- ```
33
 
34
  ## Intended uses & limitations
35
 
36
- Build sick prompts and lots of them.. use it to [make animations](https://colab.research.google.com/drive/1Ooe7c87xGMa9oG5BDrFVzYqJLvnoKcyZ?usp=sharing) or a discord bot that can interact with MidJourney.
37
-
38
- [![](https://pearsonkyle.github.io/Art-Prompter/images/discord_bot.png)](https://discord.gg/3S8Taqa2Xy)
39
-
40
 
41
- ## Examples
42
-
43
- - *The entire universe is a simulation,a confessional with a smiling guy fawkes mask, symmetrical, inviting,hyper realistic*
44
-
45
- - *a pug disguised as a teacher. Setting is a class room*
46
-
47
- - *I wish I had an angel For one moment of love I wish I had your angel Your Virgin Mary undone Im in love with my desire Burning angelwings to dust*
48
-
49
- - *The heart of a galaxy, surrounded by stars, magnetic fields, big bang, cinestill 800T,black background, hyper detail, 8k, black*
50
 
 
51
 
52
  ## Training procedure
53
 
54
- ~48 hour of finetune on RTX2080 with 212K unique prompts
55
-
56
  ### Training hyperparameters
57
 
58
  The following hyperparameters were used during training:
59
  - learning_rate: 5e-05
60
- - train_batch_size: 16
61
- - eval_batch_size: 4
62
  - seed: 42
63
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
64
  - lr_scheduler_type: linear
65
- - num_epochs: 50
 
 
 
 
66
 
67
  ### Framework versions
68
 
69
- - Transformers 4.25.1
70
  - Pytorch 1.13.1
71
- - Tokenizers 0.13.2
 
10
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
11
  should probably proofread and complete it, then remove this comment. -->
12
 
13
+ # ArtPrompter
14
 
15
+ This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset.
16
 
17
+ ## Model description
18
 
19
+ More information needed
 
 
 
 
 
 
 
 
 
 
 
 
 
20
 
21
  ## Intended uses & limitations
22
 
23
+ More information needed
 
 
 
24
 
25
+ ## Training and evaluation data
 
 
 
 
 
 
 
 
26
 
27
+ More information needed
28
 
29
  ## Training procedure
30
 
 
 
31
  ### Training hyperparameters
32
 
33
  The following hyperparameters were used during training:
34
  - learning_rate: 5e-05
35
+ - train_batch_size: 32
36
+ - eval_batch_size: 8
37
  - seed: 42
38
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
39
  - lr_scheduler_type: linear
40
+ - num_epochs: 10
41
+
42
+ ### Training results
43
+
44
+
45
 
46
  ### Framework versions
47
 
48
+ - Transformers 4.26.0
49
  - Pytorch 1.13.1
50
+ - Tokenizers 0.13.2