Falah commited on
Commit
d948e42
1 Parent(s): 39871c2
Files changed (1) hide show
  1. README.md +5 -4
README.md CHANGED
@@ -16,7 +16,8 @@ tags:
16
 
17
  # Stable Diffusion Prompts Generation Model
18
 
19
- This Hugging Face model, named "Falah/stable_diffusion_prompts_gen", is designed for generating illustration art style prompts using the Stable Diffusion tool for text-to-image generation. It utilizes the custom dataset "Falah/stable_diffusion_prompts_dataset" to generate creative and coherent text prompts.
 
20
 
21
  ## Examples
22
 
@@ -29,9 +30,9 @@ from transformers import AutoTokenizer, AutoModelForCausalLM
29
  model_name = "Falah/stable_diffusion_prompts_gen"
30
  dataset_name = "Falah/stable_diffusion_prompts_dataset"
31
  prompt = r'a beautiful female' # the beginning of the prompt
32
- temperature = 0.9 # a higher temperature will produce more diverse results, but with a higher risk of less coherent text
33
  top_k = 8 # the number of tokens to sample from at each step
34
- max_length = 100 # the maximum number of tokens for the output of the model
35
  repetition_penalty = 1.2 # the penalty value for each repetition of a token
36
  num_return_sequences = 5 # the number of results to generate
37
 
@@ -54,7 +55,7 @@ print('\033[96m' + prompt + '\033[0m')
54
  for i in range(len(output)):
55
  print(tokenizer.decode(output[i], skip_special_tokens=True) + '\n')
56
  ```
57
- These are examples for prompts generating and testing the model with web site![stable diffusion sdxl](https://clipdrop.co/) for the stable diffusion model
58
  generating images from prompts
59
 
60
  ```
 
16
 
17
  # Stable Diffusion Prompts Generation Model
18
 
19
+ This model is designed for generating illustration art style prompts for the Stable Diffusion tool for text-to-image generation.
20
+ It utilizes the custom dataset "Falah/stable_diffusion_prompts_dataset" to generate creative and coherent text prompts.
21
 
22
  ## Examples
23
 
 
30
  model_name = "Falah/stable_diffusion_prompts_gen"
31
  dataset_name = "Falah/stable_diffusion_prompts_dataset"
32
  prompt = r'a beautiful female' # the beginning of the prompt
33
+ temperature = 0.9 # A higher temperature will produce more diverse results, but with a higher risk of less coherent text
34
  top_k = 8 # the number of tokens to sample from at each step
35
+ max_length = 200 # the maximum number of tokens for the output of the model
36
  repetition_penalty = 1.2 # the penalty value for each repetition of a token
37
  num_return_sequences = 5 # the number of results to generate
38
 
 
55
  for i in range(len(output)):
56
  print(tokenizer.decode(output[i], skip_special_tokens=True) + '\n')
57
  ```
58
+ These are examples of prompts generating and testing the model with the website [Link Text](https://clipdrop.co/) for the stable diffusion model
59
  generating images from prompts
60
 
61
  ```