roborovski commited on
Commit
5499d96
1 Parent(s): 8974993

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -2
README.md CHANGED
@@ -30,14 +30,14 @@ model = T5ForConditionalGeneration.from_pretrained("roborovski/superprompt-v1",
30
  input_text = "Expand the following prompt to add more detail: A storefront with 'Text to Image' written on it."
31
  input_ids = tokenizer(input_text, return_tensors="pt").input_ids.to("cuda")
32
 
33
- outputs = model.generate(input_ids, max_length=77)
34
  print(tokenizer.decode(outputs[0]))
35
 
36
  # The neon sign above the storefront reads "NeurIPS" in bold, white letters. The storefront is surrounded by a bustling cityscape, with skyscrapers and neon signs lining the walls. The sign is surrounded by a variety of colorful goods, including a variety of fruits, vegetables, and fruits, all arranged in a neat and organized manner. The storefront is surrounded by a bustling crowd of people, all chatting and laughing as they go about their daily routines.
37
 
38
  ```
39
 
40
- It's important that you use the exact task prefix: `Expand the following prompt to add more detail:` and limit the max tokens to 77.
41
 
42
 
43
  ## Examples
 
30
  input_text = "Expand the following prompt to add more detail: A storefront with 'Text to Image' written on it."
31
  input_ids = tokenizer(input_text, return_tensors="pt").input_ids.to("cuda")
32
 
33
+ outputs = model.generate(input_ids, max_new_tokens=77)
34
  print(tokenizer.decode(outputs[0]))
35
 
36
  # The neon sign above the storefront reads "NeurIPS" in bold, white letters. The storefront is surrounded by a bustling cityscape, with skyscrapers and neon signs lining the walls. The sign is surrounded by a variety of colorful goods, including a variety of fruits, vegetables, and fruits, all arranged in a neat and organized manner. The storefront is surrounded by a bustling crowd of people, all chatting and laughing as they go about their daily routines.
37
 
38
  ```
39
 
40
+ It's important that you use the exact task prefix: `Expand the following prompt to add more detail:` and limit the max tokens to 77 - which is the max prompt length for Stable Diffusion models.
41
 
42
 
43
  ## Examples