update
Browse files
README.md
CHANGED
@@ -16,7 +16,8 @@ tags:
|
|
16 |
|
17 |
# Stable Diffusion Prompts Generation Model
|
18 |
|
19 |
-
This
|
|
|
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 #
|
33 |
top_k = 8 # the number of tokens to sample from at each step
|
34 |
-
max_length =
|
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
|
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 |
```
|