Text-to-Image
Diffusers
Safetensors
English
High-Dynamic-Range-Pipeline
Large
lambda
image generation
ai
generative
synthesis
deep-learning
neural-networks
artistic
style transfer
technology
advanced
floral
high dynamic range
future technologies
floral hdr
art
high quality
HDR
Floral
Imagery
Future
Quality
Dynamic
Vision
Dream
Beauty
lambda-technologies-limited
commited on
Update README.md
Browse files
README.md
CHANGED
@@ -140,94 +140,78 @@ Created by: Future Technologies Limited
|
|
140 |
- **Ethical and Responsible Use:** Users must ensure that the model is not exploited for harmful purposes such as generating misleading content, deepfakes, or offensive imagery. Ethical guidelines and responsible practices should be followed in all use cases.
|
141 |
|
142 |
## How to Get Started with the Model
|
143 |
-
|
144 |
-
|
145 |
-
|
146 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
147 |
|
148 |
## Training Details
|
149 |
|
150 |
-
|
151 |
-
|
152 |
-
#### Preprocessing [optional]
|
153 |
-
|
154 |
-
[More Information Needed]
|
155 |
|
156 |
|
157 |
#### Training Hyperparameters
|
158 |
|
159 |
- **Training regime:** bf16 mixed precision <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
160 |
-
-
|
161 |
-
|
162 |
-
### Results
|
163 |
-
|
164 |
-
[More Information Needed]
|
165 |
-
|
166 |
-
#### Summary
|
167 |
-
|
168 |
-
|
169 |
-
|
170 |
-
## Model Examination [optional]
|
171 |
-
|
172 |
-
<!-- Relevant interpretability work for the model goes here -->
|
173 |
-
|
174 |
-
[More Information Needed]
|
175 |
|
176 |
## Environmental Impact
|
177 |
|
178 |
-
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
179 |
-
|
180 |
-
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
181 |
-
|
182 |
- **Hardware Type:** Nividia A100 GPU
|
183 |
- **Hours used:** 45k+
|
184 |
- **Cloud Provider:** Future Technologies Limited
|
185 |
- **Compute Region:** Rajasthan, India
|
186 |
-
- **Carbon Emitted:** 0 (Powered by clean Solar Energy with no harmful or polluting machines used. Environmentally sustainable and eco-friendly!)
|
187 |
-
|
188 |
-
|
189 |
-
### Model Architecture and Objective
|
190 |
-
|
191 |
-
[More Information Needed]
|
192 |
-
|
193 |
-
### Compute Infrastructure
|
194 |
-
|
195 |
-
[More Information Needed]
|
196 |
-
|
197 |
-
#### Hardware
|
198 |
-
|
199 |
-
[More Information Needed]
|
200 |
-
|
201 |
-
#### Software
|
202 |
-
|
203 |
-
[More Information Needed]
|
204 |
-
|
205 |
-
## Citation [optional]
|
206 |
-
|
207 |
-
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
208 |
-
|
209 |
-
**BibTeX:**
|
210 |
-
|
211 |
-
[More Information Needed]
|
212 |
-
|
213 |
-
**APA:**
|
214 |
-
|
215 |
-
[More Information Needed]
|
216 |
-
|
217 |
-
## Glossary [optional]
|
218 |
-
|
219 |
-
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
220 |
-
|
221 |
-
[More Information Needed]
|
222 |
-
|
223 |
-
## More Information [optional]
|
224 |
-
|
225 |
-
[More Information Needed]
|
226 |
-
|
227 |
-
## Model Card Authors [optional]
|
228 |
-
|
229 |
-
[More Information Needed]
|
230 |
-
|
231 |
-
## Model Card Contact
|
232 |
-
|
233 |
-
[More Information Needed]
|
|
|
140 |
- **Ethical and Responsible Use:** Users must ensure that the model is not exploited for harmful purposes such as generating misleading content, deepfakes, or offensive imagery. Ethical guidelines and responsible practices should be followed in all use cases.
|
141 |
|
142 |
## How to Get Started with the Model
|
143 |
+
**Prerequisites:**
|
144 |
+
- **Install necessary libraries:**
|
145 |
+
```
|
146 |
+
pip install pip install transformers diffusers torch Pillow huggingface_hub
|
147 |
+
```
|
148 |
+
- **Code to Use the Model:**
|
149 |
+
|
150 |
+
```
|
151 |
+
from transformers import AutoTokenizer, AutoModelForImageGeneration
|
152 |
+
from diffusers import DiffusionPipeline
|
153 |
+
import torch
|
154 |
+
from PIL import Image
|
155 |
+
import requests
|
156 |
+
from io import BytesIO
|
157 |
+
|
158 |
+
# Your Hugging Face API token
|
159 |
+
API_TOKEN = "your_hugging_face_api_token"
|
160 |
+
|
161 |
+
# Load the model and tokenizer from Hugging Face
|
162 |
+
model_name = "future-technologies/Floral-High-Dynamic-Range"
|
163 |
+
|
164 |
+
# Error handling for model loading
|
165 |
+
try:
|
166 |
+
model = AutoModelForImageGeneration.from_pretrained(model_name, use_auth_token=API_TOKEN)
|
167 |
+
tokenizer = AutoTokenizer.from_pretrained(model_name, use_auth_token=API_TOKEN)
|
168 |
+
except Exception as e:
|
169 |
+
print(f"Error loading model: {e}")
|
170 |
+
exit()
|
171 |
+
|
172 |
+
# Initialize the diffusion pipeline
|
173 |
+
try:
|
174 |
+
pipe = DiffusionPipeline.from_pretrained(model_name, use_auth_token=API_TOKEN)
|
175 |
+
pipe.to("cuda" if torch.cuda.is_available() else "cpu")
|
176 |
+
except Exception as e:
|
177 |
+
print(f"Error initializing pipeline: {e}")
|
178 |
+
exit()
|
179 |
+
|
180 |
+
# Example prompt for image generation
|
181 |
+
prompt = "A futuristic city skyline with glowing skyscrapers during sunset, reflecting the light."
|
182 |
+
|
183 |
+
# Error handling for image generation
|
184 |
+
try:
|
185 |
+
result = pipe(prompt)
|
186 |
+
image = result.images[0]
|
187 |
+
except Exception as e:
|
188 |
+
print(f"Error generating image: {e}")
|
189 |
+
exit()
|
190 |
+
|
191 |
+
# Save or display the image
|
192 |
+
try:
|
193 |
+
image.save("generated_image.png")
|
194 |
+
image.show()
|
195 |
+
except Exception as e:
|
196 |
+
print(f"Error saving or displaying image: {e}")
|
197 |
+
exit()
|
198 |
+
|
199 |
+
print("Image generation and saving successful!")
|
200 |
+
```
|
201 |
|
202 |
## Training Details
|
203 |
|
204 |
+
The **Floral High Dynamic Range (LIGM)** model has been trained on a diverse and extensive dataset containing over 1 billion high-quality images. This vast dataset encompasses a wide range of visual styles and content, enabling the model to generate highly detailed and accurate images. The training process focused on capturing intricate features, dynamic lighting, and complex scenes, which allows the model to produce images with stunning realism and creative potential.
|
|
|
|
|
|
|
|
|
205 |
|
206 |
|
207 |
#### Training Hyperparameters
|
208 |
|
209 |
- **Training regime:** bf16 mixed precision <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
210 |
|
211 |
## Environmental Impact
|
212 |
|
|
|
|
|
|
|
|
|
213 |
- **Hardware Type:** Nividia A100 GPU
|
214 |
- **Hours used:** 45k+
|
215 |
- **Cloud Provider:** Future Technologies Limited
|
216 |
- **Compute Region:** Rajasthan, India
|
217 |
+
- **Carbon Emitted:** 0 (Powered by clean Solar Energy with no harmful or polluting machines used. Environmentally sustainable and eco-friendly!)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|