README.md in gen-ai-0.2.3 vs README.md in gen-ai-0.3.0

@@ -19,33 +19,32 @@
     $ gem install gen-ai
 
 ## Usage
 
 Require it in you code:
+
 ```ruby
 require 'gen_ai'
 ```
 
-
-
 ### Feature support
-✅ - Supported  |  ❌ - Not supported  |  🛠️ - Work in progress
 
+✅ - Supported | ❌ - Not supported | 🛠️ - Work in progress
+
 Language models capabilities
 
 | Provider         | Embedding | Completion | Conversation | Sentiment | Summarization |
 | ---------------- | :-------: | :--------: | :----------: | :-------: | :-----------: |
-| **OpenAI**       | ✅        | ✅         | ✅            | 🛠️        | 🛠️             |
-| **Google Palm2** | ✅        | ✅         | ✅            | 🛠️        | 🛠️             |
+| **OpenAI**       |    ✅     |     ✅     |      ✅      |    🛠️     |      🛠️       |
+| **Google Palm2** |    ✅     |     ✅     |      ✅      |    🛠️     |      🛠️       |
 
-
 Image generation model capabilities
 
-| Provider         | Generate  | Variations | Edit         | Upscale   |
-| ---------------- | :-------: | :--------: | :----------: | :-------: |
-| **OpenAI**       | ✅        | ✅         | ✅            | ❌        |
-| **StabilityAI**  | ✅        | ❌         | ✅            | ✅        |
+| Provider        | Generate | Variations | Edit | Upscale |
+| --------------- | :------: | :--------: | :--: | :-----: |
+| **OpenAI**      |    ✅    |     ✅     |  ✅  |   ❌    |
+| **StabilityAI** |    ✅    |     ❌     |  ✅  |   ✅    |
 
 ### Language
 
 Instantiate a language model client by passing a provider name and an API token.
 
@@ -121,55 +120,63 @@
 ```ruby
 result = model.generate('A painting of a dog')
 # => #<GenAI::Result:0x0000000110be6f20...>
 
 result.value
-# => Base64 encoded image
+# => image binary
 
+result.value(:base64)
+# => image in base64
+
 # Save image to file
 File.open('dog.jpg', 'wb') do |f|
-  f.write(Base64.decode64(result.value))
+  f.write(result.value)
 end
 ```
+
 ![dog](https://github.com/alchaplinsky/gen-ai/assets/695947/27a2af5d-530b-4966-94e8-6cdf628b6cac)
 
-
 Get more **variations** of the same image
 
 ```ruby
 result = model.variations('./dog.jpg')
 # => #<GenAI::Result:0x0000000116a1ec50...>
 
 result.value
-# => Base64 encoded image
+# => image binary
 
+result.value(:base64)
+# => image in base64
+
 # Save image to file
 File.open('dog_variation.jpg', 'wb') do |f|
-  f.write(Base64.decode64(result.value))
+  f.write(result.value)
 end
 
 ```
+
 ![dog_variation](https://github.com/alchaplinsky/gen-ai/assets/695947/977f5238-0114-4085-8e61-8f8b356ce308)
 
-
 **Editing** existing images with additional prompt
 
 ```ruby
 result = model.edit('./llama.jpg', 'A cute llama wearing a beret', mask: './mask.png')
 # => #<GenAI::Result:0x0000000116a1ec50...>
 
 result.value
-# => Base64 encoded image
+# => image binary
 
+result.value(:base64)
+# => image in base64
+
 # Save image to file
 File.open('dog_edited.jpg', 'wb') do |f|
-  f.write(Base64.decode64(result.value))
+  f.write(result.value)
 end
 ```
 
 ![llama](https://github.com/alchaplinsky/gen-ai/assets/695947/9c862c6c-428e-463c-b935-ca749a6a33df)
 ![llama_edited](https://github.com/alchaplinsky/gen-ai/assets/695947/070d8e6a-07a0-4ed2-826f-8b9aabd183ae)
-
 
 ## Development
 
 After checking out the repo, run `bin/setup` to install dependencies. Then, run `rake spec` to run the tests. You can also run `bin/console` for an interactive prompt that will allow you to experiment.