Fold image size into model params

Author: josefarias

docs/_core_features/image-generation.md

@@ -119,7 +119,7 @@ image_portrait = RubyLLM.paint(
 )
 ```
 
-> Not all models support size customization. If a size is specified for a model that doesn't support it (like Google Imagen), RubyLLM may log a debug message indicating the size parameter is ignored. Check the provider's documentation or the [Available Models Guide]({% link _reference/available-models.md %}) for supported sizes.
+> Not all models support size customization. Check the provider's documentation or the [Available Models Guide]({% link _reference/available-models.md %}) for supported sizes.
 {: .note }
 
 ## Working with Generated Images
@@ -277,4 +277,4 @@ Image generation can take several seconds (typically 5-20 seconds depending on t
 
 *   [Chatting with AI Models]({% link _core_features/chat.md %}): Learn about conversational AI.
 *   [Embeddings]({% link _core_features/embeddings.md %}): Explore text vector representations.
-*   [Error Handling]({% link _advanced/error-handling.md %}): Master handling API errors.
+*   [Error Handling]({% link _advanced/error-handling.md %}): Master handling API errors.

lib/ruby_llm/image.rb

@@ -35,16 +35,15 @@ def self.paint(prompt, # rubocop:disable Metrics/ParameterLists
                    model: nil,
                    provider: nil,
                    assume_model_exists: false,
-                   size: '1024x1024',
                    context: nil,
-                   model_params: {})
+                   **model_params)
       config = context&.config || RubyLLM.config
       model ||= config.default_image_model
       model, provider_instance = Models.resolve(model, provider: provider, assume_exists: assume_model_exists,
                                                        config: config)
       model_id = model.id
 
-      provider_instance.paint(prompt, model: model_id, size:, **model_params)
+      provider_instance.paint(prompt, model: model_id, **model_params)
     end
   end
 end

lib/ruby_llm/provider.rb

@@ -76,8 +76,8 @@ def moderate(input, model:)
       parse_moderation_response(response, model:)
     end
 
-    def paint(prompt, model:, size:, **params)
-      payload = render_image_payload(prompt, model:, size:, **params)
+    def paint(prompt, model:, **params)
+      payload = render_image_payload(prompt, model:, **params)
       response = @connection.post images_url, payload
       parse_image_response(response, model:)
     end

lib/ruby_llm/providers/gemini/images.rb

@@ -9,8 +9,7 @@ def images_url
           "models/#{@model}:predict"
         end
 
-        def render_image_payload(prompt, model:, size:)
-          RubyLLM.logger.debug "Ignoring size #{size}. Gemini does not support image size customization."
+        def render_image_payload(prompt, model:, **)
           @model = model
           {
             instances: [

lib/ruby_llm/providers/openai/images.rb

@@ -11,12 +11,12 @@ def images_url
           'images/generations'
         end
 
-        def render_image_payload(prompt, model:, size:)
+        def render_image_payload(prompt, model:, **params)
           {
             model: model,
             prompt: prompt,
             n: 1,
-            size: size
+            size: params.delete(:size) || '1024x1024'
           }
         end
 

lib/ruby_llm/providers/replicate/images.rb

@@ -15,9 +15,7 @@ def images_url
           end
         end
 
-        def render_image_payload(prompt, model:, size:, **params)
-          RubyLLM.logger.debug "Use `model_params` for model-dependent sizing instead of size #{size}." if size
-
+        def render_image_payload(prompt, model:, **params)
           self.model_id = model
 
           {}.tap do |payload|