image s imsages images model fixes new model see dream

2026-01-10 13:16:05 +00:00
parent 6fb0411f56
commit 854b3efd45
9 changed files with 582 additions and 66 deletions
--- a/backend/igny8_core/ai/ai_core.py
+++ b/backend/igny8_core/ai/ai_core.py
@@ -1028,9 +1028,18 @@ class AICore:
            print(f"[AI][{function_name}] Using Nano Banana config: resolution=1k (no width/height)")
        elif runware_model.startswith('bytedance:'):
            # Seedream 4.5 (bytedance:seedream@4.5) - High quality ByteDance model
-            # Uses basic format with just width/height - no steps, CFGScale, or special providerSettings needed
-            # Just use the base inference_task as-is
-            print(f"[AI][{function_name}] Using Seedream 4.5 config: basic format, width={width}, height={height}")
+            # Uses basic format - no steps, CFGScale, negativePrompt, or special providerSettings needed
+            # Remove negativePrompt as it's not supported
+            if 'negativePrompt' in inference_task:
+                del inference_task['negativePrompt']
+            # Enforce minimum size for Seedream (min 3,686,400 pixels ~ 1920x1920)
+            current_pixels = width * height
+            if current_pixels < 3686400:
+                # Use default Seedream square size
+                inference_task['width'] = 2048
+                inference_task['height'] = 2048
+                width, height = 2048, 2048
+            print(f"[AI][{function_name}] Using Seedream 4.5 config: basic format (no negativePrompt), width={inference_task['width']}, height={inference_task['height']}")
        elif runware_model.startswith('runware:'):
            # Hi Dream Full (runware:97@1) - General diffusion, steps 20, CFGScale 7
            inference_task['steps'] = 20
--- a/backend/igny8_core/ai/tasks.py
+++ b/backend/igny8_core/ai/tasks.py
@@ -187,22 +187,42 @@ def process_image_generation_queue(self, image_ids: list, account_id: int = None
    logger.info("[process_image_generation_queue] Step 1: Loading image generation settings")
    from igny8_core.modules.system.ai_settings import AISettings
    from igny8_core.ai.model_registry import ModelRegistry
+    from igny8_core.business.billing.models import AIModelConfig
    
    # Get effective settings
    image_type = AISettings.get_effective_image_style(account)
    image_format = 'webp'  # Default format
    
-    # Get default image model from database
+    # Get user's selected quality tier (from account settings)
+    quality_tier = AISettings.get_effective_quality_tier(account)
+    logger.info(f"[process_image_generation_queue] User's quality tier: {quality_tier}")
+    
+    # Find image model based on quality tier (DYNAMIC from database)
+    model_config = None
+    if quality_tier:
+        model_config = AIModelConfig.objects.filter(
+            model_type='image',
+            quality_tier=quality_tier,
+            is_active=True
+        ).first()
+    
+    # Fallback to default image model if no tier match
+    if not model_config:
        default_model = ModelRegistry.get_default_model('image')
        if default_model:
            model_config = ModelRegistry.get_model(default_model)
-        provider = model_config.provider if model_config else 'openai'
-        model = default_model
+    
+    # Set provider and model from database config
+    if model_config:
+        provider = model_config.provider or 'openai'
+        model = model_config.model_name
    else:
+        # Ultimate fallback (should never happen if database is configured)
+        logger.warning("[process_image_generation_queue] No image model found in database, using fallback")
        provider = 'openai'
        model = 'dall-e-3'
    
-    logger.info(f"[process_image_generation_queue] Using PROVIDER: {provider}, MODEL: {model} from settings")
+    logger.info(f"[process_image_generation_queue] Using PROVIDER: {provider}, MODEL: {model} from AIModelConfig")
    
    # Style to prompt enhancement mapping
    # These style descriptors are added to the image prompt for better results
@@ -225,25 +245,23 @@ def process_image_generation_queue(self, image_ids: list, account_id: int = None
    style_description = STYLE_PROMPT_MAP.get(image_type, STYLE_PROMPT_MAP.get('photorealistic'))
    logger.info(f"[process_image_generation_queue] Style: {image_type} -> prompt enhancement: {style_description[:50]}...")
    
-    # Model-specific landscape sizes (square is always 1024x1024)
-    # For Runware models - based on Runware documentation for optimal results per model
-    # For OpenAI DALL-E 3 - uses 1792x1024 for landscape
-    MODEL_LANDSCAPE_SIZES = {
-        'runware:97@1': '1280x768',   # Hi Dream Full landscape
-        'bria:10@1': '1344x768',       # Bria 3.2 landscape (16:9)
-        'google:4@2': '1376x768',      # Nano Banana landscape (16:9)
-        'dall-e-3': '1792x1024',       # DALL-E 3 landscape
-        'dall-e-2': '1024x1024',       # DALL-E 2 only supports square
-    }
-    DEFAULT_SQUARE_SIZE = '1024x1024'
-    
-    # Get model-specific landscape size for featured images
-    model_landscape_size = MODEL_LANDSCAPE_SIZES.get(model, '1792x1024' if provider == 'openai' else '1280x768')
+    # Load image sizes from AIModelConfig (DYNAMIC from database)
+    # model_config was loaded above based on quality tier
+    if model_config:
+        # Get sizes from database (single source of truth)
+        model_landscape_size = model_config.landscape_size or '1792x1024'
+        model_square_size = model_config.square_size or '1024x1024'
+        logger.info(f"[process_image_generation_queue] Loaded sizes from AIModelConfig: landscape={model_landscape_size}, square={model_square_size}")
+    else:
+        # Fallback sizes if no model config (should never happen)
+        model_landscape_size = '1792x1024'
+        model_square_size = '1024x1024'
+        logger.warning(f"[process_image_generation_queue] No model config, using fallback sizes")
    
    # Featured image always uses model-specific landscape size
    featured_image_size = model_landscape_size
    # In-article images: alternating square/landscape based on position (handled in image loop)
-    in_article_square_size = DEFAULT_SQUARE_SIZE
+    in_article_square_size = model_square_size
    in_article_landscape_size = model_landscape_size
    
    logger.info(f"[process_image_generation_queue] Settings loaded:")
--- a/backend/igny8_core/modules/billing/migrations/0032_historicalaimodelconfig_landscape_size_and_more.py
+++ b/backend/igny8_core/modules/billing/migrations/0032_historicalaimodelconfig_landscape_size_and_more.py
@@ -0,0 +1,38 @@
+# Generated by Django 5.2.10 on 2026-01-10 12:46
+
+from django.db import migrations, models
+
+
+class Migration(migrations.Migration):
+
+    dependencies = [
+        ('billing', '0031_add_seedream_model'),
+    ]
+
+    operations = [
+        migrations.AddField(
+            model_name='historicalaimodelconfig',
+            name='landscape_size',
+            field=models.CharField(blank=True, help_text="Landscape image size for this model (e.g., '1792x1024', '1280x768')", max_length=20, null=True),
+        ),
+        migrations.AddField(
+            model_name='historicalaimodelconfig',
+            name='square_size',
+            field=models.CharField(blank=True, default='1024x1024', help_text="Square image size for this model (e.g., '1024x1024')", max_length=20),
+        ),
+        migrations.AddField(
+            model_name='historicalaimodelconfig',
+            name='valid_sizes',
+            field=models.JSONField(blank=True, default=list, help_text="List of valid sizes for this model (e.g., ['1024x1024', '1792x1024'])"),
+        ),
+        migrations.AlterField(
+            model_name='aimodelconfig',
+            name='quality_tier',
+            field=models.CharField(blank=True, choices=[('basic', 'Basic'), ('quality', 'Quality'), ('quality_option2', 'Quality-Option2'), ('premium', 'Premium')], help_text='basic / quality / premium - for image models', max_length=20, null=True),
+        ),
+        migrations.AlterField(
+            model_name='historicalaimodelconfig',
+            name='quality_tier',
+            field=models.CharField(blank=True, choices=[('basic', 'Basic'), ('quality', 'Quality'), ('quality_option2', 'Quality-Option2'), ('premium', 'Premium')], help_text='basic / quality / premium - for image models', max_length=20, null=True),
+        ),
+    ]
--- a/backend/igny8_core/modules/system/ai_settings.py
+++ b/backend/igny8_core/modules/system/ai_settings.py
@@ -194,7 +194,7 @@ class SystemAISettings(models.Model):
    
    @classmethod
    def get_effective_quality_tier(cls, account=None) -> str:
-        """Get quality_tier, checking account override first (from ai_settings key)"""
+        """Get quality_tier, checking account override first, then default image model"""
        if account:
            # Check consolidated ai_settings first
            try:
@@ -214,6 +214,21 @@ class SystemAISettings(models.Model):
            override = cls._get_account_override(account, 'ai.quality_tier')
            if override is not None:
                return str(override)
+        
+        # No account override - get tier from DEFAULT image model (is_default=True)
+        try:
+            from igny8_core.business.billing.models import AIModelConfig
+            default_model = AIModelConfig.objects.filter(
+                model_type='image',
+                is_default=True,
+                is_active=True
+            ).first()
+            if default_model and default_model.quality_tier:
+                return default_model.quality_tier
+        except Exception as e:
+            logger.debug(f"Could not get default image model tier: {e}")
+        
+        # Ultimate fallback
        return cls.get_instance().default_quality_tier
    
    @staticmethod
--- a/backend/igny8_core/modules/system/integration_views.py
+++ b/backend/igny8_core/modules/system/integration_views.py
@@ -793,23 +793,38 @@ class IntegrationSettingsViewSet(viewsets.ViewSet):
                }
                
            elif integration_type == 'image_generation':
-                # Model-specific landscape sizes
-                MODEL_LANDSCAPE_SIZES = {
-                    'runware:97@1': '1280x768',
-                    'bria:10@1': '1344x768',
-                    'google:4@2': '1376x768',
-                }
+                from igny8_core.business.billing.models import AIModelConfig
+                from igny8_core.modules.system.ai_settings import AISettings
                
-                # Get default image model from AIModelConfig
+                # Get user's quality tier (from account settings)
+                quality_tier = AISettings.get_effective_quality_tier(account)
+                
+                # Find image model based on quality tier (DYNAMIC from database)
+                model_config = None
+                if quality_tier:
+                    model_config = AIModelConfig.objects.filter(
+                        model_type='image',
+                        quality_tier=quality_tier,
+                        is_active=True
+                    ).first()
+                
+                # Fallback to default image model
+                if not model_config:
                    default_model = ModelRegistry.get_default_model('image')
                    if default_model:
                        model_config = ModelRegistry.get_model(default_model)
-                    default_service = model_config.provider if model_config else 'openai'
+                
+                # Extract settings from model config
+                if model_config:
+                    default_service = model_config.provider or 'openai'
+                    default_model = model_config.model_name
+                    model_landscape_size = model_config.landscape_size or '1792x1024'
+                    model_square_size = model_config.square_size or '1024x1024'
                else:
                    default_service = 'openai'
                    default_model = 'dall-e-3'
-                
-                model_landscape_size = MODEL_LANDSCAPE_SIZES.get(default_model, '1280x768')
+                    model_landscape_size = '1792x1024'
+                    model_square_size = '1024x1024'
                
                response_data = {
                    'id': 'image_generation',
@@ -826,8 +841,11 @@ class IntegrationSettingsViewSet(viewsets.ViewSet):
                    'image_format': 'webp',
                    'desktop_enabled': True,
                    'featured_image_size': model_landscape_size,
+                    'in_article_landscape_size': model_landscape_size,
+                    'in_article_square_size': model_square_size,
                    'desktop_image_size': SystemAISettings.get_effective_image_size(account),
                    'using_global': True,
+                    'quality_tier': quality_tier,
                }
            else:
                # Other integration types - return empty
@@ -856,9 +874,11 @@ class IntegrationSettingsViewSet(viewsets.ViewSet):
        1. SystemAISettings (singleton) provides system-wide defaults
        2. AccountSettings (key-value) provides per-account overrides
        3. API keys come from IntegrationProvider (accounts cannot override API keys)
+        4. Model config (sizes, etc.) from AIModelConfig (DYNAMIC, single source of truth)
        """
-        from igny8_core.modules.system.ai_settings import SystemAISettings
+        from igny8_core.modules.system.ai_settings import SystemAISettings, AISettings
        from igny8_core.ai.model_registry import ModelRegistry
+        from igny8_core.business.billing.models import AIModelConfig
        
        account = getattr(request, 'account', None)
        
@@ -868,29 +888,36 @@ class IntegrationSettingsViewSet(viewsets.ViewSet):
            if user and hasattr(user, 'is_authenticated') and user.is_authenticated:
                account = getattr(user, 'account', None)
        
-        # Model-specific landscape sizes
-        MODEL_LANDSCAPE_SIZES = {
-            'runware:97@1': '1280x768',   # Hi Dream Full landscape
-            'bria:10@1': '1344x768',       # Bria 3.2 landscape (16:9)
-            'google:4@2': '1376x768',      # Nano Banana landscape (16:9)
-            'dall-e-3': '1792x1024',       # DALL-E 3 landscape
-            'dall-e-2': '1024x1024',       # DALL-E 2 square only
-        }
-        
        try:
-            # Get default image model from AIModelConfig
+            # Get user's quality tier from account settings (DYNAMIC)
+            quality_tier = AISettings.get_effective_quality_tier(account)
+            
+            # Find image model based on quality tier (DYNAMIC from database)
+            model_config = None
+            if quality_tier:
+                model_config = AIModelConfig.objects.filter(
+                    model_type='image',
+                    quality_tier=quality_tier,
+                    is_active=True
+                ).first()
+            
+            # Fallback to default image model
+            if not model_config:
                default_model = ModelRegistry.get_default_model('image')
                if default_model:
                    model_config = ModelRegistry.get_model(default_model)
-                provider = model_config.provider if model_config else 'openai'
-                model = default_model
+            
+            # Extract settings from model config (SINGLE SOURCE OF TRUTH)
+            if model_config:
+                provider = model_config.provider or 'openai'
+                model = model_config.model_name
+                model_landscape_size = model_config.landscape_size or '1792x1024'
+                model_square_size = model_config.square_size or '1024x1024'
            else:
                provider = 'openai'
                model = 'dall-e-3'
-            
-            # Get model-specific landscape size
-            model_landscape_size = MODEL_LANDSCAPE_SIZES.get(model, '1280x768')
-            default_featured_size = model_landscape_size if provider == 'runware' else '1792x1024'
+                model_landscape_size = '1792x1024'
+                model_square_size = '1024x1024'
            
            # Get image style from SystemAISettings with AccountSettings overrides
            image_style = SystemAISettings.get_effective_image_style(account)
@@ -915,7 +942,7 @@ class IntegrationSettingsViewSet(viewsets.ViewSet):
                if not image_style or image_style in ['natural', 'vivid']:
                    image_style = 'photorealistic'
            
-            logger.info(f"[get_image_generation_settings] Returning: provider={provider}, model={model}, image_style={image_style}")
+            logger.info(f"[get_image_generation_settings] Returning: provider={provider}, model={model}, image_style={image_style}, quality_tier={quality_tier}")
            
            return success_response(
                data={
@@ -927,8 +954,11 @@ class IntegrationSettingsViewSet(viewsets.ViewSet):
                        'max_in_article_images': SystemAISettings.get_effective_max_images(account),
                        'image_format': 'webp',
                        'desktop_enabled': True,
-                        'featured_image_size': default_featured_size,
+                        'featured_image_size': model_landscape_size,
+                        'in_article_landscape_size': model_landscape_size,
+                        'in_article_square_size': model_square_size,
                        'desktop_image_size': SystemAISettings.get_effective_image_size(account),
+                        'quality_tier': quality_tier,
                    }
                },
                request=request
--- a/backend/igny8_core/modules/system/migrations/0024_alter_systemaisettings_default_quality_tier_and_more.py
+++ b/backend/igny8_core/modules/system/migrations/0024_alter_systemaisettings_default_quality_tier_and_more.py
@@ -0,0 +1,19 @@
+# Generated by Django 5.2.10 on 2026-01-10 12:46
+
+from django.db import migrations, models
+
+
+class Migration(migrations.Migration):
+
+    dependencies = [
+        ('system', '0023_systemaisettings_max_allowed_images_and_more'),
+    ]
+
+    operations = [
+        migrations.AlterField(
+            model_name='systemaisettings',
+            name='default_quality_tier',
+            field=models.CharField(choices=[('basic', 'Basic'), ('quality', 'Quality'), ('quality_option2', 'Quality-Option2'), ('premium', 'Premium')], default='basic', help_text='Default quality tier for image generation', max_length=20),
+        ),
+        # Removed DeleteModel for AccountIntegrationOverride - table doesn't exist
+    ]
--- a/backend/igny8_core/modules/system/settings_views.py
+++ b/backend/igny8_core/modules/system/settings_views.py
@@ -621,15 +621,20 @@ class ContentGenerationSettingsViewSet(viewsets.ViewSet):
            # Get system defaults
            system_defaults = SystemAISettings.get_instance()
            
+            # Get default image model (is_default=True) - SINGLE SOURCE OF TRUTH
+            default_image_model = AIModelConfig.get_default_image_model()
+            
+            # Determine default tier from default model (not hardcoded)
+            default_tier = default_image_model.quality_tier if default_image_model else 'basic'
+            
            # Apply account overrides or use system defaults
            temperature = account_settings.get('temperature', system_defaults.temperature)
            max_tokens = account_settings.get('max_tokens', system_defaults.max_tokens)
            image_style = account_settings.get('image_style', system_defaults.image_style)
            max_images = account_settings.get('max_images', system_defaults.max_images_per_article)
-            selected_tier = account_settings.get('quality_tier', system_defaults.default_quality_tier)
            
-            # Get default image model (or model for selected tier)
-            default_image_model = AIModelConfig.get_default_image_model()
+            # Get selected tier: account override > default model's tier
+            selected_tier = account_settings.get('quality_tier') or default_tier
            
            # Try to find model matching selected tier
            selected_model = AIModelConfig.objects.filter(
--- a/backend/igny8_core/utils/ai_processor.py
+++ b/backend/igny8_core/utils/ai_processor.py
@@ -869,8 +869,17 @@ Make sure each prompt is detailed enough for image generation, describing the vi
                del inference_task['height']
                inference_task['resolution'] = '1k'
            elif runware_model.startswith('bytedance:'):
-                # Seedream models use basic format - no steps, CFGScale needed
-                pass
+                # Seedream models use basic format - no steps, CFGScale, negativePrompt needed
+                # Also require minimum 3,686,400 pixels (roughly 1920x1920)
+                if 'negativePrompt' in inference_task:
+                    del inference_task['negativePrompt']
+                # Enforce minimum size for Seedream (min ~1920x1920, use 2048x2048 for square)
+                current_pixels = width * height
+                if current_pixels < 3686400:
+                    # Use default Seedream square size
+                    inference_task['width'] = 2048
+                    inference_task['height'] = 2048
+                    logger.info(f"[AIProcessor.generate_image] Seedream requires min 3.6M pixels, adjusted to 2048x2048")
            elif runware_model.startswith('runware:'):
                # Hi Dream Full - needs steps and CFGScale
                inference_task['steps'] = 30
--- a/docs/90-REFERENCE/IMAGE-GENERATION-GAPS.md
+++ b/docs/90-REFERENCE/IMAGE-GENERATION-GAPS.md
@@ -0,0 +1,373 @@
+# Image Generation System - Comprehensive Gap Analysis
+
+**Date:** January 2026  
+**Status:** Audit Complete  
+**Reviewer:** System Audit
+
+## Executive Summary
+
+This document provides a comprehensive audit of the image generation system, analyzing the flow from model configuration to image delivery, both for manual and automation workflows.
+
+---
+
+## 1. System Architecture Overview
+
+### Current Flow
+```
+User Selects Quality Tier (basic/quality/quality_option2/premium)
+        ↓
+AIModelConfig (database) → provider, model_name, landscape_size, square_size
+        ↓
+process_image_generation_queue (Celery task)
+        ↓
+ai_core.generate_image() → provider-specific handler
+        ↓
+_generate_image_openai() / _generate_image_runware()
+        ↓
+Downloaded to /frontend/public/images/ai-images/
+        ↓
+Image record updated (Images model)
+```
+
+### Image Count Determination
+```
+User sets max_images (1-8) in Site Settings
+        ↓
+AISettings.get_effective_max_images(account)
+        ↓
+generate_image_prompts.py: 1 featured + max_images in_article
+        ↓
+Images created with positions: featured(0) + in_article(0,1,2,3...)
+```
+
+---
+
+## 2. RESOLVED Issues (Previously Fixed)
+
+### ✅ 2.1 Quality Tier Fallback
+- **Issue:** `get_effective_quality_tier()` was returning hardcoded 'basic' instead of default model's tier
+- **Fixed in:** `ai_settings.py` lines 196-232
+- **Solution:** Now falls back to `AIModelConfig.is_default=True` model's `quality_tier`
+
+### ✅ 2.2 Image Sizes from Database
+- **Issue:** `tasks.py` had hardcoded `MODEL_LANDSCAPE_SIZES` dict
+- **Fixed in:** `tasks.py` lines 242-260
+- **Solution:** Now loads `landscape_size` and `square_size` from `AIModelConfig`
+
+### ✅ 2.3 Settings Endpoint Default Tier
+- **Issue:** `settings_views.py` returned hardcoded 'basic' as default tier
+- **Fixed in:** `settings_views.py` lines 616-640
+- **Solution:** Gets `default_tier` from `default_image_model.quality_tier`
+
+### ✅ 2.4 Integration Views Dynamic Sizes
+- **Issue:** Two endpoints in `integration_views.py` had hardcoded size lookup
+- **Fixed:** Both endpoints now load from `AIModelConfig`
+
+---
+
+## 3. REMAINING Gaps (Action Required)
+
+### 🔴 GAP-1: Hardcoded Size Constants in global_settings_models.py
+
+**Location:** `backend/igny8_core/modules/system/global_settings_models.py` lines 180-188
+
+**Code:**
+```python
+# Model-specific landscape sizes (square is always 1024x1024 for all models)
+MODEL_LANDSCAPE_SIZES = {
+    'runware:97@1': '1280x768',   # Hi Dream Full landscape
+    'bria:10@1': '1344x768',       # Bria 3.2 landscape (16:9)
+    'google:4@2': '1376x768',      # Nano Banana landscape (16:9)
+}
+
+# Default square size (universal across all models)
+DEFAULT_SQUARE_SIZE = '1024x1024'
+```
+
+**Impact:** These constants are UNUSED but could cause confusion. They're legacy from before the AIModelConfig migration.
+
+**Recommendation:** 
+- [ ] Remove unused `MODEL_LANDSCAPE_SIZES` dict
+- [ ] Remove unused `DEFAULT_SQUARE_SIZE` constant
+- [ ] Add deprecation comment if keeping for reference
+
+---
+
+### 🔴 GAP-2: Hardcoded Size Fallbacks in Tasks
+
+**Location:** `backend/igny8_core/ai/tasks.py` lines 254-260
+
+**Code:**
+```python
+else:
+    # Fallback sizes if no model config (should never happen)
+    model_landscape_size = '1792x1024'
+    model_square_size = '1024x1024'
+    logger.warning(f"[process_image_generation_queue] No model config, using fallback sizes")
+```
+
+**Impact:** LOW - Fallback only triggers if database is misconfigured. But the hardcoded sizes may not match actual model requirements.
+
+**Recommendation:**
+- [ ] Consider failing gracefully with clear error instead of using fallback
+- [ ] Or: Load fallback from a system default in database
+
+---
+
+### 🔴 GAP-3: Frontend VALID_SIZES_BY_MODEL Hardcoded
+
+**Location:** `frontend/src/components/common/ImageGenerationCard.tsx` lines 52-55
+
+**Code:**
+```tsx
+const VALID_SIZES_BY_MODEL: Record<string, string[]> = {
+  'dall-e-3': ['1024x1024', '1024x1792', '1792x1024'],
+  'dall-e-2': ['256x256', '512x512', '1024x1024'],
+};
+```
+
+**Impact:** MEDIUM - Test image generation card only shows OpenAI sizes, not Runware/Bytedance sizes.
+
+**Recommendation:**
+- [ ] Fetch valid_sizes from AIModelConfig via API
+- [ ] Or: Pass sizes from backend settings endpoint
+
+---
+
+### 🔴 GAP-4: Backend VALID_SIZES_BY_MODEL Hardcoded
+
+**Location:** `backend/igny8_core/ai/constants.py` lines 40-43
+
+**Code:**
+```python
+VALID_SIZES_BY_MODEL = {
+    'dall-e-3': ['1024x1024', '1024x1792', '1792x1024'],
+    'dall-e-2': ['256x256', '512x512', '1024x1024'],
+}
+```
+
+**Impact:** MEDIUM - Used for OpenAI validation only. Runware models bypass this validation.
+
+**Status:** PARTIAL - Only affects OpenAI validation. Runware has its own validation via provider-specific code.
+
+**Recommendation:**
+- [ ] Move validation to AIModelConfig.valid_sizes field
+- [ ] Validate against model's valid_sizes from database
+
+---
+
+### 🔴 GAP-5: Missing Runware Model Size Validation
+
+**Location:** `backend/igny8_core/ai/ai_core.py` lines 943-1050
+
+**Code:** The `_generate_image_runware()` method does NOT validate sizes against `valid_sizes` from database.
+
+**Impact:** LOW - Runware API will reject invalid sizes anyway, but error message won't be clear.
+
+**Recommendation:**
+- [ ] Add validation: check `size` against `AIModelConfig.valid_sizes` before API call
+- [ ] Return clear error: "Size X is not valid for model Y"
+
+---
+
+### 🔴 GAP-6: Seedream Minimum Pixel Validation Hardcoded
+
+**Location:** `backend/igny8_core/ai/ai_core.py` lines 1018-1027
+
+**Code:**
+```python
+elif runware_model.startswith('bytedance:'):
+    # Enforce minimum size for Seedream (min 3,686,400 pixels ~ 1920x1920)
+    current_pixels = width * height
+    if current_pixels < 3686400:
+        # Use default Seedream square size
+        inference_task['width'] = 2048
+        inference_task['height'] = 2048
+```
+
+**Impact:** LOW - This hardcoded check works, but should come from database.
+
+**Recommendation:**
+- [ ] Add `min_pixels` field to AIModelConfig
+- [ ] Check model.min_pixels instead of hardcoded 3686400
+
+---
+
+### 🔴 GAP-7: Provider-Specific Steps/CFGScale Hardcoded
+
+**Location:** `backend/igny8_core/ai/ai_core.py` lines 995-1040
+
+**Code:**
+```python
+if runware_model.startswith('bria:'):
+    inference_task['steps'] = 20
+    # ...
+elif runware_model.startswith('runware:'):
+    inference_task['steps'] = 20
+    inference_task['CFGScale'] = 7
+```
+
+**Impact:** LOW - Works correctly but adding new models requires code changes.
+
+**Recommendation:**
+- [ ] Add `generation_params` JSON field to AIModelConfig
+- [ ] Store steps, CFGScale, etc. in database per model
+
+---
+
+### 🔴 GAP-8: Image Count Not Per-Content Configurable
+
+**Location:** System-wide setting only
+
+**Current Behavior:**
+- `max_images` is a global setting (site-wide)
+- All articles get the same number of in_article images
+
+**Impact:** MEDIUM - Users cannot set different image counts per article/keyword.
+
+**Recommendation:**
+- [ ] Add `images_count` field to Content model (nullable, inherits from site default)
+- [ ] Or: Add to Keywords model for keyword-level override
+
+---
+
+### 🟡 GAP-9: Legacy generate_images.py Function (Partially Dead Code)
+
+**Location:** `backend/igny8_core/ai/functions/generate_images.py`
+
+**Issue:** `generate_images_core()` function exists but appears to be legacy. Main flow uses `process_image_generation_queue()` in tasks.py.
+
+**Impact:** LOW - Code duplication, potential maintenance burden.
+
+**Recommendation:**
+- [ ] Audit if `generate_images.py` is actually used anywhere
+- [ ] If not: Add deprecation warning or remove
+- [ ] If used: Ensure it uses same dynamic config loading
+
+---
+
+### 🟡 GAP-10: No Validation of quality_tier Values
+
+**Location:** Multiple locations
+
+**Issue:** When user selects a quality_tier, there's no validation that:
+1. The tier exists in AIModelConfig
+2. The tier has an active model
+3. The user's plan allows that tier
+
+**Impact:** MEDIUM - Could lead to runtime errors if tier doesn't exist.
+
+**Recommendation:**
+- [ ] Add validation in settings save endpoint
+- [ ] Return error if selected tier has no active model
+
+---
+
+## 4. Image Count Flow (Working Correctly)
+
+### How image count works:
+
+1. **User configures:**
+   - `max_images` (1-8) in Site Settings → saved to AccountSettings
+
+2. **Prompt generation:**
+   ```python
+   # generate_image_prompts.py
+   max_images = AISettings.get_effective_max_images(account)  # e.g., 4
+   # Creates: 1 featured + 4 in_article = 5 image prompts
+   ```
+
+3. **Image types:**
+   - `featured` - Always 1, position=0, landscape size
+   - `in_article` - Up to max_images, positions 0,1,2,3..., alternating square/landscape
+
+4. **Size determination:**
+   ```python
+   # tasks.py
+   if image.image_type == 'featured':
+       image_size = featured_image_size  # landscape
+   elif image.image_type == 'in_article':
+       position = image.position or 0
+       if position % 2 == 0:  # 0, 2
+           image_size = square_size
+       else:  # 1, 3
+           image_size = landscape_size
+   ```
+
+**STATUS:** ✅ Working correctly. No gaps identified in image count logic.
+
+---
+
+## 5. Automation Flow (Working Correctly)
+
+### Stage 6: Image Generation
+
+**Location:** `automation_service.py` lines 1236-1400
+
+**Flow:**
+1. Query `Images.objects.filter(site=site, status='pending')`
+2. For each image: `process_image_generation_queue.delay(image_ids=[image.id], ...)`
+3. Monitor task completion
+4. Update run progress
+
+**STATUS:** ✅ Uses same task as manual generation. Consistent behavior.
+
+---
+
+## 6. Model Provider Support Matrix
+
+| Provider | Models | Status | Gaps |
+|----------|--------|--------|------|
+| OpenAI | dall-e-3, dall-e-2 | ✅ Working | Valid sizes hardcoded |
+| Runware | runware:97@1 | ✅ Working | No size validation |
+| Runware | bria:10@1 | ✅ Working | Steps hardcoded |
+| Runware | google:4@2 | ✅ Working | Resolution param hardcoded |
+| Runware | bytedance:seedream@4.5 | ✅ Working | Min pixels hardcoded |
+
+---
+
+## 7. Priority Action Items
+
+### High Priority
+1. **GAP-4/5:** Implement database-driven size validation for all providers
+2. **GAP-10:** Add quality_tier validation on save
+
+### Medium Priority
+3. **GAP-6/7:** Move provider-specific params to AIModelConfig.generation_params
+4. **GAP-8:** Consider per-content image count override
+
+### Low Priority
+5. **GAP-1:** Clean up unused constants
+6. **GAP-9:** Audit and deprecate legacy code
+7. **GAP-3:** Fetch valid sizes from API in frontend
+
+---
+
+## 8. Recommendations Summary
+
+### Short-term (Before Launch)
+- Ensure all hardcoded fallbacks are clearly logged
+- Test each model tier end-to-end
+
+### Medium-term (Post-Launch)
+- Migrate all hardcoded params to AIModelConfig fields
+- Add model validation on quality_tier save
+
+### Long-term (Future Enhancement)
+- Per-content image count override
+- Per-keyword image style override
+- Image regeneration without deleting existing
+
+---
+
+## Appendix: Key Files Reference
+
+| File | Purpose |
+|------|---------|
+| `ai/tasks.py` | Main image generation Celery task |
+| `ai/ai_core.py` | Provider-specific generation methods |
+| `ai/functions/generate_image_prompts.py` | Extract prompts from content |
+| `modules/system/ai_settings.py` | System defaults + account overrides |
+| `modules/system/settings_views.py` | Frontend settings API |
+| `business/billing/models.py` | AIModelConfig model |
+| `business/automation/services/automation_service.py` | Automation Stage 6 |