@umituz/react-native-ai-fal-provider 2.0.11 → 2.0.15

package/src/domain/constants/models/image-to-video.README.md

@@ -1,266 +0,0 @@
-# Image-to-Video Generation
-
-Transforms static images into moving videos.
-
-**Location:** `src/domain/constants/models/image-to-video.ts`
-
-## Overview
-
-Image-to-video generation animates static images to create video content using AI models. This module provides model configurations for converting images into videos with various camera movements and durations.
-
-## Purpose
-
-Provides image-to-video models by:
-- Animating static images
-- Supporting camera movements
-- Enabling configurable durations
-- Providing various aspect ratios
-- Maintaining image quality in video
-
-## Import
-
-```typescript
-import {
-  falProvider,
-  useFalGeneration
-} from '@umituz/react-native-ai-fal-provider';
-```
-
-## Available Models
-
-### Kling I2V
-- **Model ID:** `fal-ai/kling-video/v1.5/pro/image-to-video`
-- **Cost:** 15 credits (Free), 8 credits (Premium)
-- **Description:** High-quality image-to-video generation (Default)
-- **Use Cases:** Professional image animation, high-quality output
-
-## Parameters
-
-### Common Parameters
-
-| Parameter | Type | Description | Default |
-|-----------|------|-------------|---------|
-| `image_url` | `string` | Source image (base64 or URL) | - |
-| `prompt` | `string` | Description of desired motion/action | - |
-| `aspect_ratio` | `string` | Video aspect ratio | `16:9` |
-| `duration` | `number` | Video duration in seconds | 5 |
-| `fps` | `number` | Frame rate | 24 |
-
-### Aspect Ratios
-
-- `16:9`: Horizontal (landscape)
-- `9:16`: Vertical (portrait)
-- `1:1`: Square
-
-### Camera Movements
-
-**Movement Types:**
-- `pan`: Horizontal panning
-- `tilt`: Vertical tilting
-- `zoom`: Zoom in/out
-- `dolly`: Forward/backward movement
-- `static`: Fixed camera
-
-## Usage Guidelines
-
-### For Image Animation
-
-**Animation Pattern:**
-1. Select high-quality source image
-2. Describe desired motion in prompt
-3. Set appropriate aspect ratio
-4. Configure duration and frame rate
-5. Specify camera movement type
-6. Handle generation result
-
-**Best Practices:**
-- Use high-resolution source images (min 512x512)
-- Focus on specific, achievable motions
-- Describe subtle movements
-- Match camera movement to subject
-- Keep prompts concise
-
-### For Image Selection
-
-**Selection Pattern:**
-1. Evaluate image quality
-2. Check resolution and clarity
-3. Identify focal point
-4. Assess lighting conditions
-5. Verify suitability for animation
-
-**Image Guidelines:**
-- Minimum 512x512 resolution
-- Well-lit and clear focus
-- Distinct subject or focal point
-- Good contrast
-- Appropriate composition
-
-## Best Practices
-
-### 1. Select Quality Source Images
-
-Choose appropriate images:
-- Use high-resolution images
-- Ensure good lighting
-- Check focus clarity
-- Verify distinct subjects
-- Assess composition quality
-
-### 2. Write Concise Motion Prompts
-
-Describe movement effectively:
-- Focus on one or two actions
-- Use movement-oriented language
-- Describe subtle changes
-- Include atmospheric details
-- Keep prompts brief
-
-**Prompt Guidelines:**
-- Be specific: "Person slowly smiling" not "Person happy"
-- Add atmosphere: "Wind blowing", "Light changing"
-- Focus on achievable motions
-- Describe natural movements
-
-### 3. Choose Appropriate Camera Movements
-
-Select movement types carefully:
-- Static: Portraits, subtle expressions
-- Pan: Landscapes, wide scenes
-- Zoom: Focusing on subjects
-- Tilt: Vertical scans
-- Dolly: Forward/backward motion
-
-### 4. Optimize Parameters
-
-Balance quality and performance:
-- Shorter durations (3-5s) for quick results
-- Standard fps (24) for most use cases
-- Higher fps (30) for smooth motion
-- Match aspect ratio to platform
-- Adjust duration to content
-
-### 5. Handle Edge Cases
-
-Manage challenging scenarios:
-- NSFW content detection
-- Invalid image formats
-- Unsupported resolutions
-- Generation failures
-- Timeout handling
-
-## For AI Agents
-
-### When Using Image-to-Video Models
-
-**DO:**
-- Validate source image quality
-- Check image resolution
-- Write concise motion prompts
-- Select appropriate camera movements
-- Handle NSFW content errors
-- Validate image format
-- Check aspect ratio compatibility
-- Test with shorter durations
-
-**DON'T:**
-- Use low-resolution images
-- Write complex multi-action prompts
-- Ignore camera movement selection
-- Skip image validation
-- Forget error handling
-- Use excessive durations
-- Ignore aspect ratios
-- Assume all images work
-
-### When Writing Prompts
-
-**DO:**
-- Keep prompts concise (1-2 actions)
-- Focus on specific movements
-- Use descriptive motion language
-- Include subtle atmospheric details
-- Describe natural movements
-- Be explicit about pace
-- Reference subject features
-
-**DON'T:**
-- Write long complex prompts
-- Describe multiple simultaneous actions
-- Use vague motion descriptions
-- Skip movement details
-- Include contradictory elements
-- Overcomplicate descriptions
-- Forget subject specifics
-
-### When Selecting Images
-
-**DO:**
-- Check minimum resolution (512x512)
-- Verify image quality
-- Ensure good lighting
-- Identify clear focal point
-- Assess composition
-- Validate image format
-- Test image suitability
-
-**DON'T:**
-- Use low-quality images
-- Skip resolution checks
-- Ignore lighting conditions
-- Use blurry images
-- Forget focal point
-- Use unsupported formats
-- Assume any image works
-
-### When Configuring Parameters
-
-**DO:**
-- Start with shorter durations (3-5s)
-- Use standard fps (24) initially
-- Match aspect ratio to platform
-- Test camera movement types
-- Adjust based on content
-- Consider file size
-- Optimize for use case
-
-**DON'T:**
-- Use maximum duration initially
-- Skip camera movement selection
-- Ignore aspect ratio requirements
-- Set excessive frame rates
-- Forget platform constraints
-- Use one-size-fits-all approach
-- Waste credits on long tests
-
-## Implementation Notes
-
-**Location:** `src/domain/constants/models/image-to-video.ts`
-
-**Dependencies:**
-- FAL provider service
-- useFalGeneration hook
-- Image format utilities
-- NSFW validators
-- Progress tracking utilities
-
-**Supported Operations:**
-- Single image animation
-- Camera movement control
-- Duration and fps configuration
-- Aspect ratio selection
-- Format validation
-
-**Import:**
-```typescript
-import {
-  falProvider,
-  useFalGeneration
-} from '@umituz/react-native-ai-fal-provider';
-```
-
-**Related:**
-- FAL provider: `src/infrastructure/services/fal-provider.ts`
-- Generation hook: `src/presentation/hooks/use-fal-generation.ts`
-- Image utilities: `src/infrastructure/utils/helpers.util.ts`
-- NSFW validator: `src/infrastructure/validators/nsfw-validator.ts`

package/src/domain/constants/models/index.README.md

@@ -1,269 +0,0 @@
-# Model Catalog Index
-
-Central export point for all FAL AI model configurations.
-
-**Location:** `src/domain/constants/models/index.ts`
-
-## Overview
-
-The model catalog provides organized access to all available FAL AI models across different generation types. Each model includes detailed configuration such as pricing, availability, and capabilities.
-
-## Purpose
-
-Provides model catalog by:
-- Organizing models by generation type
-- Exporting all model configurations
-- Supporting model discovery
-- Enabling model comparison
-- Facilitating model selection
-
-## Import
-
-```typescript
-import {
-  DEFAULT_TEXT_TO_IMAGE_MODELS,
-  DEFAULT_TEXT_TO_VIDEO_MODELS,
-  DEFAULT_IMAGE_TO_VIDEO_MODELS,
-  DEFAULT_TEXT_TO_VOICE_MODELS,
-  DEFAULT_TEXT_TO_TEXT_MODELS,
-} from '@umituz/react-native-ai-fal-provider';
-```
-
-## Exports
-
-### Text-to-Image Models
-
-Models for generating images from text prompts.
-
-**Documentation:** See `text-to-image.README.md`
-
-**Models:**
-- Flux Schnell (1 credit) - Fast generation
-- Flux Dev (2 credits) - High quality
-- Flux Pro (3 credits) - Professional quality
-
-**Path:** `src/domain/constants/models/text-to-image.ts`
-
-### Text-to-Video Models
-
-Models for generating videos from text descriptions.
-
-**Documentation:** See `text-to-video.README.md`
-
-**Models:**
-- Hunyuan (10 credits) - Balanced quality/speed
-- MiniMax (15 credits) - High quality video
-- Kling 1.5 (20 credits) - Premium video generation
-- Mochi (8 credits) - Fast video generation
-
-**Path:** `src/domain/constants/models/text-to-video.ts`
-
-### Image-to-Video Models
-
-Models for converting images to videos.
-
-**Documentation:** See `image-to-video.README.md`
-
-**Models:**
-- Kling I2V (15 credits) - Professional image-to-video conversion
-
-**Path:** `src/domain/constants/models/image-to-video.ts`
-
-### Text-to-Voice Models
-
-Models for text-to-speech generation.
-
-**Documentation:** See `text-to-voice.README.md`
-
-**Models:**
-- PlayAI TTS v3 (1 credit) - Fast text-to-speech
-- ElevenLabs TTS (2 credits) - High quality TTS
-
-**Path:** `src/domain/constants/models/text-to-voice.ts`
-
-### Text-to-Text Models
-
-Models for text generation and completion.
-
-**Documentation:** See `text-to-text.README.md`
-
-**Models:**
-- Llama 3 8B Instruct (0.1 credits) - General purpose LLM
-
-**Path:** `src/domain/constants/models/text-to-text.ts`
-
-## Usage Guidelines
-
-### For Model Discovery
-
-**Discovery Pattern:**
-1. Import model arrays by type
-2. Filter models based on criteria
-3. Access model configurations
-4. Display model information
-5. Enable user selection
-
-**Best Practices:**
-- Import from package root
-- Use model arrays for UI components
-- Filter by cost, quality, or availability
-- Display pricing information
-- Indicate default models
-
-### For Model Information
-
-**Information Pattern:**
-1. Access model configuration
-2. Read model metadata
-3. Check availability and pricing
-4. Display to users
-5. Guide model selection
-
-**Available Information:**
-- Model ID and name
-- Generation type
-- Pricing (free/premium)
-- Default status
-- Active status
-- Description
-
-## Best Practices
-
-### 1. Use Model IDs Directly
-
-Reference models by ID:
-- Use model IDs from catalog
-- Avoid hardcoding IDs
-- Reference through configuration
-- Maintain single source of truth
-- Update models centrally
-
-### 2. Check Model Availability
-
-Validate model status:
-- Check `isActive` property
-- Handle inactive models
-- Provide fallback options
-- Inform users of issues
-- Update UI accordingly
-
-### 3. Display Cost to Users
-
-Show pricing information:
-- Display credit cost per generation
-- Show free vs premium pricing
-- Calculate batch costs
-- Warn before expensive operations
-- Help users optimize costs
-
-### 4. Respect Default Models
-
-Use default appropriately:
-- Identify default models
-- Use default for new users
-- Enable easy switching
-- Clearly mark defaults
-- Support user preferences
-
-### 5. Enable Model Comparison
-
-Facilitate model selection:
-- Compare by cost
-- Compare by quality
-- Compare by capabilities
-- Show pros and cons
-- Help users choose
-
-## For AI Agents
-
-### When Using Model Catalog
-
-**DO:**
-- Import from package root
-- Use model arrays from catalog
-- Check model availability
-- Display pricing information
-- Respect default models
-- Filter models appropriately
-- Use model IDs from catalog
-
-**DON'T:**
-- Hardcode model IDs
-- Skip availability checks
-- Hide pricing information
-- Ignore default status
-- Create duplicate model lists
-- Import from internal paths
-- Assume model validity
-
-### When Displaying Models
-
-**DO:**
-- Show model names clearly
-- Display pricing information
-- Indicate default models
-- Show availability status
-- Provide descriptions
-- Enable filtering
-- Support comparison
-
-**DON'T:**
-- Hide model information
-- Skip pricing display
-- Ignore defaults
-- Show inactive models
-- Prevent comparison
-- Create confusing UIs
-- Overwhelm users
-
-### When Selecting Models
-
-**DO:**
-- Use default models initially
-- Enable user switching
-- Validate selections
-- Check availability
-- Warn about costs
-- Provide recommendations
-- Support preferences
-
-**DON'T:**
-- Force model selection
-- Skip validation
-- Ignore costs
-- Hide options
-- Remove user control
-- Make arbitrary choices
-- Override user preferences
-
-## Implementation Notes
-
-**Location:** `src/domain/constants/models/index.ts`
-
-**Dependencies:**
-- Re-exports all model type files
-- No external dependencies
-- Pure TypeScript exports
-
-**Export Categories:**
-- Text-to-image models
-- Text-to-video models
-- Image-to-video models
-- Text-to-voice models
-- Text-to-text models
-
-**Import:**
-```typescript
-import {
-  DEFAULT_TEXT_TO_IMAGE_MODELS,
-  DEFAULT_TEXT_TO_VIDEO_MODELS,
-  DEFAULT_IMAGE_TO_VIDEO_MODELS,
-  DEFAULT_TEXT_TO_VOICE_MODELS,
-  DEFAULT_TEXT_TO_TEXT_MODELS,
-} from '@umituz/react-native-ai-fal-provider';
-```
-
-**Related:**
-- Individual model docs: `src/domain/constants/models/*.README.md`
-- Default models: `src/domain/constants/default-models.constants.ts`
-- Feature models: `src/domain/constants/feature-models.constants.ts`