paintplus: vendor the app source and rename from EditmaskwithAI
Bring the full EditmaskwithAI application into the repo under paintplus/ (429 files) so the service is self-contained — the installer copies the vendored source to ~/docker/paintplus/src instead of cloning at runtime. Rename to PaintPlus (service + branding; app logic untouched): - services/editmaskwithai.sh -> services/paintplus.sh (register_service paintplus, install_paintplus, ~/docker/paintplus, Caddy paintplus:8000, Authelia option preserved) - container names -> paintplus across docker-compose*.yml; dev network -> paintplus-network - browser <title> -> "PaintPlus - AI Image Editor"; README heading -> PaintPlus with upstream provenance note - README utilities table: editmaskwithai -> paintplus Backend/frontend code (help strings referencing the old container name, the ai_photo_edit.db filename) is intentionally left as-is to avoid touching application logic. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01Nb2vJ8W7bHKx1JXVvpCraH
This commit is contained in:
Claude
@@ -0,0 +1,261 @@
|
||||
# AI Provider Cost & Quality Comparison
|
||||
|
||||
## Provider Options for Inpainting/Image Editing
|
||||
|
||||
### 1. OpenAI DALL-E 2 ❌ (Not Recommended)
|
||||
**Current implementation uses this when `AI_PROVIDER=openai`**
|
||||
|
||||
**Pricing:**
|
||||
- $0.020 per image (1024x1024)
|
||||
- $0.018 per image (512x512)
|
||||
|
||||
**Quality:** ⭐⭐ (2/5)
|
||||
- Old model (2022)
|
||||
- Significantly lower quality than DALL-E 3
|
||||
- Cannot match ChatGPT web interface
|
||||
- Often produces artifacts
|
||||
|
||||
**Pros:**
|
||||
- Simple API
|
||||
- Fast responses
|
||||
|
||||
**Cons:**
|
||||
- Poor quality by modern standards
|
||||
- Limited to 1024x1024 max
|
||||
- No access to DALL-E 3 inpainting
|
||||
|
||||
**Verdict:** ❌ Don't use unless you need the cheapest option and quality doesn't matter
|
||||
|
||||
---
|
||||
|
||||
### 2. Stability AI (Stable Diffusion XL) ✅ (Good Choice)
|
||||
**Direct API to Stability AI**
|
||||
|
||||
**Pricing:**
|
||||
- Credits-based system
|
||||
- ~$0.010 per image (512x512)
|
||||
- ~$0.040 per image (1024x1024)
|
||||
- Must buy credit packs ($10 minimum = 1000 credits)
|
||||
|
||||
**Quality:** ⭐⭐⭐⭐ (4/5)
|
||||
- Excellent inpainting quality
|
||||
- Good at following prompts
|
||||
- Natural-looking results
|
||||
- Well-suited for photo editing
|
||||
|
||||
**Pros:**
|
||||
- Built specifically for inpainting
|
||||
- Good quality-to-cost ratio
|
||||
- Reliable API
|
||||
- Fast generation (15-30 seconds)
|
||||
|
||||
**Cons:**
|
||||
- Requires credit purchase upfront
|
||||
- Limited to SDXL models
|
||||
- Less flexible than Replicate
|
||||
|
||||
**Verdict:** ✅ Best balance of quality and cost for direct API
|
||||
|
||||
---
|
||||
|
||||
### 3. Replicate ⭐ (Most Flexible)
|
||||
**API marketplace with multiple models**
|
||||
|
||||
**Pricing:** Pay-per-second of GPU time
|
||||
- SDXL Inpainting: ~$0.0023/sec (~$0.01-0.03 per image)
|
||||
- Kandinsky 2.2: ~$0.0023/sec (~$0.01-0.02 per image)
|
||||
- LaMa (removal): ~$0.0005/sec (~$0.002 per image)
|
||||
- Varies by model and parameters
|
||||
|
||||
**Quality:** ⭐⭐⭐⭐⭐ (5/5 - depends on model choice)
|
||||
- Access to multiple models
|
||||
- Can choose best model for each use case
|
||||
- Community models available
|
||||
- Often better than Stability direct
|
||||
|
||||
**Pros:**
|
||||
- Multiple models to choose from
|
||||
- Pay only for what you use (no minimums)
|
||||
- Can use free models
|
||||
- New models added regularly
|
||||
- Fine-tuned models available
|
||||
|
||||
**Cons:**
|
||||
- More complex to implement
|
||||
- Pricing varies by model
|
||||
- Need to understand different models
|
||||
|
||||
**Best Models on Replicate:**
|
||||
- **SDXL Inpainting**: General purpose, excellent quality
|
||||
- **LaMa**: Best for object removal
|
||||
- **Kandinsky 2.2**: Good alternative to SDXL
|
||||
- **ControlNet Inpainting**: More control over results
|
||||
|
||||
**Verdict:** ⭐ Most flexible, best value if you implement multiple models
|
||||
|
||||
---
|
||||
|
||||
### 4. Local Models (Self-Hosted) 💰 (Best Quality, No Per-Use Cost)
|
||||
|
||||
**Pricing:**
|
||||
- $0 per image after setup
|
||||
- Requires GPU (RTX 3060 12GB minimum, RTX 4090 ideal)
|
||||
- Cloud GPU: $0.30-$1.00/hour (RunPod, Vast.ai)
|
||||
|
||||
**Quality:** ⭐⭐⭐⭐⭐ (5/5)
|
||||
- Best possible quality
|
||||
- Full control over model selection
|
||||
- Can use latest open-source models
|
||||
- No API limitations
|
||||
|
||||
**Setup Costs:**
|
||||
- GPU hardware: $300-$2000
|
||||
- OR Cloud GPU rental: $0.30-$1.00/hour
|
||||
|
||||
**Pros:**
|
||||
- Unlimited usage once set up
|
||||
- Best quality available
|
||||
- Complete privacy
|
||||
- No API rate limits
|
||||
- Can fine-tune models
|
||||
|
||||
**Cons:**
|
||||
- Requires GPU or cloud rental
|
||||
- More complex setup
|
||||
- Slower than cloud APIs (if CPU only)
|
||||
|
||||
**Verdict:** 💰 Best long-term if you have GPU or high volume
|
||||
|
||||
---
|
||||
|
||||
## Stability AI vs Replicate: What's the Difference?
|
||||
|
||||
### Stability AI (stability.ai)
|
||||
**What it is:**
|
||||
- The company that created Stable Diffusion
|
||||
- Direct API to their hosted models
|
||||
- Official source
|
||||
|
||||
**Business Model:**
|
||||
- Buy credits upfront
|
||||
- Credits expire after 3 months
|
||||
- Official support
|
||||
- Guaranteed uptime SLA
|
||||
|
||||
**Models Available:**
|
||||
- Stable Diffusion XL
|
||||
- Stable Diffusion 1.5
|
||||
- Their official models only
|
||||
|
||||
---
|
||||
|
||||
### Replicate (replicate.com)
|
||||
**What it is:**
|
||||
- Marketplace/platform for running ML models
|
||||
- Hosts models from many sources
|
||||
- Pay-per-use GPU time
|
||||
|
||||
**Business Model:**
|
||||
- Pay only for GPU seconds used
|
||||
- No upfront purchase
|
||||
- No credits that expire
|
||||
- $0.01 minimum charge per prediction
|
||||
|
||||
**Models Available:**
|
||||
- Stability AI's models (SDXL, SD 1.5)
|
||||
- Community models
|
||||
- Fine-tuned variants
|
||||
- Specialized models (LaMa, ControlNet, etc.)
|
||||
- 100+ image generation models
|
||||
|
||||
**Think of it like:**
|
||||
- **Stability AI** = Buying directly from Apple
|
||||
- **Replicate** = App Store with many developers
|
||||
|
||||
---
|
||||
|
||||
## Cost Comparison Examples
|
||||
|
||||
### Scenario: 100 edits per month
|
||||
|
||||
| Provider | Cost per Image | Monthly Cost | Quality |
|
||||
|----------|---------------|--------------|---------|
|
||||
| DALL-E 2 | $0.020 | $2.00 | ⭐⭐ Poor |
|
||||
| Stability AI | $0.040 | $4.00 | ⭐⭐⭐⭐ Good |
|
||||
| Replicate (SDXL) | $0.025 | $2.50 | ⭐⭐⭐⭐⭐ Excellent |
|
||||
| Replicate (LaMa) | $0.002 | $0.20 | ⭐⭐⭐⭐ Good for removal |
|
||||
| Local GPU | $0.00 | $0.00* | ⭐⭐⭐⭐⭐ Best |
|
||||
|
||||
*Requires $500+ GPU or $0.30-1.00/hr cloud GPU
|
||||
|
||||
### Scenario: 1000 edits per month (Heavy use)
|
||||
|
||||
| Provider | Monthly Cost | Notes |
|
||||
|----------|--------------|-------|
|
||||
| DALL-E 2 | $20.00 | Not worth it |
|
||||
| Stability AI | $40.00 | Need $10-40 credit refills |
|
||||
| Replicate (SDXL) | $25.00 | Pay as you go |
|
||||
| Local GPU | $0.00 | GPU pays for itself after ~50K images |
|
||||
| Cloud GPU (RunPod) | $20-60 | Depends on uptime needed |
|
||||
|
||||
---
|
||||
|
||||
## Quality Rankings for Inpainting
|
||||
|
||||
**Best to Worst:**
|
||||
|
||||
1. **Local SDXL Inpainting** ⭐⭐⭐⭐⭐ (self-hosted)
|
||||
2. **Replicate SDXL Inpainting** ⭐⭐⭐⭐⭐
|
||||
3. **Stability AI SDXL** ⭐⭐⭐⭐
|
||||
4. **Replicate LaMa** ⭐⭐⭐⭐ (for removal only)
|
||||
5. **DALL-E 2** ⭐⭐ (outdated)
|
||||
|
||||
---
|
||||
|
||||
## Recommendation by Use Case
|
||||
|
||||
### Best for Testing/Development: Mock Provider
|
||||
- Cost: $0
|
||||
- Quality: N/A (returns original)
|
||||
- Use when: Building/testing UI
|
||||
|
||||
### Best for Low Volume (< 100/month): Replicate
|
||||
- Cost: ~$2.50/month
|
||||
- Quality: ⭐⭐⭐⭐⭐
|
||||
- No minimum purchase
|
||||
- Multiple model options
|
||||
|
||||
### Best for Medium Volume (100-1000/month): Replicate or Stability AI
|
||||
- Replicate: ~$25/month, more flexibility
|
||||
- Stability AI: ~$40/month, simpler API
|
||||
|
||||
### Best for High Volume (1000+/month): Local GPU or Cloud GPU
|
||||
- Unlimited usage
|
||||
- Best quality
|
||||
- Full control
|
||||
|
||||
### Best Overall Value: Replicate
|
||||
- No minimum purchase
|
||||
- Pay only for what you use
|
||||
- Best model selection
|
||||
- Easy to try multiple models
|
||||
|
||||
---
|
||||
|
||||
## My Recommendation
|
||||
|
||||
Start with **Replicate** because:
|
||||
|
||||
1. ✅ No upfront cost (vs Stability's $10 minimum)
|
||||
2. ✅ Better quality than DALL-E 2
|
||||
3. ✅ Can try multiple models to find what works
|
||||
4. ✅ Cheapest per-image for low-medium volume
|
||||
5. ✅ Can switch to Stability AI later if needed
|
||||
|
||||
**Next Steps:**
|
||||
- I can add Replicate support (30 min of work)
|
||||
- Test with SDXL Inpainting first
|
||||
- Try LaMa for object removal
|
||||
- Fall back to Stability if needed
|
||||
|
||||
Would you like me to add Replicate support?
|
||||
@@ -0,0 +1,369 @@
|
||||
# Model Selection Guide for Body Parts and Editing Tasks
|
||||
|
||||
## Quick Reference: Best Models by Use Case
|
||||
|
||||
### Human Features (Faces, Hands, Bodies)
|
||||
|
||||
**Best Choice: `realistic-vision` (Replicate)**
|
||||
|
||||
```env
|
||||
AI_PROVIDER=replicate
|
||||
REPLICATE_API_KEY=your-key
|
||||
REPLICATE_MODEL=realistic-vision
|
||||
```
|
||||
|
||||
**Why:** Trained specifically on human anatomy and realistic photos. Handles difficult features like:
|
||||
- ✅ Hands (notoriously hard for AI)
|
||||
- ✅ Faces and facial features
|
||||
- ✅ Skin textures and tones
|
||||
- ✅ Body proportions
|
||||
- ✅ Portraits
|
||||
|
||||
**Examples:**
|
||||
- "Fix the hand position"
|
||||
- "Remove red eye"
|
||||
- "Smooth skin blemishes"
|
||||
- "Adjust facial expression"
|
||||
- "Fix fingers"
|
||||
|
||||
**Cost:** ~$0.020/image
|
||||
**Quality:** ⭐⭐⭐⭐⭐
|
||||
|
||||
---
|
||||
|
||||
### Object Removal
|
||||
|
||||
**Best Choice: `lama` (Replicate)**
|
||||
|
||||
```env
|
||||
AI_PROVIDER=replicate
|
||||
REPLICATE_MODEL=lama
|
||||
```
|
||||
|
||||
**Why:** Specifically designed for inpainting and object removal. Excellent at:
|
||||
- ✅ Removing objects cleanly
|
||||
- ✅ Filling in backgrounds naturally
|
||||
- ✅ Maintaining surrounding context
|
||||
- ✅ Fast and cheap
|
||||
|
||||
**Examples:**
|
||||
- "Remove the person"
|
||||
- "Delete the watermark"
|
||||
- "Erase the object"
|
||||
- "Clean up the background"
|
||||
|
||||
**Cost:** ~$0.002/image (cheapest!)
|
||||
**Quality:** ⭐⭐⭐⭐
|
||||
|
||||
---
|
||||
|
||||
### General Purpose Editing
|
||||
|
||||
**Best Choice: `sdxl-inpaint` (Replicate or Stability AI)**
|
||||
|
||||
```env
|
||||
# Option 1: Replicate
|
||||
AI_PROVIDER=replicate
|
||||
REPLICATE_MODEL=sdxl-inpaint
|
||||
|
||||
# Option 2: Stability AI Direct
|
||||
AI_PROVIDER=stability
|
||||
STABILITY_MODEL=sdxl
|
||||
```
|
||||
|
||||
**Why:** SDXL (Stable Diffusion XL) is the best all-around model for:
|
||||
- ✅ Landscapes and scenery
|
||||
- ✅ Objects and textures
|
||||
- ✅ Creative edits
|
||||
- ✅ Style changes
|
||||
- ✅ Adding elements
|
||||
|
||||
**Examples:**
|
||||
- "Change sky to sunset"
|
||||
- "Add flowers"
|
||||
- "Make it autumn"
|
||||
- "Replace with grass"
|
||||
|
||||
**Cost:**
|
||||
- Replicate: ~$0.025/image
|
||||
- Stability AI: ~$0.040/image
|
||||
|
||||
**Quality:** ⭐⭐⭐⭐⭐
|
||||
|
||||
---
|
||||
|
||||
## Detailed Comparison by Body Part
|
||||
|
||||
### Hands ✋
|
||||
|
||||
**Challenge:** Hands are the hardest thing for AI to generate correctly. Common issues:
|
||||
- Wrong number of fingers
|
||||
- Unnatural finger positions
|
||||
- Distorted proportions
|
||||
- Weird joints
|
||||
|
||||
**Best Models (in order):**
|
||||
|
||||
1. **Realistic Vision** (Replicate) - ⭐⭐⭐⭐⭐
|
||||
- Best overall for hands
|
||||
- Understands hand anatomy
|
||||
- Cost: ~$0.020/image
|
||||
|
||||
2. **SDXL Inpainting** (Replicate/Stability) - ⭐⭐⭐
|
||||
- Decent but less consistent
|
||||
- Cost: ~$0.025-0.040/image
|
||||
|
||||
3. **DALL-E 2** (OpenAI) - ⭐⭐
|
||||
- Often struggles with hands
|
||||
- Not recommended
|
||||
|
||||
**Tips for Better Hand Edits:**
|
||||
- Use detailed prompts: "realistic human hand with five fingers"
|
||||
- Add negative prompts if provider supports: "deformed, extra fingers, missing fingers"
|
||||
- Use Mode B (full image context) for better results
|
||||
- Consider editing in multiple passes if needed
|
||||
|
||||
---
|
||||
|
||||
### Faces 😊
|
||||
|
||||
**Challenge:** Faces need to look natural and maintain proper proportions
|
||||
|
||||
**Best Models:**
|
||||
|
||||
1. **Realistic Vision** (Replicate) - ⭐⭐⭐⭐⭐
|
||||
- Excellent for facial features
|
||||
- Natural skin textures
|
||||
- Good expression handling
|
||||
|
||||
2. **SDXL Inpainting** - ⭐⭐⭐⭐
|
||||
- Good for general facial edits
|
||||
- Better for style than realism
|
||||
|
||||
**Use Cases:**
|
||||
- Remove blemishes
|
||||
- Fix red eye
|
||||
- Adjust expressions
|
||||
- Change hair
|
||||
- Smooth wrinkles
|
||||
|
||||
---
|
||||
|
||||
### Full Body / Torso 🧍
|
||||
|
||||
**Best Model:** Realistic Vision
|
||||
|
||||
**Why:** Maintains body proportions and realistic anatomy
|
||||
|
||||
**Examples:**
|
||||
- "Fix the clothing wrinkles"
|
||||
- "Change shirt color to blue"
|
||||
- "Remove the stain"
|
||||
|
||||
---
|
||||
|
||||
### Hearts ♥️ (Decorative Elements)
|
||||
|
||||
**Best Model:** SDXL Inpainting
|
||||
|
||||
**Why:** Great for creative and decorative elements
|
||||
|
||||
**Examples:**
|
||||
- "Add heart shape"
|
||||
- "Draw a heart pattern"
|
||||
- "Replace with hearts"
|
||||
|
||||
---
|
||||
|
||||
## Auto-Selection Feature
|
||||
|
||||
The system automatically selects the best model based on your prompt:
|
||||
|
||||
### Keywords that trigger `realistic-vision`:
|
||||
- hand, hands, finger, fingers
|
||||
- face, facial, portrait, eyes, nose, mouth
|
||||
- body, person, human, skin, people
|
||||
- realistic, photo, photograph
|
||||
|
||||
### Keywords that trigger `lama` (removal):
|
||||
- remove, delete, erase, cleanup
|
||||
- disappear, hide, clear
|
||||
|
||||
### Default: `sdxl-inpaint`
|
||||
- Everything else uses SDXL for best general quality
|
||||
|
||||
**Example Auto-Selection:**
|
||||
```python
|
||||
# User prompt: "Fix the hand" → auto-selects realistic-vision
|
||||
# User prompt: "Remove the person" → auto-selects lama
|
||||
# User prompt: "Change to sunset" → auto-selects sdxl-inpaint
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## Manual Model Override
|
||||
|
||||
### Via Environment Variable
|
||||
Set default model in `.env`:
|
||||
```env
|
||||
REPLICATE_MODEL=realistic-vision
|
||||
```
|
||||
|
||||
### Via API Request
|
||||
Override per-edit in the API:
|
||||
```json
|
||||
{
|
||||
"prompt": "Fix the hand",
|
||||
"ai_provider": "replicate",
|
||||
"ai_model": "realistic-vision",
|
||||
"mode": "A",
|
||||
...
|
||||
}
|
||||
```
|
||||
|
||||
### Via Frontend (Future Feature)
|
||||
Model selector dropdown in the UI.
|
||||
|
||||
---
|
||||
|
||||
## Cost Optimization Strategies
|
||||
|
||||
### For Low-Volume Users (< 100 edits/month)
|
||||
**Recommendation:** Use Replicate with auto-selection
|
||||
|
||||
**Why:**
|
||||
- No minimum purchase
|
||||
- Pay only for what you use
|
||||
- Auto-selects cheapest appropriate model
|
||||
|
||||
**Estimated Cost:** $1-3/month
|
||||
|
||||
---
|
||||
|
||||
### For Medium-Volume Users (100-1000 edits/month)
|
||||
**Recommendation:** Replicate or Stability AI
|
||||
|
||||
**Strategy:**
|
||||
- Use `lama` for removals ($0.002/image)
|
||||
- Use `realistic-vision` for humans ($0.020/image)
|
||||
- Use `sdxl-inpaint` for general ($0.025/image)
|
||||
|
||||
**Estimated Cost:** $10-30/month
|
||||
|
||||
---
|
||||
|
||||
### For High-Volume Users (1000+ edits/month)
|
||||
**Recommendation:** Consider local GPU or cloud GPU
|
||||
|
||||
**Why:**
|
||||
- No per-image cost
|
||||
- Best quality control
|
||||
- Privacy
|
||||
|
||||
**Setup:**
|
||||
- Local: RTX 3060+ GPU ($300-2000 one-time)
|
||||
- Cloud: RunPod/Vast.ai ($0.30-1.00/hour)
|
||||
|
||||
---
|
||||
|
||||
## Quality Comparison Table
|
||||
|
||||
| Use Case | DALL-E 2 | Stability SDXL | Replicate SDXL | Replicate Realistic | Replicate LaMa |
|
||||
|----------|----------|----------------|----------------|---------------------|----------------|
|
||||
| Hands | ⭐⭐ | ⭐⭐⭐ | ⭐⭐⭐⭐ | ⭐⭐⭐⭐⭐ | ⭐⭐ |
|
||||
| Faces | ⭐⭐ | ⭐⭐⭐⭐ | ⭐⭐⭐⭐ | ⭐⭐⭐⭐⭐ | ⭐⭐ |
|
||||
| Bodies | ⭐⭐ | ⭐⭐⭐⭐ | ⭐⭐⭐⭐ | ⭐⭐⭐⭐⭐ | ⭐⭐ |
|
||||
| Objects | ⭐⭐ | ⭐⭐⭐⭐ | ⭐⭐⭐⭐⭐ | ⭐⭐⭐ | N/A |
|
||||
| Landscapes | ⭐⭐ | ⭐⭐⭐⭐⭐ | ⭐⭐⭐⭐⭐ | ⭐⭐⭐ | N/A |
|
||||
| Removal | ⭐⭐ | ⭐⭐⭐ | ⭐⭐⭐⭐ | ⭐⭐⭐ | ⭐⭐⭐⭐⭐ |
|
||||
| Creative | ⭐⭐ | ⭐⭐⭐⭐⭐ | ⭐⭐⭐⭐⭐ | ⭐⭐⭐ | ⭐ |
|
||||
|
||||
---
|
||||
|
||||
## Advanced Tips
|
||||
|
||||
### For Difficult Hands
|
||||
1. **Use Mode B** - Provides full image context
|
||||
2. **Be specific** - "realistic five-fingered hand in natural pose"
|
||||
3. **Multiple passes** - Fix gross errors first, then refine
|
||||
4. **Reference images** - Mode B helps AI understand the pose
|
||||
|
||||
### For Facial Features
|
||||
1. **High feather value** - 10-15px for smooth blending
|
||||
2. **Small selections** - Target specific features
|
||||
3. **Natural lighting** - Mention lighting in prompt
|
||||
|
||||
### For Body Parts
|
||||
1. **Maintain proportions** - Use Mode B for body context
|
||||
2. **Clothing context** - Include clothing description in prompt
|
||||
3. **Skin tone consistency** - Mention skin tone if needed
|
||||
|
||||
---
|
||||
|
||||
## Troubleshooting Common Issues
|
||||
|
||||
### "Hands have too many fingers"
|
||||
- **Solution:** Switch to `realistic-vision` model
|
||||
- **Prompt:** "realistic human hand with exactly five fingers"
|
||||
- **Try:** Multiple generations, pick best result
|
||||
|
||||
### "Face looks unnatural"
|
||||
- **Solution:** Use `realistic-vision` model
|
||||
- **Increase:** Feather value to 15-20px
|
||||
- **Try:** Mode B for better context
|
||||
|
||||
### "Removal leaves artifacts"
|
||||
- **Solution:** Use `lama` model (designed for removal)
|
||||
- **Alternative:** SDXL with prompt "clean background"
|
||||
|
||||
### "Colors don't match"
|
||||
- **Increase:** Feather value to 20-30px
|
||||
- **Try:** Mode B for better color context
|
||||
- **Prompt:** Include color description
|
||||
|
||||
---
|
||||
|
||||
## Quick Start Examples
|
||||
|
||||
### Example 1: Fix a Hand
|
||||
```json
|
||||
{
|
||||
"prompt": "realistic human hand with five fingers, natural pose",
|
||||
"ai_provider": "replicate",
|
||||
"ai_model": "realistic-vision",
|
||||
"mode": "B",
|
||||
"feather_px": 10
|
||||
}
|
||||
```
|
||||
|
||||
### Example 2: Remove an Object
|
||||
```json
|
||||
{
|
||||
"prompt": "remove the object, clean background",
|
||||
"ai_provider": "replicate",
|
||||
"ai_model": "lama",
|
||||
"mode": "A",
|
||||
"feather_px": 5
|
||||
}
|
||||
```
|
||||
|
||||
### Example 3: Change Sky
|
||||
```json
|
||||
{
|
||||
"prompt": "sunset sky with orange and pink clouds",
|
||||
"ai_provider": "replicate",
|
||||
"ai_model": "sdxl-inpaint",
|
||||
"mode": "A",
|
||||
"feather_px": 15
|
||||
}
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## Summary
|
||||
|
||||
**For Body Parts:** Use `realistic-vision` (Replicate)
|
||||
**For Removal:** Use `lama` (Replicate)
|
||||
**For Everything Else:** Use `sdxl-inpaint` (Replicate or Stability)
|
||||
|
||||
**Let the auto-selection do its job** - it's optimized for these use cases!
|
||||
@@ -0,0 +1,300 @@
|
||||
# Public Domain Carved Eye Sources
|
||||
|
||||
Where to find high-quality images of carved eyes from classical sculptures (all public domain).
|
||||
|
||||
---
|
||||
|
||||
## Best Museums with Public Domain Images
|
||||
|
||||
### 1. Metropolitan Museum of Art (CC0 Public Domain)
|
||||
|
||||
**Website:** https://www.metmuseum.org/art/collection
|
||||
|
||||
**Search tips:**
|
||||
- Search: "greek statue marble head"
|
||||
- Search: "roman portrait bust"
|
||||
- Filter: "Public Domain" only
|
||||
- Download: Click "Download" for high-resolution
|
||||
|
||||
**Great examples:**
|
||||
- Greek Kouros heads (Archaic period)
|
||||
- Roman portrait busts
|
||||
- Hellenistic marble sculptures
|
||||
|
||||
**Direct collections:**
|
||||
- Greek & Roman Art: https://www.metmuseum.org/art/collection/search#!?department=13
|
||||
- Filter by "Images" → "Public Domain"
|
||||
|
||||
---
|
||||
|
||||
### 2. Smithsonian Open Access (CC0)
|
||||
|
||||
**Website:** https://www.si.edu/openaccess
|
||||
|
||||
**Features:**
|
||||
- 3 million+ images
|
||||
- All CC0 (no copyright restrictions)
|
||||
- High-resolution downloads
|
||||
|
||||
**Search:**
|
||||
- "roman marble head"
|
||||
- "greek sculpture eyes"
|
||||
- "classical portrait bust"
|
||||
|
||||
**API available:** https://api.si.edu/openaccess/api/v1.0/
|
||||
|
||||
---
|
||||
|
||||
### 3. Getty Museum (Open Content)
|
||||
|
||||
**Website:** https://www.getty.edu/art/collection/
|
||||
|
||||
**Search tips:**
|
||||
- Filter: "Open Content Program"
|
||||
- Greek and Roman antiquities
|
||||
- High-resolution IIIF images
|
||||
|
||||
**Great for:**
|
||||
- Archaic Greek sculptures
|
||||
- Classical period heads
|
||||
- Detailed close-ups
|
||||
|
||||
---
|
||||
|
||||
### 4. Rijksmuseum (Public Domain)
|
||||
|
||||
**Website:** https://www.rijksmuseum.nl/en/rijksstudio
|
||||
|
||||
**Features:**
|
||||
- Rijksstudio (free download tool)
|
||||
- High-resolution images
|
||||
- Classical sculpture collection
|
||||
|
||||
---
|
||||
|
||||
### 5. British Museum (CC BY-NC-SA 4.0)
|
||||
|
||||
**Website:** https://www.britishmuseum.org/collection
|
||||
|
||||
**Note:** Some restrictions, but many images free for non-commercial use
|
||||
|
||||
**Great for:**
|
||||
- Egyptian carved eyes
|
||||
- Greek marble heads
|
||||
- Roman portraits
|
||||
|
||||
---
|
||||
|
||||
### 6. Louvre Collections
|
||||
|
||||
**Website:** https://collections.louvre.fr/en/
|
||||
|
||||
**Search:** "sculpture greek head" or "sculpture roman portrait"
|
||||
|
||||
**Note:** Check individual image licenses
|
||||
|
||||
---
|
||||
|
||||
## How to Find the Perfect Eyes
|
||||
|
||||
### Search Strategy
|
||||
|
||||
1. **Search for heads/busts, not full statues:**
|
||||
- "greek marble head"
|
||||
- "roman portrait bust"
|
||||
- "classical sculpture face"
|
||||
|
||||
2. **Specific periods:**
|
||||
- "archaic greek kouros" (serene, stylized)
|
||||
- "classical greek sculpture" (idealized, peaceful)
|
||||
- "hellenistic sculpture" (emotional, dramatic)
|
||||
- "roman portrait" (realistic, wise)
|
||||
|
||||
3. **Look for close-ups:**
|
||||
- Museums often provide detail shots
|
||||
- Check "zoom" or "IIIF viewer" options
|
||||
|
||||
---
|
||||
|
||||
## Recommended Starting Collection
|
||||
|
||||
### Serene/Peaceful Eyes
|
||||
|
||||
**Greek Classical Period (450-400 BCE):**
|
||||
- Doryphoros (Spear Bearer) type
|
||||
- Athena heads
|
||||
- Apollo statues
|
||||
- Smooth, idealized features
|
||||
- Almond-shaped eyes
|
||||
- Minimal lid detail
|
||||
|
||||
**Best sources:** Met Museum, Getty
|
||||
|
||||
---
|
||||
|
||||
### Fierce/Intense Eyes
|
||||
|
||||
**Hellenistic Period (323-31 BCE):**
|
||||
- Alexander the Great portraits
|
||||
- Dying Gaul
|
||||
- Laocoon group
|
||||
- Dramatic expressions
|
||||
- Deep-set eyes
|
||||
- Strong brow ridges
|
||||
|
||||
**Best sources:** Smithsonian, British Museum
|
||||
|
||||
---
|
||||
|
||||
### Wise/Aged Eyes
|
||||
|
||||
**Roman Republican Period:**
|
||||
- Senator portraits
|
||||
- Veristic portraits
|
||||
- Realistic aging details
|
||||
- Detailed wrinkles
|
||||
- Saggy eyelids
|
||||
- Life-like features
|
||||
|
||||
**Best sources:** Met Museum, Getty
|
||||
|
||||
---
|
||||
|
||||
### Stylized/Archaic Eyes
|
||||
|
||||
**Greek Archaic Period (700-480 BCE):**
|
||||
- Kouros statues
|
||||
- Kore statues
|
||||
- Almond-shaped
|
||||
- Simplified forms
|
||||
- "Archaic smile"
|
||||
- Clean, simple carving
|
||||
|
||||
**Best sources:** Getty, Met Museum
|
||||
|
||||
---
|
||||
|
||||
## How to Download and Crop
|
||||
|
||||
### Step 1: Find the Statue
|
||||
|
||||
Example: Met Museum
|
||||
1. Go to https://www.metmuseum.org/art/collection
|
||||
2. Search: "roman portrait marble"
|
||||
3. Filter: Public Domain only
|
||||
4. Click on a good example
|
||||
|
||||
### Step 2: Download High-Res
|
||||
|
||||
1. Click "Download" button
|
||||
2. Choose largest size (usually 4000px+)
|
||||
3. Save to your computer
|
||||
|
||||
### Step 3: Crop the Eyes
|
||||
|
||||
Use any image editor (Photoshop, GIMP, etc.):
|
||||
|
||||
1. Open the full statue image
|
||||
2. Zoom in on one eye
|
||||
3. Crop just the eye area:
|
||||
- Include: eyeball, eyelids, tear duct, socket
|
||||
- Leave some surrounding area for context
|
||||
- Square or slightly rectangular crop
|
||||
|
||||
4. Save as PNG:
|
||||
- `greek_serene_left.png`
|
||||
- `roman_fierce_right.png`
|
||||
- etc.
|
||||
|
||||
5. Repeat for other eye (if different)
|
||||
|
||||
### Step 4: Organize
|
||||
|
||||
Place cropped eyes in:
|
||||
```
|
||||
./backend/scripts/seed_data/eyes/
|
||||
├── greek_serene_left.png
|
||||
├── greek_serene_right.png
|
||||
├── roman_fierce_left.png
|
||||
├── roman_fierce_right.png
|
||||
├── greek_peaceful_left.png
|
||||
└── ...
|
||||
```
|
||||
|
||||
### Step 5: Run Seed Script
|
||||
|
||||
```bash
|
||||
cd backend
|
||||
python scripts/seed_eye_catalog.py
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## Recommended Starting Collection (10 Eyes)
|
||||
|
||||
To start, get these 10 eyes:
|
||||
|
||||
### Greek Classical (Serene)
|
||||
1. Left eye - Greek marble head
|
||||
2. Right eye - Greek marble head
|
||||
|
||||
### Greek Archaic (Stylized/Peaceful)
|
||||
3. Left eye - Kouros statue
|
||||
4. Right eye - Kouros statue
|
||||
|
||||
### Hellenistic (Fierce/Dramatic)
|
||||
5. Left eye - Alexander portrait
|
||||
6. Right eye - Alexander portrait
|
||||
|
||||
### Roman Republican (Wise/Aged)
|
||||
7. Left eye - Roman senator bust
|
||||
8. Right eye - Roman senator bust
|
||||
|
||||
### Roman Imperial (Powerful)
|
||||
9. Left eye - Emperor portrait
|
||||
10. Right eye - Emperor portrait
|
||||
|
||||
This gives you 5 emotional ranges × 2 eyes = 10 eyes to start!
|
||||
|
||||
---
|
||||
|
||||
## Quick Links
|
||||
|
||||
- **Met Museum Collection:** https://www.metmuseum.org/art/collection/search#!?department=13&showOnly=openAccess
|
||||
- **Smithsonian Open Access:** https://www.si.edu/openaccess
|
||||
- **Getty Open Content:** https://www.getty.edu/about/whatwedo/opencontent.html
|
||||
- **Rijksmuseum API:** https://data.rijksmuseum.nl/object-metadata/api/
|
||||
|
||||
---
|
||||
|
||||
## Legal Notes
|
||||
|
||||
- **CC0/Public Domain:** Use freely for any purpose
|
||||
- **CC BY:** Must credit the source
|
||||
- **CC BY-NC:** Non-commercial use only
|
||||
- **Always check** individual image licenses
|
||||
|
||||
For commercial carving business, stick to **CC0** or **Public Domain** images.
|
||||
|
||||
---
|
||||
|
||||
## Tips for Best Results
|
||||
|
||||
1. **High resolution:** Download largest size available (2000px+ minimum)
|
||||
2. **Good lighting:** Look for evenly lit photographs
|
||||
3. **Straight-on angle:** Avoid extreme angles
|
||||
4. **Clear detail:** Can you see the eyelid lines clearly?
|
||||
5. **Minimal damage:** Choose well-preserved sculptures
|
||||
|
||||
---
|
||||
|
||||
## Next Steps
|
||||
|
||||
1. Browse the museums above
|
||||
2. Download 10-20 good eye examples
|
||||
3. Crop them in an image editor
|
||||
4. Place in `backend/scripts/seed_data/eyes/`
|
||||
5. Run the seed script
|
||||
6. Your catalog is ready!
|
||||
|
||||
**You'll have a library of proven carved eyes from master sculptors spanning 2000+ years!**
|
||||
@@ -0,0 +1,350 @@
|
||||
# Quick Start Guide
|
||||
|
||||
## How to Choose the Right AI Model
|
||||
|
||||
### For Body Parts (Hands, Faces, Bodies)
|
||||
|
||||
Use **Replicate with `realistic-vision`** model:
|
||||
|
||||
```env
|
||||
AI_PROVIDER=replicate
|
||||
REPLICATE_API_KEY=your-key-here
|
||||
REPLICATE_MODEL=realistic-vision
|
||||
```
|
||||
|
||||
**Why:** This model is specifically trained on human anatomy and handles difficult features like:
|
||||
- ✅ Hands (even complex finger positions)
|
||||
- ✅ Faces and expressions
|
||||
- ✅ Skin textures
|
||||
- ✅ Body proportions
|
||||
|
||||
**Cost:** ~$0.020/image
|
||||
|
||||
### For Removing Objects
|
||||
|
||||
Use **Replicate with `lama`** model:
|
||||
|
||||
```env
|
||||
AI_PROVIDER=replicate
|
||||
REPLICATE_MODEL=lama
|
||||
```
|
||||
|
||||
**Why:** Designed specifically for inpainting and removal
|
||||
**Cost:** ~$0.002/image (cheapest!)
|
||||
|
||||
### For General Edits (Landscapes, Objects, Creative)
|
||||
|
||||
Use **Replicate with `sdxl-inpaint`** model (default):
|
||||
|
||||
```env
|
||||
AI_PROVIDER=replicate
|
||||
REPLICATE_MODEL=sdxl-inpaint
|
||||
```
|
||||
|
||||
**Cost:** ~$0.025/image
|
||||
|
||||
---
|
||||
|
||||
## Auto-Model Selection
|
||||
|
||||
The system automatically picks the best model based on your prompt:
|
||||
|
||||
| Your Prompt | Auto-Selected Model | Why |
|
||||
|-------------|-------------------|-----|
|
||||
| "Fix the hand" | realistic-vision | Detects "hand" keyword |
|
||||
| "Remove person" | lama | Detects "remove" keyword |
|
||||
| "Change sky to sunset" | sdxl-inpaint | General purpose default |
|
||||
|
||||
**You don't need to manually specify models** - the auto-selection is optimized for quality and cost!
|
||||
|
||||
---
|
||||
|
||||
## Patch Library: Save and Reuse Parts
|
||||
|
||||
### What is the Patch Library?
|
||||
|
||||
A library where you can save image patches (regions) and reuse them across different images.
|
||||
|
||||
**Use Cases:**
|
||||
- Save a well-generated hand to reuse later
|
||||
- Save a perfect face for multiple photos
|
||||
- Build a collection of good body parts
|
||||
- Save textures, objects, or backgrounds
|
||||
- Reuse AI-generated elements that came out great
|
||||
|
||||
### How to Save a Patch
|
||||
|
||||
#### Option 1: Save AI-Generated Result
|
||||
|
||||
After an AI edit completes:
|
||||
|
||||
```bash
|
||||
POST /patches/
|
||||
{
|
||||
"name": "Perfect Hand",
|
||||
"description": "Well-formed left hand, palm up",
|
||||
"source_type": "ai_generated",
|
||||
"source_edit_id": 123,
|
||||
"category": "hand",
|
||||
"tags": "left, palm, realistic"
|
||||
}
|
||||
```
|
||||
|
||||
This saves the AI-generated output (`patch_out.png`) to your library.
|
||||
|
||||
#### Option 2: Save Manual Selection
|
||||
|
||||
Select any region from your current image:
|
||||
|
||||
```bash
|
||||
POST /patches/
|
||||
{
|
||||
"name": "Good Face",
|
||||
"description": "Frontal face with good lighting",
|
||||
"source_type": "manual_selection",
|
||||
"source_project_id": 456,
|
||||
"bbox": {"x": 100, "y": 100, "width": 200, "height": 200},
|
||||
"category": "face",
|
||||
"tags": "front, smile, female"
|
||||
}
|
||||
```
|
||||
|
||||
This saves whatever is currently in that region of your image.
|
||||
|
||||
#### Option 3: Import from File
|
||||
|
||||
Upload an external image:
|
||||
|
||||
```bash
|
||||
POST /patches/
|
||||
FormData:
|
||||
name: "Downloaded Hand"
|
||||
source_type: "imported"
|
||||
file: [uploaded PNG file]
|
||||
category: "hand"
|
||||
```
|
||||
|
||||
### How to Apply a Saved Patch
|
||||
|
||||
```bash
|
||||
POST /patches/apply
|
||||
{
|
||||
"project_id": 789,
|
||||
"patch_id": 123,
|
||||
"bbox": {"x": 300, "y": 400, "width": 200, "height": 200},
|
||||
"feather_px": 10
|
||||
}
|
||||
```
|
||||
|
||||
This places the saved patch at the specified location in your image.
|
||||
|
||||
### Browse Your Patch Library
|
||||
|
||||
```bash
|
||||
# List all patches
|
||||
GET /patches/
|
||||
|
||||
# Filter by category
|
||||
GET /patches/?category=hand
|
||||
|
||||
# Filter by tags
|
||||
GET /patches/?tags=realistic
|
||||
|
||||
# Get specific patch
|
||||
GET /patches/123
|
||||
|
||||
# Get patch image
|
||||
GET /patches/123/image
|
||||
|
||||
# Get patch thumbnail
|
||||
GET /patches/123/image?thumbnail=true
|
||||
```
|
||||
|
||||
### Organize Your Patches
|
||||
|
||||
**Categories:**
|
||||
- `hand` - Hand images
|
||||
- `face` - Facial features
|
||||
- `body` - Body parts
|
||||
- `object` - Objects and items
|
||||
- `texture` - Textures and patterns
|
||||
- `background` - Backgrounds and scenery
|
||||
|
||||
**Tags:** Comma-separated keywords for searching
|
||||
- "left, palm, realistic"
|
||||
- "front, smile, female"
|
||||
- "five fingers, open hand"
|
||||
|
||||
---
|
||||
|
||||
## Complete Workflow Example
|
||||
|
||||
### Scenario: Fix hands in a portrait photo
|
||||
|
||||
**Step 1: Create project and upload image**
|
||||
```bash
|
||||
POST /projects/ {"name": "Portrait Edit"}
|
||||
POST /projects/1/upload [upload photo]
|
||||
```
|
||||
|
||||
**Step 2: Try to fix the hand with AI**
|
||||
```bash
|
||||
POST /edits/projects/1/fix
|
||||
{
|
||||
"prompt": "realistic human hand with five fingers, natural pose",
|
||||
"mode": "B", # Use full image for context
|
||||
"selection_type": "rectangle",
|
||||
"bbox": {"x": 200, "y": 300, "width": 150, "height": 200},
|
||||
"feather_px": 10
|
||||
}
|
||||
```
|
||||
|
||||
The system auto-selects `realistic-vision` model because prompt mentions "hand".
|
||||
|
||||
**Step 3: If result is good, save it for later**
|
||||
```bash
|
||||
POST /patches/
|
||||
{
|
||||
"name": "Good Left Hand",
|
||||
"source_type": "ai_generated",
|
||||
"source_edit_id": 1,
|
||||
"category": "hand",
|
||||
"tags": "left, natural, realistic, five fingers"
|
||||
}
|
||||
```
|
||||
|
||||
**Step 4: Use saved hand on another photo**
|
||||
```bash
|
||||
# On a different project
|
||||
POST /patches/apply
|
||||
{
|
||||
"project_id": 2,
|
||||
"patch_id": 1,
|
||||
"bbox": {"x": 150, "y": 250, "width": 150, "height": 200},
|
||||
"feather_px": 15
|
||||
}
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## Cost Comparison
|
||||
|
||||
### Example: Fixing 10 hands in different photos
|
||||
|
||||
**Option A: Generate each hand with AI**
|
||||
- 10 edits × $0.020 = **$0.20**
|
||||
|
||||
**Option B: Generate one good hand, save it, reuse it**
|
||||
- 1 AI generation: $0.020
|
||||
- 9 patch applications: $0.00 (no AI cost)
|
||||
- **Total: $0.020** (90% savings!)
|
||||
|
||||
### When to Use Saved Patches vs AI
|
||||
|
||||
**Use Saved Patches When:**
|
||||
- You have a perfect result you want to reuse
|
||||
- Same angle/lighting/style needed
|
||||
- Want to maintain consistency across images
|
||||
- Want to avoid AI generation costs
|
||||
|
||||
**Use AI Generation When:**
|
||||
- Need unique/different result each time
|
||||
- Different angle or perspective needed
|
||||
- Want variation and creativity
|
||||
- Patch doesn't fit the context
|
||||
|
||||
---
|
||||
|
||||
## Pro Tips
|
||||
|
||||
### Building a Good Patch Library
|
||||
|
||||
1. **Save your best AI results** - When AI generates something great, save it immediately
|
||||
2. **Organize with categories** - Use consistent categories for easy finding
|
||||
3. **Tag descriptively** - Include orientation (left/right), pose, lighting, etc.
|
||||
4. **Create variations** - Save multiple versions of common needs (left hand, right hand, etc.)
|
||||
5. **Build gradually** - Your library becomes more valuable over time
|
||||
|
||||
### Maximizing Quality
|
||||
|
||||
1. **For hands:** Always use `realistic-vision` model or save good results
|
||||
2. **For faces:** Use Mode B (full image context) for better matching
|
||||
3. **Use high feather values** (15-20px) when applying saved patches
|
||||
4. **Test positioning** before finalizing - patches work best when lighting/angle matches
|
||||
|
||||
### Saving Money
|
||||
|
||||
1. **Build a patch library** of common needs
|
||||
2. **Use `lama` for removals** instead of expensive models
|
||||
3. **Let auto-selection work** - it picks the cheapest appropriate model
|
||||
4. **Reuse successful patches** instead of regenerating
|
||||
|
||||
---
|
||||
|
||||
## API Quick Reference
|
||||
|
||||
```bash
|
||||
# List available patches
|
||||
GET /patches/
|
||||
|
||||
# Get patch details
|
||||
GET /patches/{id}
|
||||
|
||||
# Get patch image
|
||||
GET /patches/{id}/image
|
||||
GET /patches/{id}/image?thumbnail=true
|
||||
|
||||
# Create patch from AI edit
|
||||
POST /patches/
|
||||
{
|
||||
"name": "My Patch",
|
||||
"source_type": "ai_generated",
|
||||
"source_edit_id": 123,
|
||||
"category": "hand"
|
||||
}
|
||||
|
||||
# Create patch from manual selection
|
||||
POST /patches/
|
||||
{
|
||||
"name": "My Patch",
|
||||
"source_type": "manual_selection",
|
||||
"source_project_id": 456,
|
||||
"bbox": {"x": 100, "y": 100, "width": 200, "height": 200}
|
||||
}
|
||||
|
||||
# Apply saved patch
|
||||
POST /patches/apply
|
||||
{
|
||||
"project_id": 789,
|
||||
"patch_id": 123,
|
||||
"bbox": {"x": 300, "y": 400, "width": 200, "height": 200},
|
||||
"feather_px": 10
|
||||
}
|
||||
|
||||
# Delete patch
|
||||
DELETE /patches/{id}
|
||||
|
||||
# Update patch metadata
|
||||
PUT /patches/{id}
|
||||
{
|
||||
"name": "Updated Name",
|
||||
"tags": "new, tags",
|
||||
"category": "hand"
|
||||
}
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## Summary
|
||||
|
||||
✅ **For hands/faces/bodies:** Use `realistic-vision` model
|
||||
✅ **For removal:** Use `lama` model
|
||||
✅ **For general edits:** Use `sdxl-inpaint` (default)
|
||||
✅ **Auto-selection works great** - just write natural prompts
|
||||
✅ **Save good AI results** to patch library for reuse
|
||||
✅ **Save manual selections** from any image
|
||||
✅ **Reuse patches across images** to save money and maintain consistency
|
||||
|
||||
**You now have the best of both worlds:**
|
||||
- AI generation when you need something new
|
||||
- Saved patches when you need consistency or want to save money
|
||||
Reference in New Issue
Block a user