Merge pull request #40 from outis1one/claude/fix-ai-paint-tool-yz6q8
Fix AI tools and My Library, add U2net background removal
This commit is contained in:
Outis
@@ -1,15 +1,122 @@
|
||||
# Caddy 2 Configuration for AI Photo Edit
|
||||
# Simple version - frontend nginx handles API routing internally
|
||||
# Caddy 2 Configuration for EditmaskwithAI
|
||||
# ==========================================
|
||||
#
|
||||
# SETUP INSTRUCTIONS:
|
||||
# 1. Replace 'your-subdomain.yourdomain.com' with your actual domain
|
||||
# 2. Make sure DNS CNAME record points to your server
|
||||
# 3. Ensure ports 80 and 443 are open (Caddy handles SSL automatically)
|
||||
# 4. The frontend runs on port 3080 by default (docker-compose)
|
||||
#
|
||||
# Common Issues:
|
||||
# - "Connection refused": Check if the frontend container is running
|
||||
# - "Bad gateway": Check if localhost:3080 is accessible
|
||||
# - "SSL error": Make sure ports 80/443 are open for Let's Encrypt
|
||||
|
||||
# Option 1: With domain name
|
||||
ai-photo-edit.yourdomain.com {
|
||||
reverse_proxy localhost:3080
|
||||
# ============================================
|
||||
# OPTION 1: Domain with automatic HTTPS (recommended)
|
||||
# ============================================
|
||||
# Replace with your actual domain
|
||||
your-subdomain.yourdomain.com {
|
||||
# Reverse proxy to frontend (nginx serves both frontend and proxies API)
|
||||
reverse_proxy localhost:3080 {
|
||||
# Health checks
|
||||
health_uri /health
|
||||
health_interval 30s
|
||||
health_timeout 10s
|
||||
|
||||
# Headers for proper proxying
|
||||
header_up Host {upstream_hostport}
|
||||
header_up X-Real-IP {remote_host}
|
||||
header_up X-Forwarded-For {remote_host}
|
||||
header_up X-Forwarded-Proto {scheme}
|
||||
}
|
||||
|
||||
# Enable compression
|
||||
encode gzip zstd
|
||||
|
||||
# Logging (optional - uncomment for debugging)
|
||||
# log {
|
||||
# output file /var/log/caddy/access.log
|
||||
# format json
|
||||
# }
|
||||
}
|
||||
|
||||
# Option 2: IP:Port (comment out option 1 if using this)
|
||||
# ============================================
|
||||
# OPTION 2: IP address or localhost (no HTTPS)
|
||||
# ============================================
|
||||
# Uncomment this block and comment out Option 1 if you don't have a domain
|
||||
# or want to test locally
|
||||
|
||||
# :8080 {
|
||||
# reverse_proxy localhost:3080
|
||||
# reverse_proxy localhost:3080 {
|
||||
# header_up Host {upstream_hostport}
|
||||
# header_up X-Real-IP {remote_host}
|
||||
# header_up X-Forwarded-For {remote_host}
|
||||
# }
|
||||
# encode gzip zstd
|
||||
# }
|
||||
|
||||
# Note: You don't need to specify /projects, /edits, etc.
|
||||
# The frontend's nginx is already configured to proxy those to the backend internally.
|
||||
# ============================================
|
||||
# OPTION 3: Multiple subdomains
|
||||
# ============================================
|
||||
# If you want both www and non-www versions
|
||||
|
||||
# yourdomain.com, www.yourdomain.com {
|
||||
# reverse_proxy localhost:3080 {
|
||||
# header_up Host {upstream_hostport}
|
||||
# header_up X-Real-IP {remote_host}
|
||||
# header_up X-Forwarded-For {remote_host}
|
||||
# header_up X-Forwarded-Proto {scheme}
|
||||
# }
|
||||
# encode gzip zstd
|
||||
# }
|
||||
|
||||
# ============================================
|
||||
# OPTION 4: Behind another reverse proxy (Cloudflare, etc.)
|
||||
# ============================================
|
||||
# Use this if Caddy is behind Cloudflare or another proxy
|
||||
|
||||
# your-subdomain.yourdomain.com {
|
||||
# # Trust proxy headers from upstream
|
||||
# servers {
|
||||
# trusted_proxies static 173.245.48.0/20 103.21.244.0/22 103.22.200.0/22 103.31.4.0/22 141.101.64.0/18 108.162.192.0/18 190.93.240.0/20 188.114.96.0/20 197.234.240.0/22 198.41.128.0/17 162.158.0.0/15 104.16.0.0/13 104.24.0.0/14 172.64.0.0/13 131.0.72.0/22
|
||||
# }
|
||||
#
|
||||
# reverse_proxy localhost:3080 {
|
||||
# header_up Host {upstream_hostport}
|
||||
# header_up X-Real-IP {http.request.header.CF-Connecting-IP}
|
||||
# header_up X-Forwarded-For {http.request.header.CF-Connecting-IP}
|
||||
# header_up X-Forwarded-Proto {scheme}
|
||||
# }
|
||||
# encode gzip zstd
|
||||
# }
|
||||
|
||||
# ============================================
|
||||
# TROUBLESHOOTING
|
||||
# ============================================
|
||||
#
|
||||
# 1. Check Caddy logs:
|
||||
# docker logs caddy
|
||||
# OR: journalctl -u caddy -f
|
||||
#
|
||||
# 2. Test backend connectivity:
|
||||
# curl -I http://localhost:3080
|
||||
#
|
||||
# 3. Check DNS resolution:
|
||||
# dig your-subdomain.yourdomain.com
|
||||
# nslookup your-subdomain.yourdomain.com
|
||||
#
|
||||
# 4. Verify ports are open:
|
||||
# sudo netstat -tlnp | grep -E ':(80|443|3080)'
|
||||
#
|
||||
# 5. Check firewall:
|
||||
# sudo ufw status
|
||||
# sudo iptables -L -n
|
||||
#
|
||||
# 6. For Let's Encrypt issues:
|
||||
# - Ensure ports 80 and 443 are accessible from internet
|
||||
# - Check if domain resolves to your server's IP
|
||||
# - Try: caddy validate --config /path/to/Caddyfile
|
||||
#
|
||||
# 7. Force reload Caddy config:
|
||||
# caddy reload --config /path/to/Caddyfile
|
||||
|
||||
+138
-20
@@ -128,53 +128,171 @@ async def inpaint_base64(request: InpaintRequest):
|
||||
raise HTTPException(status_code=500, detail=str(e))
|
||||
|
||||
|
||||
class RemoveBackgroundRequestV2(BaseModel):
|
||||
image: str # Base64 encoded image
|
||||
model: Optional[str] = "auto" # "auto", "u2net", "rembg", "birefnet"
|
||||
|
||||
|
||||
@router.post("/remove-background-base64")
|
||||
async def remove_background_base64(request: RemoveBackgroundRequest):
|
||||
"""
|
||||
Remove background from a base64 encoded image using rembg with BiRefNet.
|
||||
BiRefNet is state-of-the-art for background removal (better than u2net).
|
||||
Remove background from a base64 encoded image.
|
||||
Tries multiple methods: U2Net (direct), rembg with BiRefNet, rembg default.
|
||||
Returns base64 encoded PNG with transparent background.
|
||||
Used by miniPaint frontend.
|
||||
"""
|
||||
try:
|
||||
from rembg import remove, new_session
|
||||
except ImportError:
|
||||
raise HTTPException(
|
||||
status_code=500,
|
||||
detail="rembg not installed. Run: pip install rembg"
|
||||
)
|
||||
|
||||
try:
|
||||
# Decode base64 image
|
||||
image_bytes = base64.b64decode(request.image)
|
||||
img = Image.open(BytesIO(image_bytes)).convert('RGB')
|
||||
|
||||
# Use BiRefNet model for best quality (state-of-the-art)
|
||||
# Falls back to default model if BiRefNet not available
|
||||
result_bytes = None
|
||||
method_used = None
|
||||
|
||||
# Try U2Net first (direct implementation, no rembg dependency issues)
|
||||
try:
|
||||
session = new_session("birefnet-general")
|
||||
result_bytes = remove(image_bytes, session=session)
|
||||
except Exception:
|
||||
# Fallback to default model
|
||||
result_bytes = remove(image_bytes)
|
||||
result_bytes = await _remove_background_u2net(img)
|
||||
method_used = "u2net"
|
||||
except Exception as e:
|
||||
print(f"U2Net failed: {e}")
|
||||
|
||||
# Fall back to rembg if U2Net failed
|
||||
if result_bytes is None:
|
||||
try:
|
||||
from rembg import remove, new_session
|
||||
try:
|
||||
session = new_session("birefnet-general")
|
||||
result_bytes = remove(image_bytes, session=session)
|
||||
method_used = "birefnet"
|
||||
except Exception:
|
||||
result_bytes = remove(image_bytes)
|
||||
method_used = "rembg-default"
|
||||
except ImportError:
|
||||
pass
|
||||
except Exception as e:
|
||||
print(f"rembg failed: {e}")
|
||||
|
||||
if result_bytes is None:
|
||||
raise HTTPException(
|
||||
status_code=500,
|
||||
detail="No background removal method available. Install u2net or rembg."
|
||||
)
|
||||
|
||||
# Convert result to base64
|
||||
result_b64 = base64.b64encode(result_bytes).decode('utf-8')
|
||||
|
||||
# Get dimensions
|
||||
img = Image.open(BytesIO(result_bytes))
|
||||
result_img = Image.open(BytesIO(result_bytes))
|
||||
|
||||
return {
|
||||
"result": result_b64,
|
||||
"width": img.width,
|
||||
"height": img.height
|
||||
"width": result_img.width,
|
||||
"height": result_img.height,
|
||||
"method": method_used
|
||||
}
|
||||
|
||||
except HTTPException:
|
||||
raise
|
||||
except Exception as e:
|
||||
import traceback
|
||||
traceback.print_exc()
|
||||
raise HTTPException(status_code=500, detail=str(e))
|
||||
|
||||
|
||||
# Global U2Net model cache
|
||||
_u2net_model = None
|
||||
|
||||
|
||||
async def _remove_background_u2net(img: Image.Image) -> bytes:
|
||||
"""
|
||||
Remove background using U2Net model directly.
|
||||
This avoids rembg dependency issues while providing good quality.
|
||||
"""
|
||||
global _u2net_model
|
||||
|
||||
import torch
|
||||
from pathlib import Path
|
||||
|
||||
# Check for U2Net model
|
||||
models_dir = Path('/app/data/models')
|
||||
u2net_path = models_dir / 'u2net.pth'
|
||||
|
||||
# Also check alternative names
|
||||
if not u2net_path.exists():
|
||||
for alt_name in ['u2net.onnx', 'u2netp.pth', 'u2net_human_seg.pth']:
|
||||
alt_path = models_dir / alt_name
|
||||
if alt_path.exists():
|
||||
u2net_path = alt_path
|
||||
break
|
||||
|
||||
if not u2net_path.exists():
|
||||
raise FileNotFoundError(
|
||||
f"U2Net model not found at {u2net_path}. "
|
||||
"Download from: https://github.com/xuebinqin/U-2-Net"
|
||||
)
|
||||
|
||||
# Load model if not cached
|
||||
if _u2net_model is None:
|
||||
print(f"Loading U2Net model from {u2net_path}")
|
||||
|
||||
if str(u2net_path).endswith('.onnx'):
|
||||
# Use ONNX runtime
|
||||
import onnxruntime as ort
|
||||
_u2net_model = ort.InferenceSession(str(u2net_path))
|
||||
else:
|
||||
# Use PyTorch
|
||||
from app.services.u2net_model import U2NET
|
||||
_u2net_model = U2NET(3, 1)
|
||||
_u2net_model.load_state_dict(torch.load(str(u2net_path), map_location='cpu'))
|
||||
_u2net_model.eval()
|
||||
|
||||
print("U2Net model loaded")
|
||||
|
||||
# Preprocess image
|
||||
img_np = np.array(img)
|
||||
original_size = img.size
|
||||
|
||||
# Resize to model input size
|
||||
input_size = 320
|
||||
img_resized = img.resize((input_size, input_size), Image.Resampling.BILINEAR)
|
||||
img_np = np.array(img_resized).astype(np.float32)
|
||||
|
||||
# Normalize
|
||||
img_np = img_np / 255.0
|
||||
img_np = (img_np - [0.485, 0.456, 0.406]) / [0.229, 0.224, 0.225]
|
||||
img_np = img_np.transpose(2, 0, 1) # HWC to CHW
|
||||
img_np = np.expand_dims(img_np, 0) # Add batch dimension
|
||||
|
||||
# Run inference
|
||||
if hasattr(_u2net_model, 'run'):
|
||||
# ONNX runtime
|
||||
input_name = _u2net_model.get_inputs()[0].name
|
||||
outputs = _u2net_model.run(None, {input_name: img_np})
|
||||
mask = outputs[0][0, 0]
|
||||
else:
|
||||
# PyTorch
|
||||
with torch.no_grad():
|
||||
input_tensor = torch.from_numpy(img_np).float()
|
||||
d1, d2, d3, d4, d5, d6, d7 = _u2net_model(input_tensor)
|
||||
mask = d1[0, 0].numpy()
|
||||
|
||||
# Post-process mask
|
||||
mask = (mask - mask.min()) / (mask.max() - mask.min() + 1e-8)
|
||||
mask = (mask * 255).astype(np.uint8)
|
||||
|
||||
# Resize mask back to original size
|
||||
mask_img = Image.fromarray(mask).resize(original_size, Image.Resampling.BILINEAR)
|
||||
|
||||
# Apply mask to original image
|
||||
result = img.convert('RGBA')
|
||||
result.putalpha(mask_img)
|
||||
|
||||
# Save to bytes
|
||||
buffer = BytesIO()
|
||||
result.save(buffer, format='PNG')
|
||||
return buffer.getvalue()
|
||||
|
||||
|
||||
@router.post("/remove-background")
|
||||
async def remove_background(
|
||||
project_id: Optional[int] = Form(None),
|
||||
|
||||
@@ -0,0 +1,500 @@
|
||||
"""
|
||||
U2Net Model Definition for Background Removal
|
||||
Based on: https://github.com/xuebinqin/U-2-Net
|
||||
|
||||
This is a simplified implementation that works with the standard U2Net weights.
|
||||
"""
|
||||
|
||||
import torch
|
||||
import torch.nn as nn
|
||||
import torch.nn.functional as F
|
||||
|
||||
|
||||
class REBNCONV(nn.Module):
|
||||
def __init__(self, in_ch=3, out_ch=3, dirate=1):
|
||||
super(REBNCONV, self).__init__()
|
||||
|
||||
self.conv_s1 = nn.Conv2d(in_ch, out_ch, 3, padding=1*dirate, dilation=1*dirate)
|
||||
self.bn_s1 = nn.BatchNorm2d(out_ch)
|
||||
self.relu_s1 = nn.ReLU(inplace=True)
|
||||
|
||||
def forward(self, x):
|
||||
hx = x
|
||||
xout = self.relu_s1(self.bn_s1(self.conv_s1(hx)))
|
||||
return xout
|
||||
|
||||
|
||||
def _upsample_like(src, tar):
|
||||
src = F.interpolate(src, size=tar.shape[2:], mode='bilinear', align_corners=False)
|
||||
return src
|
||||
|
||||
|
||||
class RSU7(nn.Module):
|
||||
def __init__(self, in_ch=3, mid_ch=12, out_ch=3):
|
||||
super(RSU7, self).__init__()
|
||||
|
||||
self.rebnconvin = REBNCONV(in_ch, out_ch, dirate=1)
|
||||
|
||||
self.rebnconv1 = REBNCONV(out_ch, mid_ch, dirate=1)
|
||||
self.pool1 = nn.MaxPool2d(2, stride=2, ceil_mode=True)
|
||||
|
||||
self.rebnconv2 = REBNCONV(mid_ch, mid_ch, dirate=1)
|
||||
self.pool2 = nn.MaxPool2d(2, stride=2, ceil_mode=True)
|
||||
|
||||
self.rebnconv3 = REBNCONV(mid_ch, mid_ch, dirate=1)
|
||||
self.pool3 = nn.MaxPool2d(2, stride=2, ceil_mode=True)
|
||||
|
||||
self.rebnconv4 = REBNCONV(mid_ch, mid_ch, dirate=1)
|
||||
self.pool4 = nn.MaxPool2d(2, stride=2, ceil_mode=True)
|
||||
|
||||
self.rebnconv5 = REBNCONV(mid_ch, mid_ch, dirate=1)
|
||||
self.pool5 = nn.MaxPool2d(2, stride=2, ceil_mode=True)
|
||||
|
||||
self.rebnconv6 = REBNCONV(mid_ch, mid_ch, dirate=1)
|
||||
|
||||
self.rebnconv7 = REBNCONV(mid_ch, mid_ch, dirate=2)
|
||||
|
||||
self.rebnconv6d = REBNCONV(mid_ch*2, mid_ch, dirate=1)
|
||||
self.rebnconv5d = REBNCONV(mid_ch*2, mid_ch, dirate=1)
|
||||
self.rebnconv4d = REBNCONV(mid_ch*2, mid_ch, dirate=1)
|
||||
self.rebnconv3d = REBNCONV(mid_ch*2, mid_ch, dirate=1)
|
||||
self.rebnconv2d = REBNCONV(mid_ch*2, mid_ch, dirate=1)
|
||||
self.rebnconv1d = REBNCONV(mid_ch*2, out_ch, dirate=1)
|
||||
|
||||
def forward(self, x):
|
||||
hx = x
|
||||
hxin = self.rebnconvin(hx)
|
||||
|
||||
hx1 = self.rebnconv1(hxin)
|
||||
hx = self.pool1(hx1)
|
||||
|
||||
hx2 = self.rebnconv2(hx)
|
||||
hx = self.pool2(hx2)
|
||||
|
||||
hx3 = self.rebnconv3(hx)
|
||||
hx = self.pool3(hx3)
|
||||
|
||||
hx4 = self.rebnconv4(hx)
|
||||
hx = self.pool4(hx4)
|
||||
|
||||
hx5 = self.rebnconv5(hx)
|
||||
hx = self.pool5(hx5)
|
||||
|
||||
hx6 = self.rebnconv6(hx)
|
||||
|
||||
hx7 = self.rebnconv7(hx6)
|
||||
|
||||
hx6d = self.rebnconv6d(torch.cat((hx7, hx6), 1))
|
||||
hx6dup = _upsample_like(hx6d, hx5)
|
||||
|
||||
hx5d = self.rebnconv5d(torch.cat((hx6dup, hx5), 1))
|
||||
hx5dup = _upsample_like(hx5d, hx4)
|
||||
|
||||
hx4d = self.rebnconv4d(torch.cat((hx5dup, hx4), 1))
|
||||
hx4dup = _upsample_like(hx4d, hx3)
|
||||
|
||||
hx3d = self.rebnconv3d(torch.cat((hx4dup, hx3), 1))
|
||||
hx3dup = _upsample_like(hx3d, hx2)
|
||||
|
||||
hx2d = self.rebnconv2d(torch.cat((hx3dup, hx2), 1))
|
||||
hx2dup = _upsample_like(hx2d, hx1)
|
||||
|
||||
hx1d = self.rebnconv1d(torch.cat((hx2dup, hx1), 1))
|
||||
|
||||
return hx1d + hxin
|
||||
|
||||
|
||||
class RSU6(nn.Module):
|
||||
def __init__(self, in_ch=3, mid_ch=12, out_ch=3):
|
||||
super(RSU6, self).__init__()
|
||||
|
||||
self.rebnconvin = REBNCONV(in_ch, out_ch, dirate=1)
|
||||
|
||||
self.rebnconv1 = REBNCONV(out_ch, mid_ch, dirate=1)
|
||||
self.pool1 = nn.MaxPool2d(2, stride=2, ceil_mode=True)
|
||||
|
||||
self.rebnconv2 = REBNCONV(mid_ch, mid_ch, dirate=1)
|
||||
self.pool2 = nn.MaxPool2d(2, stride=2, ceil_mode=True)
|
||||
|
||||
self.rebnconv3 = REBNCONV(mid_ch, mid_ch, dirate=1)
|
||||
self.pool3 = nn.MaxPool2d(2, stride=2, ceil_mode=True)
|
||||
|
||||
self.rebnconv4 = REBNCONV(mid_ch, mid_ch, dirate=1)
|
||||
self.pool4 = nn.MaxPool2d(2, stride=2, ceil_mode=True)
|
||||
|
||||
self.rebnconv5 = REBNCONV(mid_ch, mid_ch, dirate=1)
|
||||
|
||||
self.rebnconv6 = REBNCONV(mid_ch, mid_ch, dirate=2)
|
||||
|
||||
self.rebnconv5d = REBNCONV(mid_ch*2, mid_ch, dirate=1)
|
||||
self.rebnconv4d = REBNCONV(mid_ch*2, mid_ch, dirate=1)
|
||||
self.rebnconv3d = REBNCONV(mid_ch*2, mid_ch, dirate=1)
|
||||
self.rebnconv2d = REBNCONV(mid_ch*2, mid_ch, dirate=1)
|
||||
self.rebnconv1d = REBNCONV(mid_ch*2, out_ch, dirate=1)
|
||||
|
||||
def forward(self, x):
|
||||
hx = x
|
||||
hxin = self.rebnconvin(hx)
|
||||
|
||||
hx1 = self.rebnconv1(hxin)
|
||||
hx = self.pool1(hx1)
|
||||
|
||||
hx2 = self.rebnconv2(hx)
|
||||
hx = self.pool2(hx2)
|
||||
|
||||
hx3 = self.rebnconv3(hx)
|
||||
hx = self.pool3(hx3)
|
||||
|
||||
hx4 = self.rebnconv4(hx)
|
||||
hx = self.pool4(hx4)
|
||||
|
||||
hx5 = self.rebnconv5(hx)
|
||||
|
||||
hx6 = self.rebnconv6(hx5)
|
||||
|
||||
hx5d = self.rebnconv5d(torch.cat((hx6, hx5), 1))
|
||||
hx5dup = _upsample_like(hx5d, hx4)
|
||||
|
||||
hx4d = self.rebnconv4d(torch.cat((hx5dup, hx4), 1))
|
||||
hx4dup = _upsample_like(hx4d, hx3)
|
||||
|
||||
hx3d = self.rebnconv3d(torch.cat((hx4dup, hx3), 1))
|
||||
hx3dup = _upsample_like(hx3d, hx2)
|
||||
|
||||
hx2d = self.rebnconv2d(torch.cat((hx3dup, hx2), 1))
|
||||
hx2dup = _upsample_like(hx2d, hx1)
|
||||
|
||||
hx1d = self.rebnconv1d(torch.cat((hx2dup, hx1), 1))
|
||||
|
||||
return hx1d + hxin
|
||||
|
||||
|
||||
class RSU5(nn.Module):
|
||||
def __init__(self, in_ch=3, mid_ch=12, out_ch=3):
|
||||
super(RSU5, self).__init__()
|
||||
|
||||
self.rebnconvin = REBNCONV(in_ch, out_ch, dirate=1)
|
||||
|
||||
self.rebnconv1 = REBNCONV(out_ch, mid_ch, dirate=1)
|
||||
self.pool1 = nn.MaxPool2d(2, stride=2, ceil_mode=True)
|
||||
|
||||
self.rebnconv2 = REBNCONV(mid_ch, mid_ch, dirate=1)
|
||||
self.pool2 = nn.MaxPool2d(2, stride=2, ceil_mode=True)
|
||||
|
||||
self.rebnconv3 = REBNCONV(mid_ch, mid_ch, dirate=1)
|
||||
self.pool3 = nn.MaxPool2d(2, stride=2, ceil_mode=True)
|
||||
|
||||
self.rebnconv4 = REBNCONV(mid_ch, mid_ch, dirate=1)
|
||||
|
||||
self.rebnconv5 = REBNCONV(mid_ch, mid_ch, dirate=2)
|
||||
|
||||
self.rebnconv4d = REBNCONV(mid_ch*2, mid_ch, dirate=1)
|
||||
self.rebnconv3d = REBNCONV(mid_ch*2, mid_ch, dirate=1)
|
||||
self.rebnconv2d = REBNCONV(mid_ch*2, mid_ch, dirate=1)
|
||||
self.rebnconv1d = REBNCONV(mid_ch*2, out_ch, dirate=1)
|
||||
|
||||
def forward(self, x):
|
||||
hx = x
|
||||
hxin = self.rebnconvin(hx)
|
||||
|
||||
hx1 = self.rebnconv1(hxin)
|
||||
hx = self.pool1(hx1)
|
||||
|
||||
hx2 = self.rebnconv2(hx)
|
||||
hx = self.pool2(hx2)
|
||||
|
||||
hx3 = self.rebnconv3(hx)
|
||||
hx = self.pool3(hx3)
|
||||
|
||||
hx4 = self.rebnconv4(hx)
|
||||
|
||||
hx5 = self.rebnconv5(hx4)
|
||||
|
||||
hx4d = self.rebnconv4d(torch.cat((hx5, hx4), 1))
|
||||
hx4dup = _upsample_like(hx4d, hx3)
|
||||
|
||||
hx3d = self.rebnconv3d(torch.cat((hx4dup, hx3), 1))
|
||||
hx3dup = _upsample_like(hx3d, hx2)
|
||||
|
||||
hx2d = self.rebnconv2d(torch.cat((hx3dup, hx2), 1))
|
||||
hx2dup = _upsample_like(hx2d, hx1)
|
||||
|
||||
hx1d = self.rebnconv1d(torch.cat((hx2dup, hx1), 1))
|
||||
|
||||
return hx1d + hxin
|
||||
|
||||
|
||||
class RSU4(nn.Module):
|
||||
def __init__(self, in_ch=3, mid_ch=12, out_ch=3):
|
||||
super(RSU4, self).__init__()
|
||||
|
||||
self.rebnconvin = REBNCONV(in_ch, out_ch, dirate=1)
|
||||
|
||||
self.rebnconv1 = REBNCONV(out_ch, mid_ch, dirate=1)
|
||||
self.pool1 = nn.MaxPool2d(2, stride=2, ceil_mode=True)
|
||||
|
||||
self.rebnconv2 = REBNCONV(mid_ch, mid_ch, dirate=1)
|
||||
self.pool2 = nn.MaxPool2d(2, stride=2, ceil_mode=True)
|
||||
|
||||
self.rebnconv3 = REBNCONV(mid_ch, mid_ch, dirate=1)
|
||||
|
||||
self.rebnconv4 = REBNCONV(mid_ch, mid_ch, dirate=2)
|
||||
|
||||
self.rebnconv3d = REBNCONV(mid_ch*2, mid_ch, dirate=1)
|
||||
self.rebnconv2d = REBNCONV(mid_ch*2, mid_ch, dirate=1)
|
||||
self.rebnconv1d = REBNCONV(mid_ch*2, out_ch, dirate=1)
|
||||
|
||||
def forward(self, x):
|
||||
hx = x
|
||||
hxin = self.rebnconvin(hx)
|
||||
|
||||
hx1 = self.rebnconv1(hxin)
|
||||
hx = self.pool1(hx1)
|
||||
|
||||
hx2 = self.rebnconv2(hx)
|
||||
hx = self.pool2(hx2)
|
||||
|
||||
hx3 = self.rebnconv3(hx)
|
||||
|
||||
hx4 = self.rebnconv4(hx3)
|
||||
|
||||
hx3d = self.rebnconv3d(torch.cat((hx4, hx3), 1))
|
||||
hx3dup = _upsample_like(hx3d, hx2)
|
||||
|
||||
hx2d = self.rebnconv2d(torch.cat((hx3dup, hx2), 1))
|
||||
hx2dup = _upsample_like(hx2d, hx1)
|
||||
|
||||
hx1d = self.rebnconv1d(torch.cat((hx2dup, hx1), 1))
|
||||
|
||||
return hx1d + hxin
|
||||
|
||||
|
||||
class RSU4F(nn.Module):
|
||||
def __init__(self, in_ch=3, mid_ch=12, out_ch=3):
|
||||
super(RSU4F, self).__init__()
|
||||
|
||||
self.rebnconvin = REBNCONV(in_ch, out_ch, dirate=1)
|
||||
|
||||
self.rebnconv1 = REBNCONV(out_ch, mid_ch, dirate=1)
|
||||
self.rebnconv2 = REBNCONV(mid_ch, mid_ch, dirate=2)
|
||||
self.rebnconv3 = REBNCONV(mid_ch, mid_ch, dirate=4)
|
||||
|
||||
self.rebnconv4 = REBNCONV(mid_ch, mid_ch, dirate=8)
|
||||
|
||||
self.rebnconv3d = REBNCONV(mid_ch*2, mid_ch, dirate=4)
|
||||
self.rebnconv2d = REBNCONV(mid_ch*2, mid_ch, dirate=2)
|
||||
self.rebnconv1d = REBNCONV(mid_ch*2, out_ch, dirate=1)
|
||||
|
||||
def forward(self, x):
|
||||
hx = x
|
||||
hxin = self.rebnconvin(hx)
|
||||
|
||||
hx1 = self.rebnconv1(hxin)
|
||||
hx2 = self.rebnconv2(hx1)
|
||||
hx3 = self.rebnconv3(hx2)
|
||||
|
||||
hx4 = self.rebnconv4(hx3)
|
||||
|
||||
hx3d = self.rebnconv3d(torch.cat((hx4, hx3), 1))
|
||||
hx2d = self.rebnconv2d(torch.cat((hx3d, hx2), 1))
|
||||
hx1d = self.rebnconv1d(torch.cat((hx2d, hx1), 1))
|
||||
|
||||
return hx1d + hxin
|
||||
|
||||
|
||||
class U2NET(nn.Module):
|
||||
def __init__(self, in_ch=3, out_ch=1):
|
||||
super(U2NET, self).__init__()
|
||||
|
||||
self.stage1 = RSU7(in_ch, 32, 64)
|
||||
self.pool12 = nn.MaxPool2d(2, stride=2, ceil_mode=True)
|
||||
|
||||
self.stage2 = RSU6(64, 32, 128)
|
||||
self.pool23 = nn.MaxPool2d(2, stride=2, ceil_mode=True)
|
||||
|
||||
self.stage3 = RSU5(128, 64, 256)
|
||||
self.pool34 = nn.MaxPool2d(2, stride=2, ceil_mode=True)
|
||||
|
||||
self.stage4 = RSU4(256, 128, 512)
|
||||
self.pool45 = nn.MaxPool2d(2, stride=2, ceil_mode=True)
|
||||
|
||||
self.stage5 = RSU4F(512, 256, 512)
|
||||
self.pool56 = nn.MaxPool2d(2, stride=2, ceil_mode=True)
|
||||
|
||||
self.stage6 = RSU4F(512, 256, 512)
|
||||
|
||||
# decoder
|
||||
self.stage5d = RSU4F(1024, 256, 512)
|
||||
self.stage4d = RSU4(1024, 128, 256)
|
||||
self.stage3d = RSU5(512, 64, 128)
|
||||
self.stage2d = RSU6(256, 32, 64)
|
||||
self.stage1d = RSU7(128, 16, 64)
|
||||
|
||||
self.side1 = nn.Conv2d(64, out_ch, 3, padding=1)
|
||||
self.side2 = nn.Conv2d(64, out_ch, 3, padding=1)
|
||||
self.side3 = nn.Conv2d(128, out_ch, 3, padding=1)
|
||||
self.side4 = nn.Conv2d(256, out_ch, 3, padding=1)
|
||||
self.side5 = nn.Conv2d(512, out_ch, 3, padding=1)
|
||||
self.side6 = nn.Conv2d(512, out_ch, 3, padding=1)
|
||||
|
||||
self.outconv = nn.Conv2d(6*out_ch, out_ch, 1)
|
||||
|
||||
def forward(self, x):
|
||||
hx = x
|
||||
|
||||
# stage 1
|
||||
hx1 = self.stage1(hx)
|
||||
hx = self.pool12(hx1)
|
||||
|
||||
# stage 2
|
||||
hx2 = self.stage2(hx)
|
||||
hx = self.pool23(hx2)
|
||||
|
||||
# stage 3
|
||||
hx3 = self.stage3(hx)
|
||||
hx = self.pool34(hx3)
|
||||
|
||||
# stage 4
|
||||
hx4 = self.stage4(hx)
|
||||
hx = self.pool45(hx4)
|
||||
|
||||
# stage 5
|
||||
hx5 = self.stage5(hx)
|
||||
hx = self.pool56(hx5)
|
||||
|
||||
# stage 6
|
||||
hx6 = self.stage6(hx)
|
||||
hx6up = _upsample_like(hx6, hx5)
|
||||
|
||||
# decoder
|
||||
hx5d = self.stage5d(torch.cat((hx6up, hx5), 1))
|
||||
hx5dup = _upsample_like(hx5d, hx4)
|
||||
|
||||
hx4d = self.stage4d(torch.cat((hx5dup, hx4), 1))
|
||||
hx4dup = _upsample_like(hx4d, hx3)
|
||||
|
||||
hx3d = self.stage3d(torch.cat((hx4dup, hx3), 1))
|
||||
hx3dup = _upsample_like(hx3d, hx2)
|
||||
|
||||
hx2d = self.stage2d(torch.cat((hx3dup, hx2), 1))
|
||||
hx2dup = _upsample_like(hx2d, hx1)
|
||||
|
||||
hx1d = self.stage1d(torch.cat((hx2dup, hx1), 1))
|
||||
|
||||
# side output
|
||||
d1 = self.side1(hx1d)
|
||||
|
||||
d2 = self.side2(hx2d)
|
||||
d2 = _upsample_like(d2, d1)
|
||||
|
||||
d3 = self.side3(hx3d)
|
||||
d3 = _upsample_like(d3, d1)
|
||||
|
||||
d4 = self.side4(hx4d)
|
||||
d4 = _upsample_like(d4, d1)
|
||||
|
||||
d5 = self.side5(hx5d)
|
||||
d5 = _upsample_like(d5, d1)
|
||||
|
||||
d6 = self.side6(hx6)
|
||||
d6 = _upsample_like(d6, d1)
|
||||
|
||||
d0 = self.outconv(torch.cat((d1, d2, d3, d4, d5, d6), 1))
|
||||
|
||||
return torch.sigmoid(d0), torch.sigmoid(d1), torch.sigmoid(d2), torch.sigmoid(d3), torch.sigmoid(d4), torch.sigmoid(d5), torch.sigmoid(d6)
|
||||
|
||||
|
||||
class U2NETP(nn.Module):
|
||||
"""Smaller/faster U2Net variant (u2netp)"""
|
||||
|
||||
def __init__(self, in_ch=3, out_ch=1):
|
||||
super(U2NETP, self).__init__()
|
||||
|
||||
self.stage1 = RSU7(in_ch, 16, 64)
|
||||
self.pool12 = nn.MaxPool2d(2, stride=2, ceil_mode=True)
|
||||
|
||||
self.stage2 = RSU6(64, 16, 64)
|
||||
self.pool23 = nn.MaxPool2d(2, stride=2, ceil_mode=True)
|
||||
|
||||
self.stage3 = RSU5(64, 16, 64)
|
||||
self.pool34 = nn.MaxPool2d(2, stride=2, ceil_mode=True)
|
||||
|
||||
self.stage4 = RSU4(64, 16, 64)
|
||||
self.pool45 = nn.MaxPool2d(2, stride=2, ceil_mode=True)
|
||||
|
||||
self.stage5 = RSU4F(64, 16, 64)
|
||||
self.pool56 = nn.MaxPool2d(2, stride=2, ceil_mode=True)
|
||||
|
||||
self.stage6 = RSU4F(64, 16, 64)
|
||||
|
||||
# decoder
|
||||
self.stage5d = RSU4F(128, 16, 64)
|
||||
self.stage4d = RSU4(128, 16, 64)
|
||||
self.stage3d = RSU5(128, 16, 64)
|
||||
self.stage2d = RSU6(128, 16, 64)
|
||||
self.stage1d = RSU7(128, 16, 64)
|
||||
|
||||
self.side1 = nn.Conv2d(64, out_ch, 3, padding=1)
|
||||
self.side2 = nn.Conv2d(64, out_ch, 3, padding=1)
|
||||
self.side3 = nn.Conv2d(64, out_ch, 3, padding=1)
|
||||
self.side4 = nn.Conv2d(64, out_ch, 3, padding=1)
|
||||
self.side5 = nn.Conv2d(64, out_ch, 3, padding=1)
|
||||
self.side6 = nn.Conv2d(64, out_ch, 3, padding=1)
|
||||
|
||||
self.outconv = nn.Conv2d(6*out_ch, out_ch, 1)
|
||||
|
||||
def forward(self, x):
|
||||
hx = x
|
||||
|
||||
hx1 = self.stage1(hx)
|
||||
hx = self.pool12(hx1)
|
||||
|
||||
hx2 = self.stage2(hx)
|
||||
hx = self.pool23(hx2)
|
||||
|
||||
hx3 = self.stage3(hx)
|
||||
hx = self.pool34(hx3)
|
||||
|
||||
hx4 = self.stage4(hx)
|
||||
hx = self.pool45(hx4)
|
||||
|
||||
hx5 = self.stage5(hx)
|
||||
hx = self.pool56(hx5)
|
||||
|
||||
hx6 = self.stage6(hx)
|
||||
hx6up = _upsample_like(hx6, hx5)
|
||||
|
||||
hx5d = self.stage5d(torch.cat((hx6up, hx5), 1))
|
||||
hx5dup = _upsample_like(hx5d, hx4)
|
||||
|
||||
hx4d = self.stage4d(torch.cat((hx5dup, hx4), 1))
|
||||
hx4dup = _upsample_like(hx4d, hx3)
|
||||
|
||||
hx3d = self.stage3d(torch.cat((hx4dup, hx3), 1))
|
||||
hx3dup = _upsample_like(hx3d, hx2)
|
||||
|
||||
hx2d = self.stage2d(torch.cat((hx3dup, hx2), 1))
|
||||
hx2dup = _upsample_like(hx2d, hx1)
|
||||
|
||||
hx1d = self.stage1d(torch.cat((hx2dup, hx1), 1))
|
||||
|
||||
d1 = self.side1(hx1d)
|
||||
|
||||
d2 = self.side2(hx2d)
|
||||
d2 = _upsample_like(d2, d1)
|
||||
|
||||
d3 = self.side3(hx3d)
|
||||
d3 = _upsample_like(d3, d1)
|
||||
|
||||
d4 = self.side4(hx4d)
|
||||
d4 = _upsample_like(d4, d1)
|
||||
|
||||
d5 = self.side5(hx5d)
|
||||
d5 = _upsample_like(d5, d1)
|
||||
|
||||
d6 = self.side6(hx6)
|
||||
d6 = _upsample_like(d6, d1)
|
||||
|
||||
d0 = self.outconv(torch.cat((d1, d2, d3, d4, d5, d6), 1))
|
||||
|
||||
return torch.sigmoid(d0), torch.sigmoid(d1), torch.sigmoid(d2), torch.sigmoid(d3), torch.sigmoid(d4), torch.sigmoid(d5), torch.sigmoid(d6)
|
||||
@@ -245,6 +245,143 @@
|
||||
margin-right: auto;
|
||||
}
|
||||
|
||||
/* Shape/Library Tabs */
|
||||
#popups .popup .shape-tabs {
|
||||
display: flex;
|
||||
gap: 0;
|
||||
margin-bottom: 1rem;
|
||||
border-bottom: 2px solid var(--border-color);
|
||||
}
|
||||
|
||||
#popups .popup .shape-tab {
|
||||
padding: 0.8rem 1.5rem;
|
||||
background: transparent;
|
||||
border: none;
|
||||
border-bottom: 2px solid transparent;
|
||||
margin-bottom: -2px;
|
||||
cursor: pointer;
|
||||
color: var(--text-color-muted);
|
||||
font-size: 1rem;
|
||||
transition: color 0.2s, border-color 0.2s;
|
||||
}
|
||||
|
||||
#popups .popup .shape-tab:hover {
|
||||
color: var(--text-color);
|
||||
}
|
||||
|
||||
#popups .popup .shape-tab.active {
|
||||
color: var(--link-color);
|
||||
border-bottom-color: var(--link-color);
|
||||
}
|
||||
|
||||
#popups .popup .library-loading {
|
||||
text-align: center;
|
||||
padding: 2rem;
|
||||
color: var(--text-color-muted);
|
||||
}
|
||||
|
||||
/* My Library Browser Styles */
|
||||
#popups .popup .library-browser {
|
||||
max-height: calc(60vh - 100px);
|
||||
overflow-y: auto;
|
||||
}
|
||||
|
||||
#popups .popup .library-categories {
|
||||
display: flex;
|
||||
flex-direction: column;
|
||||
gap: 1.5rem;
|
||||
}
|
||||
|
||||
#popups .popup .library-category h3 {
|
||||
color: var(--text-color);
|
||||
font-size: 1.4rem;
|
||||
margin-bottom: 0.8rem;
|
||||
padding-bottom: 0.4rem;
|
||||
border-bottom: 1px solid var(--border-color);
|
||||
}
|
||||
|
||||
#popups .popup .library-items {
|
||||
display: flex;
|
||||
flex-wrap: wrap;
|
||||
gap: 1rem;
|
||||
}
|
||||
|
||||
#popups .popup .library-item {
|
||||
display: flex;
|
||||
flex-direction: column;
|
||||
align-items: center;
|
||||
width: 120px;
|
||||
padding: 0.8rem;
|
||||
background: var(--input-background-color);
|
||||
border: 1px solid var(--border-color);
|
||||
border-radius: 4px;
|
||||
cursor: pointer;
|
||||
transition: background 0.2s, border-color 0.2s;
|
||||
}
|
||||
|
||||
#popups .popup .library-item:hover {
|
||||
background: var(--input-background-color-hover);
|
||||
border-color: var(--link-color);
|
||||
}
|
||||
|
||||
#popups .popup .library-item img {
|
||||
width: 100px;
|
||||
height: 80px;
|
||||
object-fit: contain;
|
||||
background: repeating-conic-gradient(#666 0% 25%, #888 0% 50%) 50% / 10px 10px;
|
||||
border-radius: 2px;
|
||||
margin-bottom: 0.5rem;
|
||||
}
|
||||
|
||||
#popups .popup .library-item-name {
|
||||
font-size: 0.85rem;
|
||||
text-align: center;
|
||||
color: var(--text-color);
|
||||
white-space: nowrap;
|
||||
overflow: hidden;
|
||||
text-overflow: ellipsis;
|
||||
width: 100%;
|
||||
margin-bottom: 0.5rem;
|
||||
}
|
||||
|
||||
#popups .popup .library-item-actions {
|
||||
display: flex;
|
||||
gap: 0.5rem;
|
||||
}
|
||||
|
||||
#popups .popup .library-item-actions button {
|
||||
font-size: 0.75rem;
|
||||
padding: 0.3rem 0.6rem;
|
||||
background: var(--button-background-color);
|
||||
border: 1px solid var(--border-color);
|
||||
border-radius: 3px;
|
||||
cursor: pointer;
|
||||
color: var(--text-color);
|
||||
}
|
||||
|
||||
#popups .popup .library-item-actions .insert-btn {
|
||||
background: #2a6d2a;
|
||||
}
|
||||
|
||||
#popups .popup .library-item-actions .insert-btn:hover {
|
||||
background: #3a8d3a;
|
||||
}
|
||||
|
||||
#popups .popup .library-item-actions .delete-btn {
|
||||
background: #6d2a2a;
|
||||
}
|
||||
|
||||
#popups .popup .library-item-actions .delete-btn:hover {
|
||||
background: #8d3a3a;
|
||||
}
|
||||
|
||||
/* Library empty state */
|
||||
#popups .popup .library-empty {
|
||||
text-align: center;
|
||||
padding: 2rem;
|
||||
color: var(--text-color-muted);
|
||||
}
|
||||
|
||||
@media screen and (max-width:500px){
|
||||
#popups .popup {
|
||||
max-height: calc(80vh - 20px); /* mobile phones has bottom menu */
|
||||
|
||||
@@ -334,7 +334,7 @@ class File_my_library_class {
|
||||
title: 'My Library (' + assets.length + ' assets)',
|
||||
params: [],
|
||||
html: html,
|
||||
className: 'library-dialog',
|
||||
className: 'wide',
|
||||
on_load: function(el) {
|
||||
// Add click handlers
|
||||
el.querySelectorAll('.insert-btn').forEach(function(btn) {
|
||||
|
||||
@@ -49,14 +49,20 @@ class Ai_inpaint_class extends Base_tools_class {
|
||||
}
|
||||
|
||||
var settings = {
|
||||
title: 'AI Inpaint',
|
||||
title: 'AI Edit Selection',
|
||||
params: [
|
||||
{
|
||||
name: "mode",
|
||||
title: "Edit Mode:",
|
||||
value: "inpaint",
|
||||
values: ["inpaint", "transform"]
|
||||
},
|
||||
{
|
||||
name: "prompt",
|
||||
title: "Describe what you want:",
|
||||
title: "AI Inpaint - Describe replacement:",
|
||||
type: "textarea",
|
||||
value: "",
|
||||
placeholder: "e.g., 'a red rose', 'remove the object', 'blue sky with clouds'"
|
||||
placeholder: "AI will REPLACE the selection with what you describe.\nExamples: 'a red rose', 'empty background', 'blue sky'"
|
||||
},
|
||||
{
|
||||
name: "negative_prompt",
|
||||
@@ -66,21 +72,164 @@ class Ai_inpaint_class extends Base_tools_class {
|
||||
},
|
||||
{
|
||||
name: "strength",
|
||||
title: "Edit Strength:",
|
||||
title: "AI Edit Strength:",
|
||||
type: "range",
|
||||
value: 80,
|
||||
range: [1, 100],
|
||||
step: 1
|
||||
},
|
||||
{
|
||||
name: "scale",
|
||||
title: "Transform - Scale %:",
|
||||
type: "range",
|
||||
value: 100,
|
||||
range: [10, 200],
|
||||
step: 5
|
||||
}
|
||||
],
|
||||
on_load: function(el) {
|
||||
// Add info text
|
||||
var infoDiv = document.createElement('div');
|
||||
infoDiv.className = 'ai-inpaint-info';
|
||||
infoDiv.innerHTML = '<p style="font-size:12px;color:#aaa;margin-bottom:10px;">' +
|
||||
'<strong>Inpaint Mode:</strong> AI replaces the selected area with generated content.<br>' +
|
||||
'<strong>Transform Mode:</strong> Scale, shrink, or enlarge the selection without AI.<br>' +
|
||||
'<em>Tip: To shrink something by 35%, use Transform mode with Scale at 65%.</em></p>';
|
||||
|
||||
var dialogContent = el.querySelector('.dialog_content');
|
||||
if (dialogContent && dialogContent.firstChild) {
|
||||
dialogContent.insertBefore(infoDiv, dialogContent.firstChild);
|
||||
}
|
||||
},
|
||||
on_finish: async function (params) {
|
||||
await _this.executeInpaint(params);
|
||||
if (params.mode === 'transform') {
|
||||
await _this.executeTransform(params);
|
||||
} else {
|
||||
await _this.executeInpaint(params);
|
||||
}
|
||||
},
|
||||
};
|
||||
|
||||
this.POP.show(settings);
|
||||
}
|
||||
|
||||
/**
|
||||
* Execute transform operation (scale without AI)
|
||||
*/
|
||||
async executeTransform(params) {
|
||||
if (this.isProcessing) {
|
||||
alertify.warning('Already processing... please wait');
|
||||
return;
|
||||
}
|
||||
|
||||
// Check if we have an image layer
|
||||
if (config.layer.type != 'image') {
|
||||
alertify.error('Please select an image layer');
|
||||
return;
|
||||
}
|
||||
|
||||
var maskCanvas = window.smartSelectMask?.canvas;
|
||||
if (!maskCanvas) {
|
||||
alertify.error('No selection mask found');
|
||||
return;
|
||||
}
|
||||
|
||||
this.isProcessing = true;
|
||||
alertify.message('Transforming selection...');
|
||||
|
||||
try {
|
||||
var layer = config.layer;
|
||||
var scale = params.scale / 100;
|
||||
|
||||
// Get mask bounds
|
||||
var maskCtx = maskCanvas.getContext('2d');
|
||||
var imageData = maskCtx.getImageData(0, 0, maskCanvas.width, maskCanvas.height);
|
||||
var minX = maskCanvas.width, minY = maskCanvas.height;
|
||||
var maxX = 0, maxY = 0;
|
||||
|
||||
for (var y = 0; y < maskCanvas.height; y++) {
|
||||
for (var x = 0; x < maskCanvas.width; x++) {
|
||||
var i = (y * maskCanvas.width + x) * 4;
|
||||
if (imageData.data[i] > 128) {
|
||||
minX = Math.min(minX, x);
|
||||
minY = Math.min(minY, y);
|
||||
maxX = Math.max(maxX, x);
|
||||
maxY = Math.max(maxY, y);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
if (maxX <= minX || maxY <= minY) {
|
||||
throw new Error('Selection is too small');
|
||||
}
|
||||
|
||||
var selWidth = maxX - minX + 1;
|
||||
var selHeight = maxY - minY + 1;
|
||||
var centerX = minX + selWidth / 2;
|
||||
var centerY = minY + selHeight / 2;
|
||||
|
||||
// Extract selected pixels
|
||||
var extractCanvas = document.createElement('canvas');
|
||||
extractCanvas.width = layer.width_original;
|
||||
extractCanvas.height = layer.height_original;
|
||||
var extractCtx = extractCanvas.getContext('2d');
|
||||
extractCtx.drawImage(layer.link, 0, 0);
|
||||
extractCtx.globalCompositeOperation = 'destination-in';
|
||||
extractCtx.drawImage(maskCanvas, 0, 0);
|
||||
|
||||
// Create result canvas
|
||||
var resultCanvas = document.createElement('canvas');
|
||||
resultCanvas.width = layer.width_original;
|
||||
resultCanvas.height = layer.height_original;
|
||||
var resultCtx = resultCanvas.getContext('2d');
|
||||
|
||||
// Draw original image
|
||||
resultCtx.drawImage(layer.link, 0, 0);
|
||||
|
||||
// Remove original selection (create hole)
|
||||
resultCtx.globalCompositeOperation = 'destination-out';
|
||||
resultCtx.drawImage(maskCanvas, 0, 0);
|
||||
|
||||
// Calculate scaled dimensions
|
||||
var newWidth = selWidth * scale;
|
||||
var newHeight = selHeight * scale;
|
||||
var newX = centerX - newWidth / 2;
|
||||
var newY = centerY - newHeight / 2;
|
||||
|
||||
// Draw scaled selection back
|
||||
resultCtx.globalCompositeOperation = 'source-over';
|
||||
|
||||
// Create temp canvas for just the selection
|
||||
var selCanvas = document.createElement('canvas');
|
||||
selCanvas.width = selWidth;
|
||||
selCanvas.height = selHeight;
|
||||
var selCtx = selCanvas.getContext('2d');
|
||||
selCtx.drawImage(extractCanvas, minX, minY, selWidth, selHeight, 0, 0, selWidth, selHeight);
|
||||
|
||||
// Draw scaled
|
||||
resultCtx.drawImage(selCanvas, 0, 0, selWidth, selHeight, newX, newY, newWidth, newHeight);
|
||||
|
||||
// Apply result
|
||||
app.State.do_action(
|
||||
new app.Actions.Bundle_action('transform_selection', 'Transform Selection', [
|
||||
new app.Actions.Update_layer_image_action(resultCanvas)
|
||||
])
|
||||
);
|
||||
|
||||
// Clear selection
|
||||
window.smartSelectMask = null;
|
||||
config.need_render = true;
|
||||
|
||||
alertify.success('Transform complete! Selection scaled to ' + params.scale + '%');
|
||||
|
||||
} catch (error) {
|
||||
console.error('Transform error:', error);
|
||||
alertify.error('Transform failed: ' + error.message);
|
||||
} finally {
|
||||
this.isProcessing = false;
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* Execute the inpainting operation
|
||||
*/
|
||||
|
||||
+148
-13
@@ -4,6 +4,7 @@ import Base_tools_class from './../core/base-tools.js';
|
||||
import Base_layers_class from './../core/base-layers.js';
|
||||
import Dialog_class from './../libs/popup.js';
|
||||
import GUI_tools_class from './../core/gui/gui-tools.js';
|
||||
import File_my_library_class from './../modules/file/my_library.js';
|
||||
|
||||
var instance = null;
|
||||
|
||||
@@ -21,11 +22,13 @@ class Shape_class extends Base_tools_class {
|
||||
this.Base_layers = new Base_layers_class();
|
||||
this.GUI_tools = new GUI_tools_class();
|
||||
this.POP = new Dialog_class();
|
||||
this.My_library = new File_my_library_class();
|
||||
this.ctx = ctx;
|
||||
this.name = 'shape';
|
||||
this.layer = {};
|
||||
this.preview_width = 150;
|
||||
this.preview_height = 120;
|
||||
this.activeTab = 'shapes'; // 'shapes' or 'library'
|
||||
|
||||
this.set_events();
|
||||
}
|
||||
@@ -53,35 +56,84 @@ class Shape_class extends Base_tools_class {
|
||||
|
||||
async show_shapes(){
|
||||
var _this = this;
|
||||
var html = '';
|
||||
|
||||
// Build tabs HTML
|
||||
var tabsHtml = '<div class="shape-tabs">';
|
||||
tabsHtml += '<button class="shape-tab active" data-tab="shapes">Built-in Shapes</button>';
|
||||
tabsHtml += '<button class="shape-tab" data-tab="library">My Library</button>';
|
||||
tabsHtml += '</div>';
|
||||
|
||||
// Build shapes HTML
|
||||
var shapesHtml = '<div class="tab-content shapes-content">';
|
||||
var data = this.get_shapes();
|
||||
|
||||
for (var i in data) {
|
||||
html += '<div class="item">';
|
||||
html += ' <canvas id="c_' + data[i].key + '" width="' + this.preview_width + '" height="'
|
||||
shapesHtml += '<div class="item">';
|
||||
shapesHtml += ' <canvas id="c_' + data[i].key + '" width="' + this.preview_width + '" height="'
|
||||
+ this.preview_height + '" class="effectsPreview" data-key="'
|
||||
+ data[i].key + '"></canvas>';
|
||||
html += '<div class="preview-item-title">' + data[i].title + '</div>';
|
||||
html += '</div>';
|
||||
shapesHtml += '<div class="preview-item-title">' + data[i].title + '</div>';
|
||||
shapesHtml += '</div>';
|
||||
}
|
||||
for (var i = 0; i < 4; i++) {
|
||||
html += '<div class="item"></div>';
|
||||
shapesHtml += '<div class="item"></div>';
|
||||
}
|
||||
shapesHtml += '</div>';
|
||||
|
||||
// Build library HTML placeholder
|
||||
var libraryHtml = '<div class="tab-content library-content" style="display:none;">';
|
||||
libraryHtml += '<div class="library-loading">Loading library...</div>';
|
||||
libraryHtml += '</div>';
|
||||
|
||||
var settings = {
|
||||
title: 'Shapes',
|
||||
title: 'Shapes & Library',
|
||||
className: 'wide',
|
||||
on_load: function (params, popup) {
|
||||
var node = document.createElement("div");
|
||||
node.classList.add('flex-container');
|
||||
node.innerHTML = html;
|
||||
popup.el.querySelector('.dialog_content').appendChild(node);
|
||||
//events
|
||||
// Add tabs
|
||||
var tabsNode = document.createElement("div");
|
||||
tabsNode.innerHTML = tabsHtml;
|
||||
popup.el.querySelector('.dialog_content').insertBefore(tabsNode, popup.el.querySelector('.dialog_content').firstChild);
|
||||
|
||||
// Add shapes container
|
||||
var shapesNode = document.createElement("div");
|
||||
shapesNode.classList.add('flex-container');
|
||||
shapesNode.innerHTML = shapesHtml;
|
||||
popup.el.querySelector('.dialog_content').appendChild(shapesNode);
|
||||
|
||||
// Add library container
|
||||
var libraryNode = document.createElement("div");
|
||||
libraryNode.innerHTML = libraryHtml;
|
||||
popup.el.querySelector('.dialog_content').appendChild(libraryNode);
|
||||
|
||||
// Tab click events
|
||||
var tabs = popup.el.querySelectorAll('.shape-tab');
|
||||
tabs.forEach(function(tab) {
|
||||
tab.addEventListener('click', function() {
|
||||
var targetTab = this.dataset.tab;
|
||||
|
||||
// Update active tab
|
||||
tabs.forEach(t => t.classList.remove('active'));
|
||||
this.classList.add('active');
|
||||
|
||||
// Show/hide content
|
||||
var shapesContent = popup.el.querySelector('.shapes-content');
|
||||
var libraryContent = popup.el.querySelector('.library-content');
|
||||
|
||||
if (targetTab === 'shapes') {
|
||||
shapesContent.style.display = '';
|
||||
libraryContent.style.display = 'none';
|
||||
} else {
|
||||
shapesContent.style.display = 'none';
|
||||
libraryContent.style.display = '';
|
||||
_this.loadLibraryContent(libraryContent);
|
||||
}
|
||||
});
|
||||
});
|
||||
|
||||
// Shape click events
|
||||
var targets = popup.el.querySelectorAll('.item canvas');
|
||||
for (var i = 0; i < targets.length; i++) {
|
||||
targets[i].addEventListener('click', function (event) {
|
||||
//we have click
|
||||
_this.GUI_tools.activate_tool(this.dataset.key);
|
||||
_this.POP.hide();
|
||||
});
|
||||
@@ -106,6 +158,89 @@ class Shape_class extends Base_tools_class {
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* Load library content into the library tab
|
||||
*/
|
||||
loadLibraryContent(container) {
|
||||
var _this = this;
|
||||
|
||||
this.My_library.getAllAssets(function(assets) {
|
||||
var html = '';
|
||||
|
||||
if (assets.length === 0) {
|
||||
html = '<div class="library-empty">';
|
||||
html += '<p>Your library is empty.</p>';
|
||||
html += '<p>Use <strong>File > My Library > Save to Library</strong> to add assets.</p>';
|
||||
html += '</div>';
|
||||
} else {
|
||||
// Group by category
|
||||
var categories = {};
|
||||
assets.forEach(function(asset) {
|
||||
var cat = asset.category || 'General';
|
||||
if (!categories[cat]) categories[cat] = [];
|
||||
categories[cat].push(asset);
|
||||
});
|
||||
|
||||
html = '<div class="library-browser">';
|
||||
html += '<div class="library-categories">';
|
||||
|
||||
for (var cat in categories) {
|
||||
html += '<div class="library-category">';
|
||||
html += '<h3>' + cat + ' (' + categories[cat].length + ')</h3>';
|
||||
html += '<div class="library-items">';
|
||||
|
||||
categories[cat].forEach(function(asset) {
|
||||
html += '<div class="library-item" data-id="' + asset.id + '">';
|
||||
html += '<img src="' + asset.thumbnail + '" alt="' + asset.name + '" title="' + asset.name + '">';
|
||||
html += '<div class="library-item-name">' + asset.name + '</div>';
|
||||
html += '<div class="library-item-actions">';
|
||||
html += '<button class="insert-btn" data-id="' + asset.id + '">Insert</button>';
|
||||
html += '<button class="delete-btn" data-id="' + asset.id + '">Delete</button>';
|
||||
html += '</div>';
|
||||
html += '</div>';
|
||||
});
|
||||
|
||||
html += '</div></div>';
|
||||
}
|
||||
|
||||
html += '</div></div>';
|
||||
}
|
||||
|
||||
container.innerHTML = html;
|
||||
|
||||
// Add event handlers for library items
|
||||
container.querySelectorAll('.insert-btn').forEach(function(btn) {
|
||||
btn.addEventListener('click', function(e) {
|
||||
e.stopPropagation();
|
||||
var id = parseInt(this.dataset.id);
|
||||
_this.My_library.insertAsset(id);
|
||||
_this.POP.hide();
|
||||
});
|
||||
});
|
||||
|
||||
container.querySelectorAll('.delete-btn').forEach(function(btn) {
|
||||
btn.addEventListener('click', function(e) {
|
||||
e.stopPropagation();
|
||||
var id = parseInt(this.dataset.id);
|
||||
if (confirm('Delete this asset?')) {
|
||||
_this.My_library.deleteAsset(id, function() {
|
||||
_this.loadLibraryContent(container);
|
||||
});
|
||||
}
|
||||
});
|
||||
});
|
||||
|
||||
// Double-click to insert
|
||||
container.querySelectorAll('.library-item').forEach(function(item) {
|
||||
item.addEventListener('dblclick', function() {
|
||||
var id = parseInt(this.dataset.id);
|
||||
_this.My_library.insertAsset(id);
|
||||
_this.POP.hide();
|
||||
});
|
||||
});
|
||||
});
|
||||
}
|
||||
|
||||
render(ctx, layer) {
|
||||
|
||||
}
|
||||
|
||||
@@ -0,0 +1,133 @@
|
||||
#!/usr/bin/env python3
|
||||
"""
|
||||
Download U2Net model for background removal.
|
||||
|
||||
U2Net is a deep learning model for salient object detection,
|
||||
commonly used for background removal tasks.
|
||||
|
||||
Usage:
|
||||
python download_u2net_model.py [model_type]
|
||||
|
||||
Model types:
|
||||
u2net - Full U2Net model (~176MB, best quality)
|
||||
u2netp - Lightweight U2Net (~4MB, faster, good quality)
|
||||
u2net_human_seg - Optimized for human segmentation (~176MB)
|
||||
|
||||
Default: u2netp (good balance of quality and speed)
|
||||
"""
|
||||
|
||||
import os
|
||||
import sys
|
||||
import urllib.request
|
||||
from pathlib import Path
|
||||
|
||||
# Model URLs (from official U2Net repository releases)
|
||||
MODEL_URLS = {
|
||||
'u2net': {
|
||||
'url': 'https://github.com/danielgatis/rembg/releases/download/v0.0.0/u2net.onnx',
|
||||
'filename': 'u2net.onnx',
|
||||
'size_mb': 176
|
||||
},
|
||||
'u2netp': {
|
||||
'url': 'https://github.com/danielgatis/rembg/releases/download/v0.0.0/u2netp.onnx',
|
||||
'filename': 'u2netp.onnx',
|
||||
'size_mb': 4
|
||||
},
|
||||
'u2net_human_seg': {
|
||||
'url': 'https://github.com/danielgatis/rembg/releases/download/v0.0.0/u2net_human_seg.onnx',
|
||||
'filename': 'u2net_human_seg.onnx',
|
||||
'size_mb': 176
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
def download_with_progress(url: str, dest_path: Path, expected_size_mb: int):
|
||||
"""Download file with progress indicator."""
|
||||
|
||||
print(f"Downloading from: {url}")
|
||||
print(f"Expected size: ~{expected_size_mb}MB")
|
||||
|
||||
def progress_hook(count, block_size, total_size):
|
||||
if total_size > 0:
|
||||
percent = min(100, count * block_size * 100 // total_size)
|
||||
downloaded_mb = count * block_size / (1024 * 1024)
|
||||
total_mb = total_size / (1024 * 1024)
|
||||
sys.stdout.write(f"\rProgress: {percent}% ({downloaded_mb:.1f}/{total_mb:.1f} MB)")
|
||||
sys.stdout.flush()
|
||||
|
||||
try:
|
||||
urllib.request.urlretrieve(url, str(dest_path), progress_hook)
|
||||
print("\nDownload complete!")
|
||||
return True
|
||||
except Exception as e:
|
||||
print(f"\nDownload failed: {e}")
|
||||
return False
|
||||
|
||||
|
||||
def main():
|
||||
# Determine model type
|
||||
model_type = 'u2netp' # Default to lightweight model
|
||||
if len(sys.argv) > 1:
|
||||
model_type = sys.argv[1].lower()
|
||||
|
||||
if model_type not in MODEL_URLS:
|
||||
print(f"Unknown model type: {model_type}")
|
||||
print(f"Available models: {', '.join(MODEL_URLS.keys())}")
|
||||
sys.exit(1)
|
||||
|
||||
model_info = MODEL_URLS[model_type]
|
||||
|
||||
# Determine models directory
|
||||
# Check if running in Docker container
|
||||
if os.path.exists('/app/data/models'):
|
||||
models_dir = Path('/app/data/models')
|
||||
else:
|
||||
# Local development
|
||||
script_dir = Path(__file__).parent
|
||||
models_dir = script_dir.parent / 'data' / 'models'
|
||||
|
||||
models_dir.mkdir(parents=True, exist_ok=True)
|
||||
|
||||
dest_path = models_dir / model_info['filename']
|
||||
|
||||
# Check if already downloaded
|
||||
if dest_path.exists():
|
||||
print(f"Model already exists at: {dest_path}")
|
||||
print("Delete the file to re-download.")
|
||||
return
|
||||
|
||||
print(f"Downloading U2Net model: {model_type}")
|
||||
print(f"Destination: {dest_path}")
|
||||
print("")
|
||||
|
||||
success = download_with_progress(
|
||||
model_info['url'],
|
||||
dest_path,
|
||||
model_info['size_mb']
|
||||
)
|
||||
|
||||
if success:
|
||||
# Create symlink for easier access
|
||||
symlink_path = models_dir / 'u2net.onnx'
|
||||
if not symlink_path.exists() or symlink_path.is_symlink():
|
||||
if symlink_path.is_symlink():
|
||||
symlink_path.unlink()
|
||||
try:
|
||||
symlink_path.symlink_to(dest_path.name)
|
||||
print(f"Created symlink: {symlink_path} -> {dest_path.name}")
|
||||
except OSError:
|
||||
# Symlinks may not work on all systems
|
||||
pass
|
||||
|
||||
print(f"\nU2Net model ({model_type}) downloaded successfully!")
|
||||
print(f"Location: {dest_path}")
|
||||
print("\nYou can now use background removal in the application.")
|
||||
else:
|
||||
print("\nFailed to download model. Please try again or download manually from:")
|
||||
print(f" {model_info['url']}")
|
||||
print(f" Save to: {dest_path}")
|
||||
sys.exit(1)
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
main()
|
||||
Reference in New Issue
Block a user