Spaces:
Paused
Paused
Update app.py
Browse files
app.py
CHANGED
@@ -1,3 +1,285 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
@spaces.GPU
|
2 |
def run_local(base_image, base_mask, reference_image, ref_mask, seed, base_mask_option, ref_mask_option, text_prompt):
|
3 |
if base_mask_option == "Draw Mask":
|
@@ -114,4 +396,79 @@ def run_local(base_image, base_mask, reference_image, ref_mask, seed, base_mask_
|
|
114 |
if ref_mask_option != "Label to Mask":
|
115 |
return [show_diptych_ref_tar, edited_image, received_tar_mask, received_ref_mask]
|
116 |
else:
|
117 |
-
return [return_ref_mask, show_diptych_ref_tar, edited_image, received_tar_mask, received_ref_mask]
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
# app.py — storage-safe + HF Hub friendly + SAM import guard
|
2 |
+
|
3 |
+
import os
|
4 |
+
|
5 |
+
# ---------- ENV & THREADS (set BEFORE importing numpy/torch) ----------
|
6 |
+
omp_val = (
|
7 |
+
os.getenv("OMP_NUM_THREADS")
|
8 |
+
or os.getenv("OMP-NUM-THREADS")
|
9 |
+
or os.getenv("OMPNUMTHREADS")
|
10 |
+
or "2"
|
11 |
+
)
|
12 |
+
try:
|
13 |
+
omp_val = str(int(omp_val))
|
14 |
+
except Exception:
|
15 |
+
omp_val = "2"
|
16 |
+
os.environ["OMP_NUM_THREADS"] = omp_val # must be a positive integer string
|
17 |
+
|
18 |
+
# Persistent caches
|
19 |
+
os.environ.setdefault("HF_HOME", "/data/.huggingface")
|
20 |
+
os.environ.setdefault("HF_HUB_CACHE", "/data/.huggingface/hub")
|
21 |
+
os.environ.setdefault("HF_DATASETS_CACHE", "/data/.huggingface/datasets")
|
22 |
+
# (TRANSFORMERS_CACHE is deprecated; rely on HF_HOME) # https://huggingface.co/docs/huggingface_hub/en/guides/manage-cache
|
23 |
+
|
24 |
+
# Disable Xet path, enable fast transfer
|
25 |
+
os.environ.setdefault("HF_HUB_DISABLE_XET", "1")
|
26 |
+
os.environ.setdefault("HF_HUB_ENABLE_HF_TRANSFER", "1")
|
27 |
+
|
28 |
+
# ---------- NOW safe to import heavy libs ----------
|
29 |
+
import sys
|
30 |
+
import cv2
|
31 |
+
import numpy as np
|
32 |
+
import torch
|
33 |
+
import gradio as gr
|
34 |
+
from PIL import Image, ImageFilter, ImageDraw
|
35 |
+
|
36 |
+
try:
|
37 |
+
torch.set_num_threads(int(omp_val))
|
38 |
+
torch.set_num_interop_threads(1)
|
39 |
+
except Exception:
|
40 |
+
pass
|
41 |
+
|
42 |
+
# ---------- HUB IMPORTS ----------
|
43 |
+
from huggingface_hub import snapshot_download, hf_hub_download
|
44 |
+
from diffusers import FluxFillPipeline, FluxPriorReduxPipeline
|
45 |
+
|
46 |
+
import math
|
47 |
+
from utils.utils import (
|
48 |
+
get_bbox_from_mask, expand_bbox, pad_to_square, box2squre, crop_back, expand_image_mask
|
49 |
+
)
|
50 |
+
|
51 |
+
# ---------- Ensure GroundingDINO & SAM are the right ones ----------
|
52 |
+
def _ensure_local_editable(pkg_name, rel_path):
|
53 |
+
try:
|
54 |
+
__import__(pkg_name)
|
55 |
+
except ImportError:
|
56 |
+
os.system(f"{sys.executable} -m pip install -e {rel_path}")
|
57 |
+
|
58 |
+
# GroundingDINO (local editable if present)
|
59 |
+
_ensure_local_editable("GroundingDINO", "GroundingDINO")
|
60 |
+
|
61 |
+
# SAM: verify the real package; fix automatically if a wrong one is installed
|
62 |
+
def _ensure_official_sam():
|
63 |
+
try:
|
64 |
+
import segment_anything as sa
|
65 |
+
if not hasattr(sa, "sam_model_registry"):
|
66 |
+
raise ImportError("Found 'segment_anything' without sam_model_registry")
|
67 |
+
except Exception:
|
68 |
+
# Nuke imposters and install the official repo
|
69 |
+
os.system(f"{sys.executable} -m pip uninstall -y segment-anything segment_anything")
|
70 |
+
os.system(f"{sys.executable} -m pip install -U git+https://github.com/facebookresearch/segment-anything.git")
|
71 |
+
|
72 |
+
_ensure_official_sam()
|
73 |
+
|
74 |
+
# Now import
|
75 |
+
sys.path.append(os.path.join(os.getcwd(), "GroundingDINO"))
|
76 |
+
import torchvision
|
77 |
+
from GroundingDINO.groundingdino.util.inference import load_model
|
78 |
+
from segment_anything import sam_model_registry, SamPredictor # official API
|
79 |
+
import spaces
|
80 |
+
import GroundingDINO.groundingdino.datasets.transforms as T
|
81 |
+
from GroundingDINO.groundingdino.util.utils import clean_state_dict, get_phrases_from_posmap
|
82 |
+
|
83 |
+
# ---------- PATHS ----------
|
84 |
+
PERSIST_ROOT = "/data"
|
85 |
+
MODELS_DIR = os.path.join(PERSIST_ROOT, "models")
|
86 |
+
CKPT_DIR = os.path.join(PERSIST_ROOT, "checkpoints")
|
87 |
+
os.makedirs(MODELS_DIR, exist_ok=True)
|
88 |
+
os.makedirs(CKPT_DIR, exist_ok=True)
|
89 |
+
|
90 |
+
# GroundingDINO config and checkpoint
|
91 |
+
GROUNDING_DINO_CONFIG_PATH = "./GroundingDINO_SwinB.cfg.py"
|
92 |
+
GROUNDING_DINO_CHECKPOINT_PATH = os.path.join(CKPT_DIR, "groundingdino_swinb_cogcoor.pth")
|
93 |
+
|
94 |
+
# Segment-Anything checkpoint
|
95 |
+
SAM_ENCODER_VERSION = "vit_h"
|
96 |
+
SAM_CHECKPOINT_PATH = os.path.join(CKPT_DIR, "sam_vit_h_4b8939.pth")
|
97 |
+
|
98 |
+
# ---------- AUTH TOKEN ----------
|
99 |
+
hf_token = os.getenv("HF_TOKEN") or os.getenv("HUGGINGFACE_HUB_TOKEN")
|
100 |
+
|
101 |
+
# ---------- DOWNLOAD CHECKPOINTS (single files) ----------
|
102 |
+
# Use hf_hub_download for single files, which returns a cached path. Keep files under /data. # https://huggingface.co/docs/huggingface_hub/en/guides/download
|
103 |
+
if not os.path.exists(GROUNDING_DINO_CHECKPOINT_PATH):
|
104 |
+
g_dino_file = hf_hub_download(
|
105 |
+
repo_id="ShilongLiu/GroundingDINO",
|
106 |
+
filename="groundingdino_swinb_cogcoor.pth",
|
107 |
+
local_dir=CKPT_DIR,
|
108 |
+
token=hf_token,
|
109 |
+
)
|
110 |
+
if g_dino_file != GROUNDING_DINO_CHECKPOINT_PATH:
|
111 |
+
os.replace(g_dino_file, GROUNDING_DINO_CHECKPOINT_PATH)
|
112 |
+
|
113 |
+
if not os.path.exists(SAM_CHECKPOINT_PATH):
|
114 |
+
sam_file = hf_hub_download(
|
115 |
+
repo_id="mrtlive/segment-anything-model", # remove "spaces/"
|
116 |
+
repo_type="space", # tell the Hub it's a Space
|
117 |
+
filename="sam_vit_h_4b8939.pth",
|
118 |
+
local_dir=CKPT_DIR,
|
119 |
+
token=hf_token,
|
120 |
+
)
|
121 |
+
if sam_file != SAM_CHECKPOINT_PATH:
|
122 |
+
os.replace(sam_file, SAM_CHECKPOINT_PATH)
|
123 |
+
|
124 |
+
# ---------- DOWNLOAD MODELS (filtered snapshots into /data) ----------
|
125 |
+
FILL_DIR = os.path.join(MODELS_DIR, "FLUX.1-Fill-dev")
|
126 |
+
REDUX_DIR = os.path.join(MODELS_DIR, "FLUX.1-Redux-dev")
|
127 |
+
LORA_DIR = os.path.join(MODELS_DIR, "insertanything_model")
|
128 |
+
for path in (FILL_DIR, REDUX_DIR, LORA_DIR):
|
129 |
+
os.makedirs(path, exist_ok=True)
|
130 |
+
|
131 |
+
# Only pull what we need (weights/configs). Keep symlinks to avoid copies.
|
132 |
+
if not os.listdir(FILL_DIR):
|
133 |
+
snapshot_download(
|
134 |
+
repo_id="black-forest-labs/FLUX.1-Fill-dev",
|
135 |
+
local_dir=FILL_DIR,
|
136 |
+
local_dir_use_symlinks=True,
|
137 |
+
allow_patterns=["*.safetensors", "*.json", "*.yaml", "*.txt", "*.py", "*.model"],
|
138 |
+
token=hf_token,
|
139 |
+
)
|
140 |
+
|
141 |
+
if not os.listdir(REDUX_DIR):
|
142 |
+
snapshot_download(
|
143 |
+
repo_id="black-forest-labs/FLUX.1-Redux-dev",
|
144 |
+
local_dir=REDUX_DIR,
|
145 |
+
local_dir_use_symlinks=True,
|
146 |
+
allow_patterns=["*.safetensors", "*.json", "*.yaml", "*.txt", "*.py", "*.model"],
|
147 |
+
token=hf_token,
|
148 |
+
)
|
149 |
+
|
150 |
+
if not os.listdir(LORA_DIR):
|
151 |
+
snapshot_download(
|
152 |
+
repo_id="WensongSong/Insert-Anything",
|
153 |
+
local_dir=LORA_DIR,
|
154 |
+
local_dir_use_symlinks=True,
|
155 |
+
allow_patterns=["*.safetensors", "*.json", "*.yaml", "*.txt"],
|
156 |
+
token=hf_token,
|
157 |
+
)
|
158 |
+
|
159 |
+
# ---------- BUILD MODELS ----------
|
160 |
+
# GroundingDINO
|
161 |
+
groundingdino_model = load_model(
|
162 |
+
model_config_path=GROUNDING_DINO_CONFIG_PATH,
|
163 |
+
model_checkpoint_path=GROUNDING_DINO_CHECKPOINT_PATH,
|
164 |
+
device="cuda"
|
165 |
+
)
|
166 |
+
|
167 |
+
# SAM + Predictor (registry API from official SAM) # https://github.com/facebookresearch/segment-anything
|
168 |
+
sam = sam_model_registry[SAM_ENCODER_VERSION](checkpoint=SAM_CHECKPOINT_PATH)
|
169 |
+
sam.to(device="cuda")
|
170 |
+
sam_predictor = SamPredictor(sam)
|
171 |
+
|
172 |
+
# Diffusers (Flux)
|
173 |
+
dtype = torch.bfloat16
|
174 |
+
size = (768, 768)
|
175 |
+
|
176 |
+
pipe = FluxFillPipeline.from_pretrained(
|
177 |
+
FILL_DIR,
|
178 |
+
torch_dtype=dtype
|
179 |
+
).to("cuda")
|
180 |
+
|
181 |
+
pipe.load_lora_weights(
|
182 |
+
os.path.join(LORA_DIR, "20250321_steps5000_pytorch_lora_weights.safetensors")
|
183 |
+
)
|
184 |
+
|
185 |
+
redux = FluxPriorReduxPipeline.from_pretrained(REDUX_DIR).to(dtype=dtype).to("cuda")
|
186 |
+
|
187 |
+
# ---------- APP LOGIC ----------
|
188 |
+
def transform_image(image_pil):
|
189 |
+
transform = T.Compose(
|
190 |
+
[
|
191 |
+
T.RandomResize([800], max_size=1333),
|
192 |
+
T.ToTensor(),
|
193 |
+
T.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225]),
|
194 |
+
]
|
195 |
+
)
|
196 |
+
image, _ = transform(image_pil, None) # 3, h, w
|
197 |
+
return image
|
198 |
+
|
199 |
+
|
200 |
+
def get_grounding_output(model, image, caption, box_threshold=0.25, text_threshold=0.25, with_logits=True):
|
201 |
+
caption = caption.lower().strip()
|
202 |
+
if not caption.endswith("."):
|
203 |
+
caption = caption + "."
|
204 |
+
with torch.no_grad():
|
205 |
+
outputs = model(image[None], captions=[caption])
|
206 |
+
logits = outputs["pred_logits"].cpu().sigmoid()[0] # (nq, 256)
|
207 |
+
boxes = outputs["pred_boxes"].cpu()[0] # (nq, 4)
|
208 |
+
|
209 |
+
# filter output
|
210 |
+
filt_mask = logits.max(dim=1)[0] > box_threshold
|
211 |
+
logits_filt = logits[filt_mask]
|
212 |
+
boxes_filt = boxes[filt_mask]
|
213 |
+
|
214 |
+
# get phrase
|
215 |
+
tokenlizer = model.tokenizer
|
216 |
+
tokenized = tokenlizer(caption)
|
217 |
+
pred_phrases, scores = [], []
|
218 |
+
for logit, box in zip(logits_filt, boxes_filt):
|
219 |
+
pred_phrase = get_phrases_from_posmap(logit > text_threshold, tokenized, tokenlizer)
|
220 |
+
pred_phrases.append(pred_phrase + f"({str(logit.max().item())[:4]})" if with_logits else pred_phrase)
|
221 |
+
scores.append(logit.max().item())
|
222 |
+
return boxes_filt, torch.Tensor(scores), pred_phrases
|
223 |
+
|
224 |
+
|
225 |
+
def get_mask(image, label):
|
226 |
+
global groundingdino_model, sam_predictor
|
227 |
+
image_pil = image.convert("RGB")
|
228 |
+
transformed_image = transform_image(image_pil)
|
229 |
+
|
230 |
+
boxes_filt, scores, pred_phrases = get_grounding_output(
|
231 |
+
groundingdino_model, transformed_image, label
|
232 |
+
)
|
233 |
+
|
234 |
+
W, H = image_pil.size
|
235 |
+
for i in range(boxes_filt.size(0)):
|
236 |
+
boxes_filt[i] = boxes_filt[i] * torch.Tensor([W, H, W, H])
|
237 |
+
boxes_filt[i][:2] -= boxes_filt[i][2:] / 2
|
238 |
+
boxes_filt[i][2:] += boxes_filt[i][:2]
|
239 |
+
boxes_filt = boxes_filt.cpu()
|
240 |
+
|
241 |
+
nms_idx = torchvision.ops.nms(boxes_filt, scores, 0.8).numpy().tolist()
|
242 |
+
boxes_filt = boxes_filt[nms_idx]
|
243 |
+
|
244 |
+
image_np = np.array(image_pil)
|
245 |
+
sam_predictor.set_image(image_np)
|
246 |
+
transformed_boxes = sam_predictor.transform.apply_boxes_torch(
|
247 |
+
boxes_filt, image_np.shape[:2]
|
248 |
+
).to("cuda")
|
249 |
+
|
250 |
+
masks, _, _ = sam_predictor.predict_torch(
|
251 |
+
point_coords=None,
|
252 |
+
point_labels=None,
|
253 |
+
boxes=transformed_boxes,
|
254 |
+
multimask_output=False,
|
255 |
+
)
|
256 |
+
result_mask = masks[0][0].cpu().numpy()
|
257 |
+
return Image.fromarray(result_mask)
|
258 |
+
|
259 |
+
|
260 |
+
def create_highlighted_mask(image_np, mask_np, alpha=0.5, gray_value=128):
|
261 |
+
if mask_np.max() <= 1.0:
|
262 |
+
mask_np = (mask_np * 255).astype(np.uint8)
|
263 |
+
mask_bool = mask_np > 128
|
264 |
+
image_float = image_np.astype(np.float32)
|
265 |
+
gray_overlay = np.full_like(image_float, gray_value, dtype=np.float32)
|
266 |
+
result = image_float.copy()
|
267 |
+
result[mask_bool] = (1 - alpha) * image_float[mask_bool] + alpha * gray_overlay[mask_bool]
|
268 |
+
return result.astype(np.uint8)
|
269 |
+
|
270 |
+
|
271 |
+
# ---------- EXAMPLES ----------
|
272 |
+
ref_dir = './examples/ref_image'
|
273 |
+
ref_mask_dir = './examples/ref_mask'
|
274 |
+
image_dir = './examples/source_image'
|
275 |
+
image_mask_dir = './examples/source_mask'
|
276 |
+
|
277 |
+
ref_list = sorted([os.path.join(ref_dir, f) for f in os.listdir(ref_dir) if f.lower().endswith((".jpg", ".png", ".jpeg"))])
|
278 |
+
ref_mask_list = sorted([os.path.join(ref_mask_dir, f) for f in os.listdir(ref_mask_dir) if f.lower().endswith((".jpg", ".png", ".jpeg"))])
|
279 |
+
image_list = sorted([os.path.join(image_dir, f) for f in os.listdir(image_dir) if f.lower().endswith((".jpg", ".png", ".jpeg"))])
|
280 |
+
image_mask_list = sorted([os.path.join(image_mask_dir, f) for f in os.listdir(image_mask_dir) if f.lower().endswith((".jpg", ".png", ".jpeg"))])
|
281 |
+
|
282 |
+
|
283 |
@spaces.GPU
|
284 |
def run_local(base_image, base_mask, reference_image, ref_mask, seed, base_mask_option, ref_mask_option, text_prompt):
|
285 |
if base_mask_option == "Draw Mask":
|
|
|
396 |
if ref_mask_option != "Label to Mask":
|
397 |
return [show_diptych_ref_tar, edited_image, received_tar_mask, received_ref_mask]
|
398 |
else:
|
399 |
+
return [return_ref_mask, show_diptych_ref_tar, edited_image, received_tar_mask, received_ref_mask]
|
400 |
+
|
401 |
+
|
402 |
+
def update_ui(option):
|
403 |
+
if option == "Draw Mask":
|
404 |
+
return gr.update(visible=False), gr.update(visible=True)
|
405 |
+
else:
|
406 |
+
return gr.update(visible=True), gr.update(visible=False)
|
407 |
+
|
408 |
+
|
409 |
+
with gr.Blocks() as demo:
|
410 |
+
gr.Markdown("# Insert-Anything")
|
411 |
+
gr.Markdown("### Make sure to select the correct mask button!!")
|
412 |
+
gr.Markdown("### Click the output image to toggle between Diptych and final results!!")
|
413 |
+
|
414 |
+
with gr.Row():
|
415 |
+
with gr.Column(scale=1):
|
416 |
+
with gr.Row():
|
417 |
+
base_image = gr.ImageEditor(label="Background Image", sources="upload", type="pil",
|
418 |
+
brush=gr.Brush(colors=["#FFFFFF"], default_size=30, color_mode="fixed"),
|
419 |
+
layers=False, interactive=True)
|
420 |
+
base_mask = gr.ImageEditor(label="Background Mask", sources="upload", type="pil",
|
421 |
+
layers=False, brush=False, eraser=False)
|
422 |
+
with gr.Row():
|
423 |
+
base_mask_option = gr.Radio(["Draw Mask", "Upload with Mask"], label="Background Mask Input Option",
|
424 |
+
value="Upload with Mask")
|
425 |
+
|
426 |
+
with gr.Row():
|
427 |
+
ref_image = gr.ImageEditor(label="Reference Image", sources="upload", type="pil",
|
428 |
+
brush=gr.Brush(colors=["#FFFFFF"], default_size=30, color_mode="fixed"),
|
429 |
+
layers=False, interactive=True)
|
430 |
+
ref_mask = gr.ImageEditor(label="Reference Mask", sources="upload", type="pil",
|
431 |
+
layers=False, brush=False, eraser=False)
|
432 |
+
|
433 |
+
with gr.Row():
|
434 |
+
ref_mask_option = gr.Radio(["Draw Mask", "Upload with Mask", "Label to Mask"],
|
435 |
+
label="Reference Mask Input Option", value="Upload with Mask")
|
436 |
+
with gr.Row():
|
437 |
+
text_prompt = gr.Textbox(label="Label",
|
438 |
+
placeholder="Enter the category of the reference object, e.g., car, dress, toy, etc.")
|
439 |
+
|
440 |
+
with gr.Column(scale=1):
|
441 |
+
baseline_gallery = gr.Gallery(label='Output', show_label=True, elem_id="gallery", height=695, columns=1)
|
442 |
+
with gr.Accordion("Advanced Option", open=True):
|
443 |
+
seed = gr.Slider(label="Seed", minimum=-1, maximum=999_999_999, step=1, value=666)
|
444 |
+
gr.Markdown("### Guidelines")
|
445 |
+
gr.Markdown(" Users can try using different seeds. For example, seeds like 42 and 123456 may produce different effects.")
|
446 |
+
gr.Markdown(" Draw Mask means manually drawing a mask on the original image.")
|
447 |
+
gr.Markdown(" Upload with Mask means uploading a mask file.")
|
448 |
+
gr.Markdown(" Label to Mask means simply inputting a label to automatically extract the mask and obtain the result.")
|
449 |
+
|
450 |
+
run_local_button = gr.Button(value="Run")
|
451 |
+
|
452 |
+
# examples
|
453 |
+
num_examples = len(image_list)
|
454 |
+
for i in range(num_examples):
|
455 |
+
with gr.Row():
|
456 |
+
if i == 0:
|
457 |
+
gr.Examples([image_list[i]], inputs=[base_image], label="Examples - Background Image", examples_per_page=1)
|
458 |
+
gr.Examples([image_mask_list[i]], inputs=[base_mask], label="Examples - Background Mask", examples_per_page=1)
|
459 |
+
gr.Examples([ref_list[i]], inputs=[ref_image], label="Examples - Reference Object", examples_per_page=1)
|
460 |
+
gr.Examples([ref_mask_list[i]], inputs=[ref_mask], label="Examples - Reference Mask", examples_per_page=1)
|
461 |
+
else:
|
462 |
+
gr.Examples([image_list[i]], inputs=[base_image], examples_per_page=1, label="")
|
463 |
+
gr.Examples([image_mask_list[i]], inputs=[base_mask], examples_per_page=1, label="")
|
464 |
+
gr.Examples([ref_list[i]], inputs=[ref_image], examples_per_page=1, label="")
|
465 |
+
gr.Examples([ref_mask_list[i]], inputs=[ref_mask], examples_per_page=1, label="")
|
466 |
+
if i < num_examples - 1:
|
467 |
+
gr.HTML("<hr>")
|
468 |
+
|
469 |
+
run_local_button.click(
|
470 |
+
fn=run_local,
|
471 |
+
inputs=[base_image, base_mask, ref_image, ref_mask, seed, base_mask_option, ref_mask_option, text_prompt],
|
472 |
+
outputs=[baseline_gallery]
|
473 |
+
)
|
474 |
+
demo.launch()
|