Spaces:
Running
on
Zero
Running
on
Zero
Fix: display introduction text
Browse files
app.py
CHANGED
@@ -153,7 +153,23 @@ header = """
|
|
153 |
|
154 |
with gr.Blocks(title="🌍 ZenCtrl") as demo:
|
155 |
gr.HTML(header)
|
156 |
-
gr.Markdown(
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
157 |
|
158 |
with gr.Tabs():
|
159 |
for mode in MODE_DEFAULTS:
|
|
|
153 |
|
154 |
with gr.Blocks(title="🌍 ZenCtrl") as demo:
|
155 |
gr.HTML(header)
|
156 |
+
gr.Markdown(
|
157 |
+
"""
|
158 |
+
# ZenCtrl Demo
|
159 |
+
[WIP] One Agent to Generate multi-view, diverse-scene, and task-specific high-resolution images from a single subject image—without fine-tuning.
|
160 |
+
We are first releasing some of the task specific weights and will release the codes soon.
|
161 |
+
The goal is to unify all of the visual content generation tasks with a single LLM...
|
162 |
+
|
163 |
+
**Modes:**
|
164 |
+
- **Subject Generation:** Focuses on generating detailed subject portraits.
|
165 |
+
- **Background Generation:** Creates dynamic, vibrant backgrounds:
|
166 |
+
You can generate part of the image from sketch while keeping part of it as it is.
|
167 |
+
- **Canny:** Emphasizes strong edge detection.
|
168 |
+
- **Depth:** Produces images with realistic depth and perspective.
|
169 |
+
|
170 |
+
For more details, shoot us a message on discord.
|
171 |
+
"""
|
172 |
+
)
|
173 |
|
174 |
with gr.Tabs():
|
175 |
for mode in MODE_DEFAULTS:
|