Spaces:
Thafx
/
Runtime error

Thafx commited on
Commit
b465a37
1 Parent(s): c771080

Update app.py

Browse files
Files changed (1) hide show
  1. app.py +11 -10
app.py CHANGED
@@ -3,7 +3,7 @@ import gradio as gr
3
  import torch
4
  from PIL import Image
5
 
6
- model_id = 'SG161222/Realistic_Vision_V2.0'
7
  prefix = 'RAW photo,'
8
 
9
  scheduler = DPMSolverMultistepScheduler.from_pretrained(model_id, subfolder="scheduler")
@@ -107,11 +107,11 @@ with gr.Blocks(css=css) as demo:
107
  f"""
108
  <div class="main-div">
109
  <div>
110
- <h1 style="color:orange;">📷 Realistic Vision V2.0 📸</h1>
111
  </div>
112
  <p>
113
- Demo for <a href="https://huggingface.co/SG161222/Realistic_Vision_V2.0">Realistic Vision V2.0</a>
114
- Stable Diffusion model by <a href="https://huggingface.co/SG161222/"><abbr title="SG1611222">Eugene</abbr></a>. {"" if prefix else ""}
115
  Running on {"<b>GPU 🔥</b>" if torch.cuda.is_available() else f"<b>CPU ⚡</b>"}.
116
  </p>
117
  <p>Please use the prompt template below to get an example of the desired generation results:
@@ -123,20 +123,21 @@ RAW photo, * subject *, (high detailed skin:1.2), 8k uhd, dslr, soft lighting, h
123
  <br>
124
  <br>
125
  <q><i>
126
- Example: RAW photo, a close up portrait photo of 26 y.o woman in wastelander clothes, long haircut, pale skin, slim body, background is city ruins, <br>
127
- (high detailed skin:1.2), 8k uhd, dslr, soft lighting, high quality, film grain, Fujifilm XT3
128
  </i></q>
129
  </code></details>
130
 
131
  <br>
132
  <b>Negative Prompt</b>:
133
  <details><code>
134
- (deformed iris, deformed pupils, semi-realistic, cgi, 3d, render, sketch, cartoon, drawing, anime:1.4), text, close up, cropped, out of frame, worst quality, <br>
135
- low quality, jpeg artifacts, ugly, duplicate, morbid, mutilated, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, mutation, deformed, blurry, <br>
136
- dehydrated, bad anatomy, bad proportions, extra limbs, cloned face, disfigured, gross proportions, malformed limbs, missing arms, missing legs, extra arms, <br>
137
- extra legs, fused fingers, too many fingers, long neck
138
  </code></details>
 
 
139
 
 
140
  <br>
141
  Have Fun & Enjoy ⚡ <a href="https://www.thafx.com"><abbr title="Website">//THAFX</abbr></a>
142
  <br>
 
3
  import torch
4
  from PIL import Image
5
 
6
+ model_id = 'digiplay/RunDiffusionFXPhotorealistic_v1'
7
  prefix = 'RAW photo,'
8
 
9
  scheduler = DPMSolverMultistepScheduler.from_pretrained(model_id, subfolder="scheduler")
 
107
  f"""
108
  <div class="main-div">
109
  <div>
110
+ <h1 style="color:orange;">📷 RunDiffusionFXPhotorealistic V1.0 📸</h1>
111
  </div>
112
  <p>
113
+ Demo for <a href="https://huggingface.co/digiplay/RunDiffusionFXPhotorealistic_v1">RunDiffusionFXPhotorealistic V1.0</a>
114
+ Stable Diffusion model by <a href="https://huggingface.co/digiplay/"><abbr title="digiplay">digiplay</abbr></a>. {"" if prefix else ""}
115
  Running on {"<b>GPU 🔥</b>" if torch.cuda.is_available() else f"<b>CPU ⚡</b>"}.
116
  </p>
117
  <p>Please use the prompt template below to get an example of the desired generation results:
 
123
  <br>
124
  <br>
125
  <q><i>
126
+ Example: (hyperrealism:1.2), BREAK fish swimming under the water BREAK (8K UHD:1.2), (photorealistic:1.2)
 
127
  </i></q>
128
  </code></details>
129
 
130
  <br>
131
  <b>Negative Prompt</b>:
132
  <details><code>
133
+ e.g. : plain background, boring, plain, standard, homogenous, uncreative, unattractive, opaque, grayscale, monochrome, distorted details, low details, grains,
134
+ grainy, foggy, dark, blurry, portrait, oversaturated, low contrast, underexposed, overexposed, low-res, low quality, close-up, macro, surreal, multiple views,
135
+ multiple angles
 
136
  </code></details>
137
+ <br>
138
+ Wide/Tall aspect ratios like '480x832'/'832x480' work great then you can upscale.
139
 
140
+ You can use a CFG scale of 3.5 to 5 to get some softer photorealistic images.
141
  <br>
142
  Have Fun & Enjoy ⚡ <a href="https://www.thafx.com"><abbr title="Website">//THAFX</abbr></a>
143
  <br>