Thafx commited on
Commit
f2dfa3d
·
1 Parent(s): 6060d1a

Update app.py

Browse files
Files changed (1) hide show
  1. app.py +15 -14
app.py CHANGED
@@ -79,26 +79,27 @@ with gr.Blocks(css=css) as demo:
79
  <h1>Realistic Vision V1.3</h1>
80
  </div>
81
  <p>
82
- Demo for <a href="https://huggingface.co/SG161222/Realistic_Vision_V1.3">Realistic Vision V1.3</a> Stable Diffusion model by "Eugene".
83
 
84
- Please use this prompt template to get the desired generation results:
85
 
86
- Prompt:
87
- RAW photo, *subject*, (high detailed skin:1.2), 8k uhd, dslr, soft lighting, high quality, film grain, Fujifilm XT3
88
 
89
  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, (high detailed skin:1.2), 8k uhd, dslr, soft lighting, high quality, film grain, Fujifilm XT3
 
90
 
91
-
92
- Negative Prompt:
93
  (deformed iris, deformed pupils, semi-realistic, cgi, 3d, render, sketch, cartoon, drawing, anime:1.4), text, close up, cropped, out of frame, worst quality, low quality, jpeg artifacts, ugly, duplicate, morbid, mutilated, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, mutation, deformed, blurry, dehydrated, bad anatomy, bad proportions, extra limbs, cloned face, disfigured, gross proportions, malformed limbs, missing arms, missing legs, extra arms, extra legs, fused fingers, too many fingers, long neck
94
-
95
- Euler a with 25 steps
96
- CFG Scale 7
97
- Hires. fix with R-ESRGAN General WDN 4xV3 upscaler
98
- 25 Hires steps and Denoising strength 0.25-0.7
99
- or
100
- 10 Hires steps and Denoising strength 0.025-0.1 for save more details
101
-
 
102
  Have Fun & Enjoy
103
  //THAFX<br>
104
  {"Add the following tokens to your prompts for the model to work properly: <b>prefix</b>" if prefix else ""}
 
79
  <h1>Realistic Vision V1.3</h1>
80
  </div>
81
  <p>
82
+ Demo for <a href="https://huggingface.co/SG161222/Realistic_Vision_V1.3">Realistic Vision V1.3</a> Stable Diffusion model by "Eugene".<br>
83
 
84
+ Please use this prompt template to get the desired generation results:<br>
85
 
86
+ <b>Prompt</b>:
87
+ RAW photo, *subject*, (high detailed skin:1.2), 8k uhd, dslr, soft lighting, high quality, film grain, Fujifilm XT3<br>
88
 
89
  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, (high detailed skin:1.2), 8k uhd, dslr, soft lighting, high quality, film grain, Fujifilm XT3
90
+ <br>
91
 
92
+ <b>Negative Prompt</b>:
 
93
  (deformed iris, deformed pupils, semi-realistic, cgi, 3d, render, sketch, cartoon, drawing, anime:1.4), text, close up, cropped, out of frame, worst quality, low quality, jpeg artifacts, ugly, duplicate, morbid, mutilated, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, mutation, deformed, blurry, dehydrated, bad anatomy, bad proportions, extra limbs, cloned face, disfigured, gross proportions, malformed limbs, missing arms, missing legs, extra arms, extra legs, fused fingers, too many fingers, long neck
94
+ <br>
95
+ <b>Settings</b><br>
96
+ -Euler a : 25 steps<br>
97
+ -CFG Scale : 7<br>
98
+ -Hires. fix with R-ESRGAN General WDN 4xV3 upscaler<br>
99
+ -25 Hires steps and Denoising strength 0.25-0.7<br>
100
+ or<br>
101
+ -10 Hires steps and Denoising strength 0.025-0.1 to save more details
102
+ <br>
103
  Have Fun & Enjoy
104
  //THAFX<br>
105
  {"Add the following tokens to your prompts for the model to work properly: <b>prefix</b>" if prefix else ""}