santhosh97 commited on
Commit
66ac19a
1 Parent(s): d610380

Update app.py

Browse files
Files changed (1) hide show
  1. app.py +8 -11
app.py CHANGED
@@ -208,7 +208,7 @@ def train_model(model_inputs):
208
  # if cli_args.train_endpoint_url is None:
209
  # Use banana backend
210
  api_key = "03cdd72e-5c04-4207-bd6a-fd5712c1740e"
211
- model_key = "bd2c55f5-84bb-40f9-82fb-196ca68b1c1d"
212
  #st.markdown(str(model_inputs))
213
  #print(model_inputs)
214
  _ = banana.run(api_key, model_key, model_inputs)
@@ -374,17 +374,14 @@ def run_prompts():
374
  #prompt = st.text_input("Token Name")
375
  st.caption(
376
  """
377
- In general, the best stable diffusion prompts will have this form:
378
 
379
- `A [prompt], [prompt_keywords]`
380
-
381
- The `[prompt]`can be anything you’re thinking of, but Stable Diffusion still struggles with compositionality, so it shouldn’t be more than one or two main things (say, a beaver wearing a suit, or a cat samurai with a pet pug). The main subject should be mostly composed of adjectives and nouns. Avoid verbs, as Stable Diffusion has a hard time interpreting them correctly.
382
-
383
- `[Prompt Keywords]` can be anything you want to condition the image on. I wouldn’t add too many, maybe only 1 to 3. These can really vary a lot but some good ones are: `[concept art, steampunk, trending in artstation, good composition, hyper realistic, oil on canvas, vivid colors]`.
384
-
385
- Additionally, adding the name of an artist as a cue will make the picture look like something that artist made, though it may condition the image’s contents, especially if that artist had narrow themes (Beatrix Potter gets you spurious rabbits, for instance).
386
-
387
- You can also find many great prompts if you use the Lexica.art prompt search engine to find images you like and make tweaks to their prompts.
388
  """
389
  )
390
  st.text("")
 
208
  # if cli_args.train_endpoint_url is None:
209
  # Use banana backend
210
  api_key = "03cdd72e-5c04-4207-bd6a-fd5712c1740e"
211
+ model_key = "12f50d2a-fc6a-4334-b77f-e97fcabdee65"
212
  #st.markdown(str(model_inputs))
213
  #print(model_inputs)
214
  _ = banana.run(api_key, model_key, model_inputs)
 
374
  #prompt = st.text_input("Token Name")
375
  st.caption(
376
  """
377
+ The `[Prompt]` and `[Prompt Keywords]` are descriptions of what you would like the model to generate.
378
 
379
+ We recommend using a simple sentence covering 1 or 2 concepts for the Prompt. Nouns or adjectives are preferred, as verbs can be more challenging for the model. Examples of good `[prompts]`:
380
+ - A charlock plant in the snow
381
+ - A beaver wearing a suit
382
+ - A cat samurai with a pet pug
383
+
384
+ You may also add 1 to 3 comma-separated `[Prompt Keywords]` to describe the desired "mood" of the generated images. Examples of good `[Prompt Keywords]` include: concept art, steampunk, trending in ArtStation, good composition, hyper realistic, vivid colors, oil on canvas, Vincent van Gogh.
 
 
 
385
  """
386
  )
387
  st.text("")