Update the description of the app, and switch the base diffuser to something else.

app.py

@@ -155,9 +155,7 @@ if OPENAI_API_KEY:
 with gr.Blocks(css="#chatbot {overflow:auto; height:500px;}") as demo:
     gr.Markdown("<h3><center>Visual ChatGPT</center></h3>")
     gr.Markdown(
-        """This is a demo to the work [Visual ChatGPT: Talking, Drawing and Editing with Visual Foundation Models](https://github.com/microsoft/visual-chatgpt).<br>
-        This space connects ChatGPT and a series of Visual Foundation Models to enable sending and receiving images during chatting.<br>  
-        This space currently only supports English (目前只支持英文对话, 中文正在开发中).<br>
+        """This is based on the [demo](https://huggingface.co/spaces/microsoft/visual_chatgpt) to the work [Visual ChatGPT: Talking, Drawing and Editing with Visual Foundation Models](https://github.com/microsoft/visual-chatgpt).<br>
         """
     )
 
@@ -214,6 +212,7 @@ with gr.Blocks(css="#chatbot {overflow:auto; height:500px;}") as demo:
     run.click(lambda: "", None, txt)
 
     btn.upload(bot.run_image, [btn, state, txt], [chatbot, state, txt])
+
     clear.click(bot.memory.clear)
     clear.click(lambda: [], None, chatbot)
     clear.click(lambda: [], None, state)

visual_foundation_models.py

@@ -16,6 +16,8 @@ from PIL import Image
 import numpy as np
 from pytorch_lightning import seed_everything
 
+base_diffuser = "johnslegers/epic-diffusion-v1.1"
+
 def prompts(name, description):
     def decorator(func):
         func.name = name
@@ -145,10 +147,10 @@ class Text2Image:
         print(f"Initializing Text2Image to {device}")
         self.device = device
         self.torch_dtype = torch.float16 if 'cuda' in device else torch.float32
-        self.pipe = StableDiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5",
+        self.pipe = StableDiffusionPipeline.from_pretrained(base_diffuser,
                                                             torch_dtype=self.torch_dtype)
         self.pipe.to(device)
-        self.a_prompt = 'best quality, extremely detailed'
+        self.a_prompt = 'digital art, highly detailed, intricate, sharp focus, Trending on Artstation, deviantart, unreal engine 5, 4K UHD image'
         self.n_prompt = 'longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, ' \
                         'fewer digits, cropped, worst quality, low quality'
 
@@ -217,7 +219,7 @@ class CannyText2Image:
         self.controlnet = ControlNetModel.from_pretrained("fusing/stable-diffusion-v1-5-controlnet-canny",
                                                           torch_dtype=self.torch_dtype)
         self.pipe = StableDiffusionControlNetPipeline.from_pretrained(
-            "runwayml/stable-diffusion-v1-5", controlnet=self.controlnet, safety_checker=None,
+            base_diffuser, controlnet=self.controlnet, safety_checker=None,
             torch_dtype=self.torch_dtype)
         self.pipe.scheduler = UniPCMultistepScheduler.from_config(self.pipe.scheduler.config)
         self.pipe.to(device)
@@ -273,7 +275,7 @@ class LineText2Image:
         self.controlnet = ControlNetModel.from_pretrained("fusing/stable-diffusion-v1-5-controlnet-mlsd",
                                                           torch_dtype=self.torch_dtype)
         self.pipe = StableDiffusionControlNetPipeline.from_pretrained(
-            "runwayml/stable-diffusion-v1-5", controlnet=self.controlnet, safety_checker=None,
+            base_diffuser, controlnet=self.controlnet, safety_checker=None,
             torch_dtype=self.torch_dtype
         )
         self.pipe.scheduler = UniPCMultistepScheduler.from_config(self.pipe.scheduler.config)
@@ -331,7 +333,7 @@ class HedText2Image:
         self.controlnet = ControlNetModel.from_pretrained("fusing/stable-diffusion-v1-5-controlnet-hed",
                                                           torch_dtype=self.torch_dtype)
         self.pipe = StableDiffusionControlNetPipeline.from_pretrained(
-            "runwayml/stable-diffusion-v1-5", controlnet=self.controlnet, safety_checker=None,
+            base_diffuser, controlnet=self.controlnet, safety_checker=None,
             torch_dtype=self.torch_dtype
         )
         self.pipe.scheduler = UniPCMultistepScheduler.from_config(self.pipe.scheduler.config)
@@ -389,7 +391,7 @@ class ScribbleText2Image:
         self.controlnet = ControlNetModel.from_pretrained("fusing/stable-diffusion-v1-5-controlnet-scribble",
                                                           torch_dtype=self.torch_dtype)
         self.pipe = StableDiffusionControlNetPipeline.from_pretrained(
-            "runwayml/stable-diffusion-v1-5", controlnet=self.controlnet, safety_checker=None,
+            base_diffuser, controlnet=self.controlnet, safety_checker=None,
             torch_dtype=self.torch_dtype
         )
         self.pipe.scheduler = UniPCMultistepScheduler.from_config(self.pipe.scheduler.config)
@@ -444,7 +446,7 @@ class PoseText2Image:
         self.controlnet = ControlNetModel.from_pretrained("fusing/stable-diffusion-v1-5-controlnet-openpose",
                                                           torch_dtype=self.torch_dtype)
         self.pipe = StableDiffusionControlNetPipeline.from_pretrained(
-            "runwayml/stable-diffusion-v1-5", controlnet=self.controlnet, safety_checker=None,
+            base_diffuser, controlnet=self.controlnet, safety_checker=None,
             torch_dtype=self.torch_dtype)
         self.pipe.scheduler = UniPCMultistepScheduler.from_config(self.pipe.scheduler.config)
         self.pipe.to(device)
@@ -551,7 +553,7 @@ class SegText2Image:
         self.controlnet = ControlNetModel.from_pretrained("fusing/stable-diffusion-v1-5-controlnet-seg",
                                                           torch_dtype=self.torch_dtype)
         self.pipe = StableDiffusionControlNetPipeline.from_pretrained(
-            "runwayml/stable-diffusion-v1-5", controlnet=self.controlnet, safety_checker=None,
+            base_diffuser, controlnet=self.controlnet, safety_checker=None,
             torch_dtype=self.torch_dtype)
         self.pipe.scheduler = UniPCMultistepScheduler.from_config(self.pipe.scheduler.config)
         self.pipe.to(device)
@@ -610,7 +612,7 @@ class DepthText2Image:
         self.controlnet = ControlNetModel.from_pretrained(
             "fusing/stable-diffusion-v1-5-controlnet-depth", torch_dtype=self.torch_dtype)
         self.pipe = StableDiffusionControlNetPipeline.from_pretrained(
-            "runwayml/stable-diffusion-v1-5", controlnet=self.controlnet, safety_checker=None,
+            base_diffuser, controlnet=self.controlnet, safety_checker=None,
             torch_dtype=self.torch_dtype)
         self.pipe.scheduler = UniPCMultistepScheduler.from_config(self.pipe.scheduler.config)
         self.pipe.to(device)
@@ -681,7 +683,7 @@ class NormalText2Image:
         self.controlnet = ControlNetModel.from_pretrained(
             "fusing/stable-diffusion-v1-5-controlnet-normal", torch_dtype=self.torch_dtype)
         self.pipe = StableDiffusionControlNetPipeline.from_pretrained(
-            "runwayml/stable-diffusion-v1-5", controlnet=self.controlnet, safety_checker=None,
+            base_diffuser, controlnet=self.controlnet, safety_checker=None,
             torch_dtype=self.torch_dtype)
         self.pipe.scheduler = UniPCMultistepScheduler.from_config(self.pipe.scheduler.config)
         self.pipe.to(device)