add more scheduler descriptions

app.py

@@ -223,7 +223,7 @@ with gr.Blocks(analytics_enabled=False) as demo:
 
     gr.Markdown("### Scheduler")
     with gr.Row():
-        in_schedulers = gr.Dropdown(choices=list(schedulers.keys()), label="Scheduler", info="see https://huggingface.co/docs/diffusers/using-diffusers/loading#schedulers" )
+        in_schedulers = gr.Dropdown(choices=list(schedulers.keys()), label="Scheduler/Solver", info="the scheduler controls parameter adaption between each inference step, depending on the right scheduler for your model, it may only take 10 or 20 steps to achieve very good results, see https://huggingface.co/docs/diffusers/using-diffusers/loading#schedulers" )
         out_scheduler_description = gr.Textbox(value="", label="Description")
     
     gr.Markdown("### Adapters")

appConfig.json

@@ -64,13 +64,13 @@
         "cpu", "cuda", "ipu", "xpu", "mkldnn", "opengl", "opencl", "ideep", "hip", "ve", "fpga", "ort", "xla", "lazy", "vulkan", "mps", "meta", "hpu", "mtia", "privateuseone", "gpu"
     ],
     "schedulers": {
-        "DDPMScheduler":                    "This is DDPM",  
-        "DDIMScheduler":                    "This is DDIM",  
-        "PNDMScheduler":                    "This is PNDM",
-        "LMSDiscreteScheduler":             "This is LMS",
-        "EulerAncestralDiscreteScheduler":  "This is Euler, too",
-        "EulerDiscreteScheduler":           "This is Euler",
-        "DPMSolverMultistepScheduler":      "This is DPM Solve Multistep"
+        "DDPMScheduler":                    "Denoising Diffusion Probabilistic Model",  
+        "DDIMScheduler":                    "Denoising Diffusion Incremental Sampling, efficient image generation, might require more tunin",  
+        "PNDMScheduler":                    "Pseudo Numerical Methods for Diffusion Models, not compatible with DDPM pipelines, probably more flexible but with in increased complexity and performance trade-offs",
+        "LMSDiscreteScheduler":             "Linear Multistep Scheduler, often leads to better quality results, linear approach, pre-defined noise levels at each step",
+        "EulerDiscreteScheduler":           "can achieve high quality images with fewer steps, predefined set of noise levels for each step",
+        "EulerAncestralDiscreteScheduler":  "can achieve high quality images with fewer steps, incorporates ancestral sampling for potentially improved image quality but less speed as its twin",
+        "DPMSolverMultistepScheduler":      "offers a balance between speed and quality, potentially better than Euler in speed and quality, faster than PNDM, similar to LMS"
     },
     "negative_prompts": [
         "lowres, cropped, worst quality, low quality"