Update app.py

app.py

@@ -9,14 +9,14 @@ from transformers import CLIPTextModel, CLIPTokenizer,T5EncoderModel, T5Tokenize
 dtype = torch.bfloat16
 device = "cuda"
 
-sd3_repo = "stabilityai/stable-diffusion-3-medium-diffusers"
-scheduler = FlowMatchEulerDiscreteScheduler.from_pretrained (sd3_repo, subfolder="scheduler")
+bfl_repo = "black-forest-labs/FLUX.1-schnell"
+scheduler = FlowMatchEulerDiscreteScheduler.from_pretrained(bfl_repo, subfolder="scheduler", revision="refs/pr/1")
 text_encoder = CLIPTextModel.from_pretrained("openai/clip-vit-large-patch14", torch_dtype=dtype)
 tokenizer = CLIPTokenizer.from_pretrained("openai/clip-vit-large-patch14", torch_dtype=dtype)
-text_encoder_2 = T5EncoderModel.from_pretrained(sd3_repo, subfolder="text_encoder_3", torch_dtype=dtype)
-tokenizer_2 = T5TokenizerFast.from_pretrained(sd3_repo, subfolder="tokenizer_3", torch_dtype=dtype)
-vae = AutoencoderKL.from_pretrained("diffusers-internal-dev/FLUX.1-schnell", subfolder="vae", torch_dtype=dtype)
-transformer = FluxTransformer2DModel.from_pretrained("diffusers-internal-dev/FLUX.1-schnell", subfolder="transformer", torch_dtype=dtype)
+text_encoder_2 = T5EncoderModel.from_pretrained(bfl_repo, subfolder="text_encoder_2", torch_dtype=dtype, revision="refs/pr/1")
+tokenizer_2 = T5TokenizerFast.from_pretrained(bfl_repo, subfolder="tokenizer_2", torch_dtype=dtype, revision="refs/pr/1")
+vae = AutoencoderKL.from_pretrained(bfl_repo, subfolder="vae", torch_dtype=dtype, revision="refs/pr/1")
+transformer = FluxTransformer2DModel.from_pretrained("diffusers-internal-dev/FLUX.1-dev", subfolder="transformer", torch_dtype=dtype, revision="refs/pr/1")
 
 device = "cuda" if torch.cuda.is_available() else "cpu"
 
@@ -34,7 +34,7 @@ MAX_SEED = np.iinfo(np.int32).max
 MAX_IMAGE_SIZE = 2048
 
 @spaces.GPU()
-def infer(prompt, seed=42, randomize_seed=False, width=1024, height=1024, num_inference_steps=4, progress=gr.Progress(track_tqdm=True)):
+def infer(prompt, seed=42, randomize_seed=False, width=1024, height=1024, guidance_scale=5.0, num_inference_steps=28, progress=gr.Progress(track_tqdm=True)):
     if randomize_seed:
         seed = random.randint(0, MAX_SEED)
     generator = torch.Generator().manual_seed(seed)
@@ -44,7 +44,7 @@ def infer(prompt, seed=42, randomize_seed=False, width=1024, height=1024, num_in
             height = height,
             num_inference_steps = num_inference_steps, 
             generator = generator,
-            guidance_scale=0.0
+            guidance_scale=guidance_scale
     ).images[0] 
     return image, seed
  
@@ -114,14 +114,21 @@ with gr.Blocks(css=css) as demo:
                 )
             
             with gr.Row():
-                
+
+                guidance_scale = gr.Slider(
+                    label="Guidance Scale",
+                    minimum=1,
+                    maximum=15,
+                    step=1,
+                    value=5.0,
+                )
   
                 num_inference_steps = gr.Slider(
                     label="Number of inference steps",
                     minimum=1,
                     maximum=50,
                     step=1,
-                    value=4,
+                    value=28,
                 )
         
         gr.Examples(
@@ -135,7 +142,7 @@ with gr.Blocks(css=css) as demo:
     gr.on(
         triggers=[run_button.click, prompt.submit],
         fn = infer,
-        inputs = [prompt, seed, randomize_seed, width, height, num_inference_steps],
+        inputs = [prompt, seed, randomize_seed, width, height, guidance_scale, num_inference_steps],
         outputs = [result, seed]
     )