llava-next

3.py

@@ -1,5 +0,0 @@
-# Load model directly
-from transformers import AutoProcessor, AutoModelForCausalLM
-
-processor = AutoProcessor.from_pretrained("lmms-lab/LLaVA-NeXT-Video-32B-Qwen")
-model = AutoModelForCausalLM.from_pretrained("lmms-lab/LLaVA-NeXT-Video-32B-Qwen")

app.old

@@ -0,0 +1,146 @@
+import gradio as gr
+import numpy as np
+import random
+from diffusers import DiffusionPipeline
+import torch
+
+device = "cuda" if torch.cuda.is_available() else "cpu"
+
+if torch.cuda.is_available():
+    torch.cuda.max_memory_allocated(device=device)
+    pipe = DiffusionPipeline.from_pretrained("stabilityai/sdxl-turbo", torch_dtype=torch.float16, variant="fp16", use_safetensors=True)
+    pipe.enable_xformers_memory_efficient_attention()
+    pipe = pipe.to(device)
+else: 
+    pipe = DiffusionPipeline.from_pretrained("stabilityai/sdxl-turbo", use_safetensors=True)
+    pipe = pipe.to(device)
+
+MAX_SEED = np.iinfo(np.int32).max
+MAX_IMAGE_SIZE = 1024
+
+def infer(prompt, negative_prompt, seed, randomize_seed, width, height, guidance_scale, num_inference_steps):
+
+    if randomize_seed:
+        seed = random.randint(0, MAX_SEED)
+        
+    generator = torch.Generator().manual_seed(seed)
+    
+    image = pipe(
+        prompt = prompt, 
+        negative_prompt = negative_prompt,
+        guidance_scale = guidance_scale, 
+        num_inference_steps = num_inference_steps, 
+        width = width, 
+        height = height,
+        generator = generator
+    ).images[0] 
+    
+    return image
+
+examples = [
+    "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k",
+    "A dog named Kendrick riding a green horse",
+    "A delicious ceviche cheesecake slice",
+]
+
+css="""
+#col-container {
+    margin: 0 auto;
+    max-width: 520px;
+}
+"""
+
+if torch.cuda.is_available():
+    power_device = "GPU"
+else:
+    power_device = "CPU"
+
+with gr.Blocks(css=css) as demo:
+    
+    with gr.Column(elem_id="col-container"):
+        gr.Markdown(f"""
+        # Text-to-Image Gradio Template
+        Currently running on {power_device}.
+        """)
+        
+        with gr.Row():
+            
+            prompt = gr.Text(
+                label="Prompt",
+                show_label=False,
+                max_lines=1,
+                placeholder="Enter your prompt",
+                container=False,
+            )
+            
+            run_button = gr.Button("Run", scale=0)
+        
+        result = gr.Image(label="Result", show_label=False)
+
+        with gr.Accordion("Advanced Settings", open=False):
+            
+            negative_prompt = gr.Text(
+                label="Negative prompt",
+                max_lines=1,
+                placeholder="Enter a negative prompt",
+                visible=False,
+            )
+            
+            seed = gr.Slider(
+                label="Seed",
+                minimum=0,
+                maximum=MAX_SEED,
+                step=1,
+                value=0,
+            )
+            
+            randomize_seed = gr.Checkbox(label="Randomize seed", value=True)
+            
+            with gr.Row():
+                
+                width = gr.Slider(
+                    label="Width",
+                    minimum=256,
+                    maximum=MAX_IMAGE_SIZE,
+                    step=32,
+                    value=512,
+                )
+                
+                height = gr.Slider(
+                    label="Height",
+                    minimum=256,
+                    maximum=MAX_IMAGE_SIZE,
+                    step=32,
+                    value=512,
+                )
+            
+            with gr.Row():
+                
+                guidance_scale = gr.Slider(
+                    label="Guidance scale",
+                    minimum=0.0,
+                    maximum=10.0,
+                    step=0.1,
+                    value=0.0,
+                )
+                
+                num_inference_steps = gr.Slider(
+                    label="Number of inference steps",
+                    minimum=1,
+                    maximum=12,
+                    step=1,
+                    value=2,
+                )
+        
+        gr.Examples(
+            examples = examples,
+            inputs = [prompt]
+        )
+
+    run_button.click(
+        fn = infer,
+        inputs = [prompt, negative_prompt, seed, randomize_seed, width, height, guidance_scale, num_inference_steps],
+        outputs = [result]
+    )
+
+demo.queue().launch()

app.py

@@ -1,146 +1,5 @@
-import gradio as gr
-import numpy as np
-import random
-from diffusers import DiffusionPipeline
-import torch
+# Load model directly
+from transformers import AutoProcessor, AutoModelForCausalLM
 
-device = "cuda" if torch.cuda.is_available() else "cpu"
-
-if torch.cuda.is_available():
-    torch.cuda.max_memory_allocated(device=device)
-    pipe = DiffusionPipeline.from_pretrained("stabilityai/sdxl-turbo", torch_dtype=torch.float16, variant="fp16", use_safetensors=True)
-    pipe.enable_xformers_memory_efficient_attention()
-    pipe = pipe.to(device)
-else: 
-    pipe = DiffusionPipeline.from_pretrained("stabilityai/sdxl-turbo", use_safetensors=True)
-    pipe = pipe.to(device)
-
-MAX_SEED = np.iinfo(np.int32).max
-MAX_IMAGE_SIZE = 1024
-
-def infer(prompt, negative_prompt, seed, randomize_seed, width, height, guidance_scale, num_inference_steps):
-
-    if randomize_seed:
-        seed = random.randint(0, MAX_SEED)
-        
-    generator = torch.Generator().manual_seed(seed)
-    
-    image = pipe(
-        prompt = prompt, 
-        negative_prompt = negative_prompt,
-        guidance_scale = guidance_scale, 
-        num_inference_steps = num_inference_steps, 
-        width = width, 
-        height = height,
-        generator = generator
-    ).images[0] 
-    
-    return image
-
-examples = [
-    "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k",
-    "A dog named Kendrick riding a green horse",
-    "A delicious ceviche cheesecake slice",
-]
-
-css="""
-#col-container {
-    margin: 0 auto;
-    max-width: 520px;
-}
-"""
-
-if torch.cuda.is_available():
-    power_device = "GPU"
-else:
-    power_device = "CPU"
-
-with gr.Blocks(css=css) as demo:
-    
-    with gr.Column(elem_id="col-container"):
-        gr.Markdown(f"""
-        # Text-to-Image Gradio Template
-        Currently running on {power_device}.
-        """)
-        
-        with gr.Row():
-            
-            prompt = gr.Text(
-                label="Prompt",
-                show_label=False,
-                max_lines=1,
-                placeholder="Enter your prompt",
-                container=False,
-            )
-            
-            run_button = gr.Button("Run", scale=0)
-        
-        result = gr.Image(label="Result", show_label=False)
-
-        with gr.Accordion("Advanced Settings", open=False):
-            
-            negative_prompt = gr.Text(
-                label="Negative prompt",
-                max_lines=1,
-                placeholder="Enter a negative prompt",
-                visible=False,
-            )
-            
-            seed = gr.Slider(
-                label="Seed",
-                minimum=0,
-                maximum=MAX_SEED,
-                step=1,
-                value=0,
-            )
-            
-            randomize_seed = gr.Checkbox(label="Randomize seed", value=True)
-            
-            with gr.Row():
-                
-                width = gr.Slider(
-                    label="Width",
-                    minimum=256,
-                    maximum=MAX_IMAGE_SIZE,
-                    step=32,
-                    value=512,
-                )
-                
-                height = gr.Slider(
-                    label="Height",
-                    minimum=256,
-                    maximum=MAX_IMAGE_SIZE,
-                    step=32,
-                    value=512,
-                )
-            
-            with gr.Row():
-                
-                guidance_scale = gr.Slider(
-                    label="Guidance scale",
-                    minimum=0.0,
-                    maximum=10.0,
-                    step=0.1,
-                    value=0.0,
-                )
-                
-                num_inference_steps = gr.Slider(
-                    label="Number of inference steps",
-                    minimum=1,
-                    maximum=12,
-                    step=1,
-                    value=2,
-                )
-        
-        gr.Examples(
-            examples = examples,
-            inputs = [prompt]
-        )
-
-    run_button.click(
-        fn = infer,
-        inputs = [prompt, negative_prompt, seed, randomize_seed, width, height, guidance_scale, num_inference_steps],
-        outputs = [result]
-    )
-
-demo.queue().launch()
+processor = AutoProcessor.from_pretrained("lmms-lab/LLaVA-NeXT-Video-32B-Qwen")
+model = AutoModelForCausalLM.from_pretrained("lmms-lab/LLaVA-NeXT-Video-32B-Qwen")