Spaces:
Paused
Paused
File size: 2,104 Bytes
216b96d aa97fb8 216b96d |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 |
from vllm import LLM, SamplingParams
import gradio as gr
repo_id = "mistral-community/pixtral-12b-240910" #Replace to the model you would like to use
sampling_params = SamplingParams(temperature=0.8, top_p=0.95)
# @spaces.GPU #[uncomment to use ZeroGPU]
def infer(image_url, prompt, progress=gr.Progress(track_tqdm=True)):
# tokenize image urls and text
llm = LLM(model="mistralai/Pixtral-12B-2409", load_params_config=True) # Name or path of your model
messages = [
{
"role": "user",
"content": [{"type": "text", "text": prompt}, {"type": "image_url", "image_url": {"url": image_url}}]
},
]
outputs = llm.chat(messages, sampling_params=sampling_params)
print(outputs[0].outputs[0].text)
return outputs
example_images = ["https://picsum.photos/id/237/200/300"]
example_prompts = ["What do you see in this image?"]
css = """
#col-container {
margin: 0 auto;
max-width: 640px;
}
"""
with gr.Blocks(css=css) as demo:
with gr.Column(elem_id="col-container"):
gr.Markdown(f"""
# Text-to-Image Gradio Template
""")
with gr.Row():
prompt = gr.Text(
label="Prompt",
show_label=False,
max_lines=2,
placeholder="Enter your prompt",
container=False,
)
image_url = gr.Text(
label="Image URL",
show_label=False,
max_lines=1,
placeholder="Enter your image URL",
container=False,
)
run_button = gr.Button("Run", scale=0)
result = gr.Textbox(
show_label=False
)
gr.Examples(
examples=example_images,
inputs=[image_url]
)
gr.Examples(
examples=example_prompts,
inputs=[prompt]
)
gr.on(
triggers=[run_button.click, image_url.submit, prompt.submit],
fn=infer,
inputs=[image_url, prompt],
outputs=[result]
)
demo.queue().launch() |