Instructions to use sitammeur/smolified-nano-banana-pro-prompt-optimizer with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use sitammeur/smolified-nano-banana-pro-prompt-optimizer with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="sitammeur/smolified-nano-banana-pro-prompt-optimizer")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("sitammeur/smolified-nano-banana-pro-prompt-optimizer")
model = AutoModelForMultimodalLM.from_pretrained("sitammeur/smolified-nano-banana-pro-prompt-optimizer")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use sitammeur/smolified-nano-banana-pro-prompt-optimizer with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "sitammeur/smolified-nano-banana-pro-prompt-optimizer"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "sitammeur/smolified-nano-banana-pro-prompt-optimizer",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/sitammeur/smolified-nano-banana-pro-prompt-optimizer

SGLang

How to use sitammeur/smolified-nano-banana-pro-prompt-optimizer with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "sitammeur/smolified-nano-banana-pro-prompt-optimizer" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "sitammeur/smolified-nano-banana-pro-prompt-optimizer",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "sitammeur/smolified-nano-banana-pro-prompt-optimizer" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "sitammeur/smolified-nano-banana-pro-prompt-optimizer",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use sitammeur/smolified-nano-banana-pro-prompt-optimizer with Docker Model Runner:
```
docker model run hf.co/sitammeur/smolified-nano-banana-pro-prompt-optimizer
```

🤏 smolified-nano-banana-pro-prompt-optimizer

Intelligence, Distilled.

This is a Domain Specific Language Model (DSLM) generated by the Smolify Foundry.

It has been synthetically distilled from SOTA reasoning engines into a high-efficiency architecture, optimized for deployment on edge hardware (CPU/NPU) or low-VRAM environments.

📦 Asset Details

Origin: Smolify Foundry (Job ID: 05a0817e)
Architecture: DSLM-Micro (270M Parameter Class)
Training Method: Proprietary Neural Distillation
Optimization: 4-bit Quantized / FP16 Mixed
Dataset: Link to Dataset

🚀 Usage (Inference)

This model is compatible with standard inference backends like vLLM.

# Example: Running your Sovereign Model
from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "sitammeur/smolified-nano-banana-pro-prompt-optimizer"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto")

messages = [
    {'role': 'system', 'content': '''You are a professional creative director specializing in Gemini 3 Pro Image (Nano Banana Pro) prompt engineering. Your role is to: Transform casual or basic image requests into structured, reasoning-optimized prompts that leverage Nano Banana Pro's advanced capabilities Apply the 6-Factor Formula (Subject, Action, Location, Composition, Style, Editing Instructions) Preserve user intent while enhancing technical specificity Utilize natural language creative briefs rather than keyword lists STRICTLY expand only what the user provides b2 do not invent new creative directions unless ambiguity requires clarification Optimize for the model's reasoning phase, typography engine, and physics-aware synthesis'''},
    {'role': 'user', 'content': '''a bustling street market'''}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize = False,
    add_generation_prompt = True,
).removeprefix('<bos>')

from transformers import TextStreamer
_ = model.generate(
    **tokenizer(text, return_tensors = "pt").to("cuda"),
    max_new_tokens = 1000,
    temperature = 1, top_p = 0.95, top_k = 64,
    streamer = TextStreamer(tokenizer, skip_prompt = True),
)

⚖️ License & Ownership

This model weights are a sovereign asset owned by sitammeur. Generated via Smolify.ai.

Downloads last month: 20

Safetensors

Model size

0.3B params

Tensor type

BF16

sitammeur
/

smolified-nano-banana-pro-prompt-optimizer

🤏 smolified-nano-banana-pro-prompt-optimizer

📦 Asset Details

🚀 Usage (Inference)

⚖️ License & Ownership

Space using sitammeur/smolified-nano-banana-pro-prompt-optimizer 1