🤏 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.