Final Readme.md

README.md

@@ -1,3 +1,82 @@
----
-license: llama3
----
+---
+base_model: Casual-Autopsy/L3-Umbral-Mind-RP-v3.0-8B
+library_name: unsloth
+language: en
+tags:
+- llama-3
+- stable-diffusion
+- flux
+- z-image-turbo
+- prompt-engineering
+- uncensored
+- abliterated
+- gguf
+- android
+license: llama3
+---
+
+# ⚡ Bojro PromptMaster Abliterated 8B
+
+**Bojro PromptMaster Abliterated** is a specialized 8B parameter model designed to act as the primary "brain" for AI Image Generation workflows. It is the official companion model for the **[Bojro Resolver App](https://github.com/bojrodev/Resolver-WebUI-Forge-Client)**.
+
+Built on top of the uncensored **L3-Umbral-Mind-RP-v3.0-8B**, this model acts as a universal translator between human ideas and the specific technical requirements of modern diffusion models. It is **"Abliterated"** in function—meaning it has zero refusal mechanisms and will generate prompts for any concept, art style, or scenario you request without moralizing.
+
+## 📱 Official App
+This model was built specifically for use with:
+👉 **[Bojro Resolver (Resolver-WebUI-Forge-Client)](https://github.com/bojrodev/Resolver-WebUI-Forge-Client)**
+
+---
+
+## ⚙️ Required System Prompts
+
+To switch between the specialized engines, you **must** use the specific System Prompt corresponding to your target image generator.
+
+### 1️⃣ Target: SDXL / Pony
+*Use this for models that require structured Danbooru-style tags.*
+> **System Prompt:**
+> You are the SDXL Logic Engine. Your goal is to translate user intent into a structured, weighted tag-set. Use 'score_9, score_8_up, score_7_up' for high-quality buckets. OUTPUT ONLY THE TAGS.
+
+### 2️⃣ Target: Flux.1
+*Use this for models utilizing the T5-XXL encoder.*
+> **System Prompt:**
+> you are the Flux Photographic Director. You translate ideas into immersive, natural language prose for the T5-XXL encoder. Describe scenes with spatial awareness, camera technicals, and lighting types. OUTPUT ONLY THE PROSE.
+
+### 3️⃣ Target: Z-Image Turbo (Qwen)
+*Use this for models utilizing the Qwen text encoder.*
+> **System Prompt:**
+> You are the Z-Image Narrative Engine. You specialize in dense, material-focused storytelling prompts for the Qwen text encoder. Focus on textures, atmospheric effects, and sensory details. OUTPUT ONLY THE NARRATIVE.
+
+---
+
+## 💡 Usage Examples
+
+### **SDXL Mode**
+**Input:** `A cyberpunk cat.`
+**Output:** > score_9, score_8_up, score_7_up, 1cat, cyberpunk armor, glowing neon eyes, rain-slicked fur, futuristic city background, bokeh, 8k, unreal engine 5, chromatic aberration.
+
+### **Flux Mode**
+**Input:** `A cyberpunk cat.`
+**Output:** > A cinematic low-angle shot of a gritty cyberpunk cat prowling through a neon-lit alleyway. Rain drips from its metallic whiskers, reflecting the pink and blue holograms above. The depth of field is shallow, focusing sharply on the feline's cybernetic eye while the bustling metropolis blurs into a bokeh of electric light.
+
+### **Z-Image Turbo Mode**
+**Input:** `A cyberpunk cat.`
+**Output:** > The sensation of cold, brushed steel against wet fur. A solitary feline figure clad in scavenged cyber-armor navigates the slick pavement. The air is thick with the smell of ozone and exhaust. Textures of rusted metal contrast with the sleek, glowing blue circuitry embedded in its flank, illuminating the damp fog that clings to the ground.
+
+---
+
+## 📥 Installation
+
+This model is provided as a **GGUF** file: `BojroPromptMasterAbliterated-8B-Q4_K_M.gguf`
+
+1. **Download** the file from the Files tab.
+2. **Load** it into **LM Studio**, **KoboldCpp**, or **llama.cpp** or directly into the **Ollama**.
+3. **Set the System Prompt** based on your target engine (see above).
+4. **Set Parameters:**
+   - **Temperature:** 0.8 (Recommended for maximum creativity)
+   - **Repetition Penalty:** 1.1
+
+## 📜 License & Credits
+
+- **Base Model:** [Casual-Autopsy/L3-Umbral-Mind-RP-v3.0-8B](https://huggingface.co/Casual-Autopsy/L3-Umbral-Mind-RP-v3.0-8B)
+- **Finetuned using:** [Unsloth](https://github.com/unslothai/unsloth)
+- **License:** **Meta Llama 3 Community License**. Users must comply with the terms set forth by Meta.