Instructions to use BennyDaBall/Z-Image-Engineer-V6 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use BennyDaBall/Z-Image-Engineer-V6 with Transformers:

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

pipe = pipeline("text-generation", model="BennyDaBall/Z-Image-Engineer-V6")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("BennyDaBall/Z-Image-Engineer-V6")
model = AutoModelForMultimodalLM.from_pretrained("BennyDaBall/Z-Image-Engineer-V6")
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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use BennyDaBall/Z-Image-Engineer-V6 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "BennyDaBall/Z-Image-Engineer-V6"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "BennyDaBall/Z-Image-Engineer-V6",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/BennyDaBall/Z-Image-Engineer-V6

SGLang

How to use BennyDaBall/Z-Image-Engineer-V6 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 "BennyDaBall/Z-Image-Engineer-V6" \
    --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": "BennyDaBall/Z-Image-Engineer-V6",
		"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 "BennyDaBall/Z-Image-Engineer-V6" \
        --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": "BennyDaBall/Z-Image-Engineer-V6",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use BennyDaBall/Z-Image-Engineer-V6 with Docker Model Runner:
```
docker model run hf.co/BennyDaBall/Z-Image-Engineer-V6
```

Z-Image-Engineer-V6 / README.md

BennyDaBall

Add files using upload-large-folder tool

496b168 verified 3 days ago

preview code

raw

history blame contribute delete

6.9 kB

	---
	license: apache-2.0
	language:
	- en
	base_model:
	- Tongyi-MAI/Z-Image-Turbo
	library_name: transformers
	pipeline_tag: text-generation
	tags:
	- text-generation
	- prompt-engineering
	- image-generation
	- z-image
	- z-image-turbo
	- qwen3
	- text-encoder
	- comfyui
	- lm-studio
	- conversational
	---

	# Z-Image-Engineer V6 (4B)

	## Model Metadata

	\| Key \| Value \|
	\|---\|---\|
	\| License \| Apache-2.0 \|
	\| Language \| English (`en`) \|
	\| Base Model \| `Tongyi-MAI/Z-Image-Turbo` \|
	\| Library \| `transformers` \|
	\| Pipeline Tag \| `text-generation` \|
	\| Format \| HF Safetensors \|

	---

	The Z-Engineer returns, fully rebuilt around the SMART DoRA training system for Z-Image Turbo.

	Yes, we jump from V4 to V6. Unlike the usual guy math, this one actually brought the extra two inches.

	Z-Image-Engineer V6 is a fine-tuned 4B Qwen text encoder (`Tongyi-MAI/Z-Image-Turbo`) optimized for dual-role performance: a local prompt-enhancement model for LM Studio, and a merged HF text encoder for Z-Image workflows.

	![Z-Image-Engineer V6 simple A/B with rewrites](evidence/gallery_z_image_engineer_v6_simple_ab_with_rewrites_CONTACT.png)

	---

	## What is Z-Image-Engineer V6?

	V6 transforms minimal seed prompts into rich, highly structured visual narratives. It adds explicit scene composition, lighting direction, material texture, and depth separation while stripping out empty prompt sludge like "8k, masterpiece, trending on ArtStation."

	It can also be used directly as a Z-Image text encoder. This repo contains the merged HF safetensors. The GGUF quantized release lives in the companion repo: [Z-Image-Engineer-V6-GGUF](https://huggingface.co/BennyDaBall/Z-Image-Engineer-V6-GGUF).

	### Key Use Cases

	- Prompt Enhancement: Upgrade simple concepts into descriptive, high-fidelity visual prompts locally.
	- Text Encoder Swap: Replace the stock Z-Image Qwen text encoder to generate different conditioning from the same seed.
	- Hybrid Mode: Use V6 to rewrite your prompt, then use V6 again to encode it. It writes the scene and drives the image model.
	- Private Local Workflow: Built for LM Studio, ComfyUI, and `llama.cpp`. No API logs, no external telemetry.

	---

	## Under the Hood: SMART DoRA

	V4 pioneered SMART training. V6 adapts that system into a Weight-Decomposed Low-Rank Adaptation (DoRA) framework.

	DoRA provides surgical adapter updates by decoupling directional and magnitude adjustments. SMART adds auxiliary pressure so the model does not collapse into repetitive prompt loops or superficial sentence patterns.

	\| Regularizer \| What it Does \| Why it Matters \|
	\|---\|---\|---\|
	\| Entropic \| Broadens output probability diversity. \| Reduces repetitive loops and generic vocabulary. \|
	\| Holographic \| Enforces structured, depth-wise feature logic. \| Improves foreground/background hierarchy. \|
	\| Topological \| Stabilizes coherent latent trajectories. \| Keeps prompts flowing naturally instead of stalling out. \|
	\| Manifold \| Regulates overall weight distributions. \| Keeps model behavior stable under high-pressure refinement. \|

	### The Refinement Pipeline

	V6 was not a simple one-and-done training run. The final architecture is a blended composite:

	1. Base Pass: Master-corpus SMART DoRA training on the native Z-Image Turbo text encoder.
	2. Retention Pass: Preservation pressure for numbers, color accuracy, text signage, named objects, actions, and spatial tracking.
	3. SceneClean SFT32: Supervised refinement to restore the cinematic V4/base-V6 voice.
	4. AntiRepeat Binary24: Binary anti-repeat refinement to reduce loops, abrupt fragments, and bad endings.
	5. Final Blend: A 25% style-restoration / 75% anti-repeat DoRA adapter blend, balancing vivid descriptions with tighter syntax.

	---

	## Quick Start

	### LM Studio: Prompt Enhancement

	Use this merged HF release directly where supported, or download a GGUF quant from [Z-Image-Engineer-V6-GGUF](https://huggingface.co/BennyDaBall/Z-Image-Engineer-V6-GGUF) for LM Studio. No complex system prompt is required.

	```text
	Enhance this image prompt for Z-Image Turbo: a unicorn
	```

	The comparison examples were generated from direct LM Studio user requests like this, with no separate system prompt. `V6_SYSTEM_PROMPT.md` is included only as an optional preset for people who want a stricter prompt-only chat setup.

	### ComfyUI: Direct Encoder Swap

	1. Download a GGUF quant from [Z-Image-Engineer-V6-GGUF](https://huggingface.co/BennyDaBall/Z-Image-Engineer-V6-GGUF).
	2. Place the GGUF file into `ComfyUI/models/text_encoders/`.
	3. Add a `CLIPLoaderGGUF` node.
	4. Set model type to `lumina2`.
	5. Use it where the stock Z-Image Qwen text encoder would normally go.

	Optional workflow repo:

	- [ComfyUI-Z-Engineer](https://github.com/BennyDaBall930/ComfyUI-Z-Engineer)

	The raw GGUF works without the node.

	### Verified Image Settings

	```text
	UNET: z_image_turbo_bf16.safetensors
	VAE: ae.safetensors
	Text Encoder: Z-Image-Engineer-V6-Q8_0.gguf from the GGUF repo
	Resolution: 1024x1024
	Steps: 8
	CFG: 1.0
	Sampler: res_multistep
	Scheduler: simple
	Shift: 3.0
	```

	---

	## Training Specifics

	\| Parameter \| Specification \|
	\|---\|---\|
	\| Base Text Encoder \| `Tongyi-MAI/Z-Image-Turbo/text_encoder` \|
	\| Tokenizer \| `Tongyi-MAI/Z-Image-Turbo/tokenizer` \|
	\| Method \| SMART DoRA / PEFT Adapter Training \|
	\| Rank / Alpha / Dropout \| 64 / 64 / 0.03 \|
	\| Target Modules \| `q_proj`, `k_proj`, `v_proj`, `o_proj`, `gate_proj`, `down_proj`, `up_proj` \|
	\| Refinement Stack \| Supervised Style SFT + Binary Anti-Repeat \|
	\| Final Packaging \| Merged HF safetensors \|

	---

	## GGUF Quantization Ladder

	The quantized release is separate on purpose:

	[BennyDaBall/Z-Image-Engineer-V6-GGUF](https://huggingface.co/BennyDaBall/Z-Image-Engineer-V6-GGUF)

	That repo contains the full GGUF ladder: F16, Q8_0, Q6_K, Q5_K_M, Q4_K_M, Q3_K_M, and MXFP4.

	---

	## Verification & Proof

	The bundled comparison image is:

	```text
	evidence/gallery_z_image_engineer_v6_simple_ab_with_rewrites_CONTACT.png
	```

	It compares foundational prompts across four isolated control paths:

	1. Stock Encoder + Raw Prompt
	2. V6 Encoder + Raw Prompt
	3. Stock Encoder + V6 LM Studio Rewrite
	4. V6 Encoder + V6 LM Studio Rewrite

	---

	## Disclaimer & Acknowledgements

	This model is a prompt engineer and text encoder. Diffusion is still diffusion; structural expansion improves compositional adherence, but it does not mathematically guarantee a perfect seed every single time. Use creative judgment locally.

	- Tongyi-MAI for the Z-Image Turbo ecosystem.
	- Qwen for the adaptable text encoder backbone.
	- The open-source maintainers behind LM Studio, ComfyUI, llama.cpp, PEFT, and Transformers.
	- My local power utility provider, for sustaining the research grid.

	Built & trained locally with care by BennyDaBall.