RunDiffusion/Juggernaut-Z-Image

Juggernaut Z by RunDiffusion

A cinematic fine-tune of Z-Image Base — tuned for presentation-ready output.

   

Juggernaut Z is a fine-tune of Z-Image Base by Team Juggernaut, trained by KandooAI, and released through RunDiffusion. It is tuned for stronger lighting, sharper focus, more refined skin texture, and more cinematic atmosphere — out of the box.

This repository hosts the official RunDiffusion release artifacts: full-precision weights, FP16 and FP8 variants, and a full set of GGUF quantizations.

---

Highlights

• More dramatic, cinematic lighting out of the box
• Sharper focus and a more deliberate camera feel
• Cleaner portraits with more natural skin texture
• Improved anatomy and structural integrity
• Better representation across ethnicities by default
• Tuned for editorial, concept, and cinematic work

Comparisons

All sets below show Juggernaut Z (left) vs Z-Image Base (right). Source: the RunDiffusion Juggernaut Z announcement.

Lighting

More dramatic, cinematic lighting out of the box.

Skin & Texture

Cleaner, more natural-looking skin — especially in close-up portraits.

Anatomy

Cleaner anatomy and more consistent structural detail across a wide range of subjects.

Composition

Improved subject and object placement within scenes, with further work planned for v2.

Diversity

More balanced results across ethnic backgrounds, with better representation by default.

Architecture

Cleaner structural lines and more coherent material rendering.

Recommended Settings

Parameter	Default	Range
CFG	6	6 – 9
Steps	35	25 – 45

Good Fit For

• Portraits with cleaner facial detail and stronger focus
• Cinematic scenes with strong lighting and atmosphere
• Concept development and visual exploration
• Editorial and fashion work that benefits from a polished finish

Files In This Repo

File	Format	Notes
Juggernaut_Z_V1_by_RunDiffusion.safetensors	safetensors (bf16)	Original release weights
Juggernaut_Z_V1_by_RunDiffusion_fp16.safetensors	safetensors (fp16)	Half-precision
Juggernaut_Z_V1_FP8_e4m3fn.safetensors	safetensors (fp8 e4m3fn)	Lower VRAM footprint
Juggernaut_Z_V1_by_RunDiffusion_q8_0.gguf	GGUF · q8_0	Highest-quality quant
Juggernaut_Z_V1_by_RunDiffusion_q6_k-004.gguf	GGUF · q6_k
Juggernaut_Z_V1_by_RunDiffusion_q5_k_m-003.gguf	GGUF · q5_k_m
Juggernaut_Z_V1_by_RunDiffusion_q5_k_s-005.gguf	GGUF · q5_k_s
Juggernaut_Z_V1_by_RunDiffusion_q4_k_m-002.gguf	GGUF · q4_k_m
Juggernaut_Z_V1_by_RunDiffusion_q4_k_s-001.gguf	GGUF · q4_k_s	Smallest footprint
diffusers/ (subfolder)	🤗 Diffusers format	Load with DiffusionPipeline.from_pretrained(..., subfolder="diffusers")

Use the .safetensors variants with the workflow that matches your local inference stack. Use the .gguf variants with a GGUF-compatible runtime. Use the diffusers/ subfolder with the 🤗 Diffusers library — see below.

Use with 🤗 Diffusers

The diffusers/ subfolder contains the model in standard 🤗 Diffusers format (ZImagePipeline) and can be loaded directly:

from diffusers import DiffusionPipeline
import torch

pipe = DiffusionPipeline.from_pretrained(
    "RunDiffusion/Juggernaut-Z-Image",
    subfolder="diffusers",
    torch_dtype=torch.bfloat16,
).to("cuda")

image = pipe(
    "a cinematic portrait, dramatic lighting",
    guidance_scale=6.0,
    num_inference_steps=35,
).images[0]
image.save("output.png")

Requires a version of diffusers that includes ZImagePipeline support (the format was exported against diffusers 0.37.1). Commercial use of the model and its outputs is restricted under CC BY-NC 4.0 — see License & Commercial Use below.

Links

• Run Juggernaut Z on RunDiffusion → rundiffusion.com/juggernaut-z
• Prompt guide → Juggernaut Z Prompt Guide
• Base model → Tongyi-MAI/Z-Image

Attribution

Juggernaut Z is built on Z-Image Base — credit for the upstream base model belongs to the Z-Image team. This fine-tuned release is by Team Juggernaut, with training by KandooAI, published by RunDiffusion.

License & Commercial Use

Juggernaut Z is released under CC BY-NC 4.0:

• BY — attribute RunDiffusion / Team Juggernaut / KandooAI when sharing output.
• NC — non-commercial use only. You may not use the model — or its outputs in a workflow — for commercial purposes without a license.

You are free to fine-tune, merge, build LoRAs, and otherwise modify the model for non-commercial purposes.

For commercial licensing, custom models, business inquiries, or consultation, contact juggernaut@rundiffusion.com.