Run Locally
new_mecha_zit_000002750.safetensors
162 MB · SafeTensor
Downloads are served by Civitai. Some creators ask for a Civitai login first.
About This Model
ZIMAGE · LoRAs
by n_Arno - Start your prompt with "NewMecha style illustration." followed by something (this can be altered) like "This is a highly detailed, digital illustration of a...". You can add "anime-like" if you wish for a flatter look or "CGI" if you want more 3D
Creator notes
New Mecha style for Flux.2 Klein 9B!
With the 9B version of Klein being more widely used that the 4B version, i did a quick attempt at training it. I can make it run on my poor setup using a , but boy it is slow. Anyway, here it is and the showcase pictures include some of the cursed stuff the model sometimes does for the sake of transparency regarding its capacities. Nonetheless, it works nicely for my rare needs of edit :D
(Done using ai-toolkit, i stop the training at half the total steps, reworked a bit the last saved checkpoint using a n_average merge of previous epochs and restarted it before doing a final merge of epochs to get something more smooth).
New Mecha style for Z-Image-Turbo V2!
This time, i did a training using Z-Image De-Turbo, an undistilled version of ZIT. I also raised the LR to 0.0002 and made a 64 dim LoRA before reducing the rank to 32 and carefully merge it with the previous LoRA. I also removed the trigger word, the only constant remaining is the fact that it was training on "Digital illustrations" with an "anime-like" "semi-realistic style".
This helped me achieve better results even if i raise the CFG to 1.2 (distilled models don't have a CFG and should be used with CFG = 1, aka no negative prompt).
All showcase pictures are made with 9 steps, CFG 1.2, Euler/Beta (aka Smoothstep in stable-diffusion.cpp) using the Q4_K quant, the ablitered version of Qwen3-4B for the TE and the regular VAE, plus a flow shift at 3. They got an img2img pass at 0.5 denoise with the same parameters to smooth some details.
Below a part of my ugly python wrapper script to parse multiple prompt ;-)
Enjoy! 💜
New Mecha style for Flux.2 Klein 4B!
This is a very first attempt at training a LoRA for Flux.2 Klein 4B! It was done using using the 4B-Base version, but all pictures are generated using the distilled version here.
All showcase pictures are done using the and , first by doing a txt2img and then a img2img to sharpen the result a bit.
This is a very first test and i still prefer ZIT, but the img edit capabilities are interesting and i wanted to have a version of the model that new my style (i'll probably try to train a better version later).
Here is demo of the img edit. The source image was made using ZIT and my LoRA:
And with this prompt and even a different resolution of 832x1216,
Change the girl top from red to green and her hair from blonde to orange
I got this picture 😁 (ok, it's a very basic test, but i'll try more stuff and at least, i am happy this run locally on my GTX 1060):
New Mecha style for Z-Image-Turbo!
This is a one shot test to allow me (and everyone of course) to test ZIT stuff with style. Works best with 8-10 steps.
Trigger: Start your prompt with "NewMecha style illustration." followed by something (this can be altered) like "This is a highly detailed, digital illustration of a...". You can add "anime-like" if you wish for a flatter look or "CGI" if you want more 3D.
This LoRA was trained using default config (since the on-site training is failing hard on ZIT) and a dataset of 250 pictures generated using New Mecha and captionned using .
Since this is a dataset of Illustrious pictures, the overall result is a bit under what ZIT supposedly can render, but lowering the LoRA weight and adding more stuff is the goal (that's why on-site i put 0.8 as the max weight).
The showcase was done by captionning my usual showcase pictures using JoyCaption too and the ugliest Gradio + Diffusers app ever (to avoid paying Yellow Buzz):
import gradio as gr
import torch
from diffusers import ZImagePipeline
from uuid import uuid4
from PIL.PngImagePlugin import PngInfo
from datetime import datetime, timezone
device = "cuda"
dtype = torch.bfloat16
pipe = ZImagePipeline.from_pretrained(
"Tongyi-MAI/Z-Image-Turbo",
dtype=dtype,
).to(device)
pipe.load_lora_weights(
"./output/new_mecha_zit",
weight_name="new_mecha_zit_000002750.safetensors",
adapter_name="new_mecha",
)
pipe.set_adapters(["new_mecha"], adapter_weights=[0.8])
def generate(prompt, seed, steps):
generator = torch.Generator(device).manual_seed(seed)
image = pipe(
prompt=f"NewMecha style illustration. {prompt}",
num_inference_steps=steps,
guidance_scale=1,
width=832,
height=1216,
generator=generator,
).images[0]
im_path = f"./im-outputs/{uuid4()}.png"
metadata = PngInfo()
timestamp = datetime.now(timezone.utc).strftime("%Y-%m-%dT%H:%M:%S.%fZ")
ressources = 'Civitai resources: [{"type":"checkpoint","modelVersionId":2442439,"modelName":"Z Image","modelVersionName":"Turbo"},{"type":"lora","weight":0.8,"modelVersionId":2507250,"modelName":"(ZIT) New Mecha style","modelVersionName":"v1.0"}], Civitai metadata: {}'
metadata.add_text(
"parameters",
f"NewMecha style illustration. {prompt}\nNegative prompt: \nSteps: {steps}, Sampler: Undefined, CFG scale: 1, Seed: {seed}, Size: 832x1216, Clip skip: 2, Created Date: {timestamp}, {ressources}",
)
image.save(im_path, pnginfo=metadata)
return im_path
demo = gr.Interface(
fn=generate,
inputs=[
gr.Textbox(
label="prompt",
value="This is a highly detailed, digital anime-style illustration of a young woman in a black dress.",
lines=6,
),
gr.Number(label="seed", value=42, minimum=1, precision=0),
gr.Number(label="steps", value=8, minimum=1, precision=0),
],
outputs=[gr.Image(height=608)],
flagging_mode="never",
clear_btn=None,
)
demo.launch(server_name="0.0.0.0", server_port=8000)
Enjoy and please give me any feedback you feel like regarding this LoRA (that's probably the only one i'll make for ZIT, at least until i can generate locally instead of on a costly GPU instance).
Trigger words
NewMecha style illustration. This is a highly detailed, digital illustration of a
SHA256
43EB87E7ACAD530EADDE6C3E3284CB3F5810BD39961A50D946646B6F53210047
ModelTrends.ai Model ID
#20737
Flag content
Example renders
Prompts and settings shared by the people who made these renders on Civitai. Pick a render to see how it was made.
Settings
Sampler
Undefined
Steps
9
Guidance
1
Seed
1881642502
Size
832x1216
Clip skip
2
Weight used
0.8
Prompt
NewMecha style illustration. This is a highly detailed digital artwork of a young, attractive female elf with long, silver-blonde hair in a braid. She has pointed ears and striking green eyes. She is sitting on a wooden surface table. She wears a green, sequined crop top that reveals her midriff and ripped, light-gray jeans with black combat boots. Her right arm rests on her knee, and her left hand touches the surface. The lighting highlights her slender, toned physique and pale skin. The image has a fantasy, semi-realistic style with a focus on texture and light with abstract magical symbols floating in the air.
Settings
Sampler
Undefined
Steps
9
Guidance
1
Seed
100666001
Size
896x1152
Clip skip
2
Weight used
0.8
Prompt
This image portrays an ethereal, celestial figure seated gracefully on a crescent moon amidst a starry night sky. The character exudes an otherworldly beauty, with flowing silver-white hair that cascades over her shoulders, blending into the soft glow of the moon. She wears a delicate, off-shoulder gown that billows around her in layers of ruffled fabric, reminiscent of clouds or stardust, further enhancing her ethereal nature. The gown is intricately detailed, with shimmering, lace-like embellishments and a soft ivory hue that complements the glowing moon she sits on. The crescent moon itself appears textured, with golden, vine-like details curling along its edges, giving it an ornate and almost organic quality. The moon’s soft light reflects off her skin, making her appear radiant, as if she is the embodiment of the moonlight itself. Her expression is calm and serene, with a subtle, melancholic gaze directed into the distance, adding a sense of mystery. The surrounding background features a deep, cosmic night sky filled with faint stars, creating a dreamlike, celestial atmosphere. This character might represent a moon goddess, a celestial maiden, or a mystical spirit connected to the stars and the night, evoking a sense of tranquility, beauty, and cosmic wonder
Settings
Sampler
Undefined
Steps
10
Guidance
1
Seed
8008135
Size
832x1216
Clip skip
2
Weight used
0.8
Prompt
NewMecha style illustration. This is a highly detailed digital illustration of a beautiful, blonde, blue-eyed woman with long, wavy hair. She is wearing ornate, blue and gold medieval armor over a white shirt, with intricate designs on the shoulder plates. Her expression is calm and slightly alluring as she looks over her shoulder. Pink roses with green leaves surround her, and petals float around her head, adding a magical, ethereal feel. The background is a deep black, making the colors of her hair, eyes, armor, and roses stand out vividly. The style is realistic with a slightly anime influence, emphasizing her delicate features and the glossy texture of her armor.
Settings
Sampler
Undefined
Steps
9
Guidance
1
Seed
1662554935
Size
832x1216
Clip skip
2
Weight used
0.8
Prompt
NewMecha style illustration. This is a digital anime-style illustration of a young woman with teal-blue hair that transitions to pink and yellow at the ends. She has intense orange eyes and a determined expression. She wears a shiny, pink and blue jacket with black straps over a black, high-neck, cut-out top, and a short black skirt. Her skin is fair, and she has a slender build with small breasts. The background is glowing vr room, with glowing blue line on black in a 3d patterns with a blue, brushstroke-like shadow on the ground. The image is highly detailed with vibrant colors and dynamic lighting, giving it a modern, energetic feel. The perspective is slightly angled downward, emphasizing her forward motion.
Settings
Sampler
Undefined
Steps
10
Guidance
1
Seed
8008135
Size
832x1216
Clip skip
2
Weight used
0.8
Prompt
NewMecha style illustration. This digital art illustration features a striking, young female pirate with long, wavy black hair and piercing green eyes. She wears a black tricorn hat adorned with a feather, a white ruffled blouse, and a brown leather jacket with gold buttons. Her high-waisted black leather pants are cinched with a brown belt featuring a gold buckle and a sheathed sword. The background is a stormy seascape with vivid turquoise lightning and dark, ominous clouds. Several pirate ships with tall masts are anchored in the turbulent water. The overall style is highly detailed and realistic, with a dramatic, fantasy-themed aesthetic.
Settings
Sampler
Undefined
Steps
10
Guidance
1
Seed
8008135
Size
832x1216
Clip skip
2
Weight used
0.8
Prompt
NewMecha style illustration. This is a highly detailed, digital fantasy artwork depicting a tall, blonde elf woman with long, flowing hair and pointed ears. She has striking blue eyes and a confident smile. She wears a form-fitting, black latex bodysuit with gold accents and a high collar, which highlights her large breasts and slim waist. She is posing in a fighting stance, ready to strike at the viewer, with a glowing blue sword she is holding in her right hand. The background features a nighttime medieval town square with cobblestone streets and illuminated buildings, creating a magical, urban fantasy atmosphere. The artist's style is hyper-realistic with a focus on vibrant colors and intricate details. The color theme of the background is blue and magical.
Settings
Sampler
Undefined
Steps
10
Guidance
1
Seed
8008135
Size
832x1216
Clip skip
2
Weight used
0.8
Prompt
NewMecha style illustration. This is a highly detailed, digital artwork in a steampunk style. The central figure is a young woman with fair skin and green eyes, wearing a brown leather jacket with brass buttons, a white blouse with puffed sleeves, and green high-waisted pants. She has short brown hair and wears steampunk goggles on her head. Her outfit is adorned with various gears, belts, and pocket watches. She holds a vintage-style shotgun in her right hand. The background is an intricate, golden-lit industrial setting with pipes, gears, and glowing orbs. The image has a warm, glowing ambiance, emphasizing the intricate, mechanical textures and the character's confident, adventurous pose.
Settings
Sampler
Undefined
Steps
10
Guidance
1
Seed
8008135
Size
832x1216
Clip skip
2
Weight used
0.8
Prompt
NewMecha style illustration. This digital anime-style illustration features a handsome, blonde-haired man with purple eyes, sitting in a luxurious, red-leather armchair. He is dressed in a black, tailored suit with gold accents, a teal shirt, and a black tie adorned with red diamonds. A white, fluffy fur stole drapes over his shoulders, and he wears black gloves. He holds a playing card (the Ace of Hearts) near his face with his right hand, while his left hand rests on his lap, adorned with a gold ring. The background shows an ornate, dimly-lit room with arched windows and poker tables, creating a high-stakes, casino atmosphere.
Similar Models
AI Models for Image, Video & Text Generation
new mecha style zit is a LoRA for the Zimage family listed on ModelTrends.ai, a read-only catalog of open source AI image, video and text models. Compare it with other Zimage models, check its heat score to see how it is trending, and open it on PirateDiffusion or BitVector to try it.
Browse by Model Family
Text / LLM Models
411
Anima Models
509
Chroma Models
14
Flux Models
1,071
Flux 2 / Klein Models
1,237
MiniMax H3 Models
331
Hunyuan Models
197
Ideogram Models
20
Krea2 Models
674
Qwen Models
17
Qwen2 Models
36
Ltx2 Models
150
Stable Diffusion 1.5 Models
6,465
Stable Diffusion XL 1.0 Models
15,432
Zimage Models
804
Wan Models
919
Model
Trends
.ai
© ModelTrends.ai
|
Made in Japan
|
© 2026