Z-Image
Collection
2 items • Updated
import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("Rin247/Z-Image-Turbo", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]Z-Image-Turbo
Quantised media packages of Tongyi-MAI/Z-Image-Turbo.
MECHA Forge
MECHA — Model Engineering & Contextual Hearth Assembly
These media packages have been forged and optimized in the MECHA Forge. Each one holds the Denoiser, Text Encoder, and VAE components packaged together for easier deployment.
Description
Z-Image Turbo: distilled fast variant. 8 steps, no CFG. Fast inference.
Available quantizations
| Quant | Denoiser | Text encoder | VAE |
|---|---|---|---|
| FP4 | FP4 | FP4 | FP8 |
| FP8 | FP8 | FP8 | FP8 |
| INT4 | INT4 | INT4 | INT8 |
| INT8 | INT8 | INT8 | INT8 |
The VAE is shared between formats: FP4 reuses the FP8 file, INT4 reuses the INT8 file.
Recommended settings
From the source model card (adjust to taste):
| Parameter | Value |
|---|---|
| Steps | 8 (9 DiT forwards) |
| CFG / Guidance scale | 0.0 (distilled) |
| Resolution | 512-2048 (total pixels) |
| Notes | Turbo distilled; guidance disabled |
Example prompts
Caught in the moment (candid, slice of life):
masterpiece, best quality, highres, absurdres, very aesthetic, safe, 1woman,
solo, candid moment, natural lighting. A cafe terrace in Paris, croissants on a
plate, a coffee cup, morning light. A 24-year-old woman with a round face and
dark eyes. She has a petite build and a bright smile. She wears a striped top
and beret, holding a croissant, mid-bite, candid and relaxed.
Fashion photography (magazine cover style):
Fashion photography, magazine cover style: a 24-year-old woman with round face,
dark eyes, and a small nose; wearing a denim jacket and beret, red lipstick;
Paris street, soft light, editorial, 8K, sharp focus.
Scenery:
Scenery: a Parisian cafe terrace at dusk, warm light, cobblestones, cafe chairs,
wine glasses, photorealistic, 8K.
- Downloads last month
- 180