Qwen-Image
Collection
2 items • Updated
import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("Rin247/Qwen-Image-2.1-Turbo", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]Qwen-Image-2.1-Turbo
Quantised media packages of Qwen/Qwen-Image-2.1-Turbo.
MECHA Forge
MECHA — Model Engineering & Contextual Hearth Assembly
These media packages have been forged and optimized in the MECHA Forge.
Description
Qwen-Image 2.1 Turbo: distilled fast variant. 8 steps, CFG 1.0. Multi-language support.
Available quantizations
| Quant | Denoiser | Text encoder | VAE |
|---|---|---|---|
| FP8 | FP8 | FP8 | FP8 |
| INT8 | INT8 | INT8 | INT8 |
| FP4 | FP4 | FP4 | FP8 |
| INT4 | INT4 | INT4 | 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 | any aspect ratio |
| 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 sunlit kitchen in the morning, fresh
bread on the counter, a window with lace curtains, warm light. A 26-year-old
woman with freckles and auburn hair. She has a soft build and a bright smile.
She wears an apron over a casual dress, holding a mug, mid-laugh, candid and
relaxed.
Fashion photography (magazine cover style):
Fashion photography, magazine cover style: a 26-year-old woman with freckles,
auburn hair, and a soft jawline; wearing a cropped leather jacket and high-
waisted jeans, chunky boots, silver rings; neon city lights, bold headline, 8K,
sharp focus.
Scenery:
Scenery: a neon-lit Tokyo street at night, rain-slicked pavement, reflections in
puddles, umbrellas, vending machines, cinematic, 8K.
- Downloads last month
- -