tsqn/Z-Image-Turbo_fp32-fp16-bf16_full_and_ema-only

Instalación y uso básico con Diffusers:

pip install -U diffusers transformers accelerate

import torch
from diffusers import DiffusionPipeline

# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained(
    "tsqn/Z-Image-Turbo_fp32-fp16-bf16_full_and_ema-only",
    dtype=torch.bfloat16,
    device_map="cuda"
)

prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]

Ejemplo con ZImagePipeline y parámetros recomendados para Turbo:

import torch
from diffusers import ZImagePipeline

pipe = ZImagePipeline.from_pretrained(
    "path/to/model_files_main_dir",
    torch_dtype=torch.float32,
    low_cpu_mem_usage=False,
)
pipe.to("cuda")

prompt = "Young Chinese woman in red Hanfu, intricate embroidery. Impeccable makeup, red floral forehead pattern. Elaborate high bun, golden phoenix headdress, red flowers, beads. Holds round folding fan with lady, trees, bird. Neon lightning-bolt lamp (⚡️), bright yellow glow, above extended left palm. Soft-lit outdoor night background, silhouetted tiered pagoda (西安大雁塔), blurred colorful distant lights."

image = pipe(
    prompt=prompt,
    height=1024,
    width=1024,
    num_inference_steps=9,
    guidance_scale=0.0,
    generator=torch.Generator("cuda").manual_seed(42),
).images[0]

image.save("example.png")

Para usar los archivos sin rutas explícitas con ZImagePipeline, el README indica renombrarlos así:

text_encoder/
└── model.safetensors
transformer/
└── diffusion_pytorch_model.safetensors
vae/
└── diffusion_pytorch_model.safetensors