ThirdMiddle/Qwen-Image-1.9

Instalación y uso con Diffusers:

pip install -U diffusers transformers accelerate

import torch
from diffusers import DiffusionPipeline

# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained(
    "ThirdMiddle/Qwen-Image-1.9",
    dtype=torch.bfloat16,
    device_map="cuda"
)

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

Ejemplo principal de la ficha del modelo:

from diffusers import DiffusionPipeline
import torch

pipe = DiffusionPipeline.from_pretrained(
    "ThirdMiddle/Qwen-Image-1.9",
    torch_dtype=torch.bfloat16,
    trust_remote_code=True,
)
pipe = pipe.to("cuda")

image = pipe(
    "a photorealistic portrait of an astronaut on Mars at sunrise",
    num_inference_steps=30,
    guidance_scale=4.0,
).images[0]
image.save("output.png")

Uso local con llama.cpp/Ollama en versión GGUF:

llama-server -hf ThirdMiddle/Qwen-Image-1.9:Q4_K_M
llama-cli -hf ThirdMiddle/Qwen-Image-1.9:Q4_K_M
ollama run hf.co/ThirdMiddle/Qwen-Image-1.9:Q4_K_M

Uso con Docker Model Runner:

docker model run hf.co/ThirdMiddle/Qwen-Image-1.9:Q4_K_M