I have this hardware 11th Gen intel i5 2.40Ghz, 32 GB RAM, Disk ssd nvme and GeForce rtx 4090, and libraries Pytorch, difussers, accelerate and python 3.10, I have already made images with SDXL and now I’m trying load FLUX either Dev or Schnell the issue is that it takes a long time to load the steps for image generation, the pipeline loads very fast but it takes a long time even though I only add 5 steps. I have tested this configuration on a 4070 Ti and it also takes time but the average is between 7 to 9 minutes for three images, but in the case of the 4090, it takes up to 20 or 30 minutes. this is a very basic code but maybe you can get an idea of what to change.
print(torch.__version__) # Torch version: 2.6.0+cu118
print(torch.cuda.is_available()) # True
global pipe_flux
torch.cuda.empty_cache()
model_id_flux = "C:/Users/GFAdmin/Documents/model/flux.1-dev/"
torch.set_default_tensor_type(torch.cuda.FloatTensor)
torch.cuda.set_device(0)
#
pipe_flux = FluxPipeline.from_pretrained(
model_id_flux,
torch_dtype=torch.bfloat16
)
pipe_flux.to("cuda")
pipe_flux.reset_device_map()
pipe_flux.enable_model_cpu_offload()
print("Pipeline FLUX por defecto cargado.")
torch.cuda.empty_cache()
torch.cuda.reset_peak_memory_stats()
with autocast("cuda"), torch.inference_mode():
image = pipe_flux(
"A capybara holding a sign that reads Hello World",
num_inference_steps=5,
guidance_scale=3.5,
).images[0]
image.save("./pruebas/capybara.png")
and another case I have other code used checkpoint file but not working too
import torch
from diffusers import FluxPipeline, AutoencoderKL
from transformers import T5EncoderModel
torch.cuda.set_device(0)
model_file = "C:/Users/GFAdmin/Documents/model/flux_checkpoint/flux_dev.safetensors"
text_encoder = CLIPTextModel.from_pretrained("C:/Users/GFAdmin/Documents/model/clip-vit-base-patch32")
text_encoder_2 = T5EncoderModel.from_pretrained("t5-base")
vae = AutoencoderKL.from_pretrained("stabilityai/sd-vae-ft-ema")
pipe_flux = FluxPipeline.from_single_file(
model_file,
torch_dtype=torch.float16,
use_safetensors=True,
text_encoder=text_encoder,
text_encoder_2=text_encoder_2,
vae=vae
)
pipe_flux.to("cuda")
pipe_flux.reset_device_map()
pipe_flux.to(torch.float16)
prompt = "A capybara holding a sign that reads Hello World"
result = pipe_flux(prompt, num_inference_steps=5, guidance_scale=3.5)
result.images[0].save("./pruebas/capybara.png")
print("Imagen guardada en './pruebas/capybara.png'")
I will be grateful for any help