For local deployment on consumer GPUs (e.g., RTX 4090 or RTX 5090), use the diffusers library. You can load a 4-bit quantized model and use a remote text-encoder to save local VRAM.
To use a remote text-encoder, you must send a POST request to the Hugging Face prediction endpoint with your prompt and authorization token, then load the resulting prompt_embeds into the Flux2Pipeline.
import torch
from diffusers import Flux2Pipeline, Flux2Transformer2DModel
from diffusers.utils import load_image
from huggingface_hub import get_token
import requests
import io
repo_id = "diffusers/FLUX.2-dev-bnb-4bit"
device = "cuda:0"
torch_dtype = torch.bfloat16
def remote_text_encoder(prompts):
response = requests.post(
"https://remote-text-encoder-flux-2.huggingface.co/predict",
json={"prompt": prompts},
headers={
"Authorization": f"Bearer {get_token()}",
"Content-Type": "application/json"
}
)
prompt_embeds = torch.load(io.BytesIO(response.content))
return prompt_embeds.to(device)
pipe = Flux2Pipeline.from_pretrained(
repo_id, transformer=transformer, text_encoder=None, torch_dtype=torch_dtype
).to(device)
prompt = "Realistic macro photograph of a hermit crab using a soda can as its shell, partially emerging from the can, captured with sharp detail and natural colors, on a sunlit beach with soft shadows and a shallow depth of field, with blurred ocean waves in the background. The can has the text `BFL Diffusers` on it and it has a color gradient that start with #FF5733 at the top and transitions to #33FF57 at the bottom."
image = pipe(
prompt_embeds=remote_text_encoder(prompt),
#image=load_image("https://huggingface.co/spaces/zerogpu-aoti/FLUX.1-Kontext-Dev-fp8-dynamic/resolve/main/cat.png") #optional image input
generator=torch.Generator(device=device).manual_seed(42),
num_inference_steps=50, #28 steps can be a good trade-off
guidance_scale=4,
).images[0]
image.save("flux2_output.png")
