We have completed the training of the first version.
The training was conducted with a total pixel count of
1024*1024
at multi-scale.
We trained for 30k steps using a batch size of 8*8.
Diffusers version:
pip install -U diffusers
Demo
import torch
from diffusers.utils import load_image
from diffusers.pipelines.flux.pipeline_flux_controlnet import FluxControlNetPipeline
from diffusers.models.controlnet_flux import FluxControlNetModel
base_model = 'black-forest-labs/FLUX.1-dev'
controlnet_model = 'InstantX/FLUX.1-dev-Controlnet-Canny'
controlnet = FluxControlNetModel.from_pretrained(controlnet_model, torch_dtype=torch.bfloat16)
pipe = FluxControlNetPipeline.from_pretrained(base_model, controlnet=controlnet, torch_dtype=torch.bfloat16)
pipe.to("cuda")
control_image = load_image("https://huggingface.co/InstantX/FLUX.1-dev-Controlnet-Canny/resolve/main/canny.jpg")
prompt = "A girl in city, 25 years old, cool, futuristic"
image = pipe(
prompt,
control_image=control_image,
controlnet_conditioning_scale=0.6,
num_inference_steps=28,
guidance_scale=3.5,
).images[0]
image.save("image.jpg")
Runs of InstantX FLUX.1-dev-Controlnet-Canny on huggingface.co
2.5K
Total runs
0
24-hour runs
-64
3-day runs
-24
7-day runs
49
30-day runs
More Information About FLUX.1-dev-Controlnet-Canny huggingface.co Model
More FLUX.1-dev-Controlnet-Canny license Visit here:
FLUX.1-dev-Controlnet-Canny huggingface.co is an AI model on huggingface.co that provides FLUX.1-dev-Controlnet-Canny's model effect (), which can be used instantly with this InstantX FLUX.1-dev-Controlnet-Canny model. huggingface.co supports a free trial of the FLUX.1-dev-Controlnet-Canny model, and also provides paid use of the FLUX.1-dev-Controlnet-Canny. Support call FLUX.1-dev-Controlnet-Canny model through api, including Node.js, Python, http.
FLUX.1-dev-Controlnet-Canny huggingface.co is an online trial and call api platform, which integrates FLUX.1-dev-Controlnet-Canny's modeling effects, including api services, and provides a free online trial of FLUX.1-dev-Controlnet-Canny, you can try FLUX.1-dev-Controlnet-Canny online for free by clicking the link below.
InstantX FLUX.1-dev-Controlnet-Canny online free url in huggingface.co:
FLUX.1-dev-Controlnet-Canny is an open source model from GitHub that offers a free installation service, and any user can find FLUX.1-dev-Controlnet-Canny on GitHub to install. At the same time, huggingface.co provides the effect of FLUX.1-dev-Controlnet-Canny install, users can directly use FLUX.1-dev-Controlnet-Canny installed effect in huggingface.co for debugging and trial. It also supports api for free installation.
FLUX.1-dev-Controlnet-Canny install url in huggingface.co: