limuloo / migc Goto Github PK

I tried to generate a single image on my PC, it takes about 7 min on the single RTX 2060, is this normal？

I'm here to ask for an update, when will the training code be released? May is almost over

hello,thanks for your excellent work, will you release the pretrained weights of sdxl in the future?

Hello, thanks for the excellent work, may I ask when the training code will be released, if it will be released soon, thank you!

Thanks for the great work! However, the pipeline does not seem to support the latest diffusers. When I use diffusers v0.25.0, I got:

  File "/home_dir/miniconda3/envs/env_name/lib/python3.10/concurrent/futures/_base.py", line 403, in __get_result
    raise self._exception
  File "/home_dir/miniconda3/envs/env_name/lib/python3.10/concurrent/futures/thread.py", line 58, in run
    result = self.fn(*self.args, **self.kwargs)
  File "/home_dir/MIGC/migc_gui/app.py", line 82, in process_request
    pipe = offlinePipelineSetupWithSafeTensor(sd_safetensors_path=sd_safetensors_path)
  File "/home_dir/MIGC/migc/migc_utils.py", line 174, in offlinePipelineSetupWithSafeTensor
    pipe = StableDiffusionMIGCPipeline.from_single_file(sd_safetensors_path,
  File "/home_dir/miniconda3/envs/env_name/lib/python3.10/site-packages/huggingface_hub/utils/_validators.py", line 118, in _inner_fn
    return fn(*args, **kwargs)
  File "/home_dir/miniconda3/envs/env_name/lib/python3.10/site-packages/diffusers/loaders/single_file.py", line 263, in from_single_file
    pipe = download_from_original_stable_diffusion_ckpt(
  File "/home_dir/miniconda3/envs/env_name/lib/python3.10/site-packages/diffusers/pipelines/stable_diffusion/convert_from_ckpt.py", line 1687, in download_from_original_stable_diffusion_ckpt
    pipe = pipeline_class(
  File "/home_dir/MIGC/migc/migc_pipeline.py", line 241, in __init__
    super().__init__(
  File "/home_dir/miniconda3/envs/env_name/lib/python3.10/site-packages/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion.py", line 237, in __init__
    self.register_modules(
  File "/home_dir/miniconda3/envs/env_name/lib/python3.10/site-packages/diffusers/pipelines/pipeline_utils.py", line 571, in register_modules
    library = not_compiled_module.__module__.split(".")[0]
AttributeError: 'bool' object has no attribute '__module__'

This is similar to the following error:
huggingface/diffusers#6094

The solution is discussed here:
huggingface/diffusers#5993 (comment)

Are you interested in solving this and making MIGC compatible with the updated diffusers?

When I used MIGC to generate "2 cats and 3 dogs", I found that the first dog below would still look like a "cat". Is there any way to improve this result?

I am using realisticVisionV51_v51VAE.safetensors, here are my parameters:

rompt_final = [['4k, best quality, masterpiece, ultra high res, ultra detailed,a cat,a cat,a dog,a dog,a dog,grass',
'a cat', 'a cat', 'a dog', 'a dog', 'a dog', 'grass']]
bboxes = [[[0.078125, 0.09375, 0.390625, 0.359375], [0.515625, 0.09375, 0.859375, 0.359375], [0.078125, 0.515625, 0.34375, 0.90625],
[0.421875, 0.515625, 0.671875, 0.921875], [0.71875, 0.484375, 0.953125, 0.921875], [0.015625, 0.015625, 0.984375, 0.96875]]]
negative_prompt = 'worst quality, low quality, watermark, text, blurry'
seed = 12573842233801288171
seed_everything(seed)
image = pipe(prompt_final, bboxes, num_inference_steps=50, guidance_scale=8,
MIGCsteps=25, NaiveFuserSteps=25, aug_phase_with_and=False, negative_prompt=negative_prompt).images[0]

And here are the images generated by MIGC:

A great job, are there any tips on setting up bounding boxes to perform batch inferencing?