Closed haile-vnu closed 8 months ago
what is your base model, prompt, neg prompt?
Neither is expected. Please share more info with us.
Hi @wangqixun , @ResearcherXman
I used the prompt = "photo of a girl, long blonde hair", and the same n_prompt in the huggginig face I used both base models
base_model_path = 'stabilityai/stable-diffusion-xl-base-1.0'
More details:
At first, I got an error TypeError: StableDiffusionXLControlNetPipeline.check_inputs() takes from 5 to 14 positional arguments but 15 were given for the file pipeline_stable_diffusion_xl_instantid.py when I called the pipe, so I commented the self.check_inputs() command in this file I also added: self.clip_skip = clip_skip self.cross_attention_kwargs = cross_attention_kwargs self.do_classifier_free_guidance = False
Thank you very much!
Can you share your full infer script?
I found the error is because my diffusers version is 0.23.0, I have upgraded the lib to 0.25.0 version. It is OK now.
Thank you very much for your wonderful work and support!
Thank you very much for your wonderful work!
I have a problem. I ran the code on my machine, I used the same image input and prompt, and the same seed, but I got a result different so much with the result on the hugging face The left image is the result using your hugging face https://huggingface.co/spaces/InstantX/InstantID The right image is the result I got on the local machine
Could you guess, where I got wrong?
Thank you very much!