instruct-pix2pix
instruct-pix2pix copied to clipboard
timothybrooks
Hi, thanks for the excellent work. I have configured the repository according to the instructions provided in the README document. The edit_cli runs well and produces the edited image as...
Hi . i want to know did you plan to update this model ? also i want to know if it is usable with any other model and checkpoints ?
my code: image = Image.fromarray(image) pipe = StableDiffusionInstructPix2PixPipeline.from_pretrained("timbrooks/instruct-pix2pix", torch_dtype=torch.float16, safety_checker=None) pipe.to("cuda") pipe.scheduler = DDIMScheduler.from_pretrained("CompVis/stable-diffusion-v1-4", subfolder="scheduler") num_inference_steps = 200 image_guidance_scale = 2.1 guidance_scale = 8.35 images = pipe(text_prompt, image=image, num_inference_steps=num_inference_steps, image_guidance_scale=image_guidance_scale,guidance_scale=guidance_scale).images[0]...
Thank you for your excellent work. I'm curious to know how much time you spent constructing the dataset containing 451,990 samples (including text generation, image generation, and data filtering), and...
Hi, thanks for sharing your research and this code! I read your paper and tried to find out the specific values in Figure 8. and Figure 10, but could not...
If i want to add myself to usual SD, i just do dreambooth training with prompt "photo of sks person" and several images with my face. But what i can...
Hi!. I made a script to generate images starting from a list of PIL images, following the edit_cli.py file. However, after a few generated images I get the "cuda out...
I can produce synthesized data for solving my problem but I don't know "In which format do I need to synthesize the data which is acceptable by the model?" What...
Hi, I wonder what dataset is used in the paper for validation/test, or can we download them somewhere? Thanks!
