File size: 3,424 Bytes
2a7e546 88deab4 2a7e546 d751051 88deab4 d751051 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 |
from rct_diffusion_pipeline import RCTDiffusionPipeline
from diffusers import UNet2DConditionModel
torch_device = "cuda"
pipeline = RCTDiffusionPipeline()
pipeline.print_class_tokens_to_csv()
output = pipeline([[('aleppo pine tree', 1.0)]], [[('dark green', 1.0)]])
# from PIL import Image
# import torch
# from transformers import CLIPTextModel, CLIPTokenizer
# from diffusers import AutoencoderKL, UNet2DConditionModel, PNDMScheduler
# vae = AutoencoderKL.from_pretrained("CompVis/stable-diffusion-v1-4", subfolder="vae", use_safetensors=True)
# tokenizer = CLIPTokenizer.from_pretrained("CompVis/stable-diffusion-v1-4", subfolder="tokenizer")
# text_encoder = CLIPTextModel.from_pretrained(
# "CompVis/stable-diffusion-v1-4", subfolder="text_encoder", use_safetensors=True
# )
# unet = UNet2DConditionModel.from_pretrained(
# "CompVis/stable-diffusion-v1-4", subfolder="unet", use_safetensors=True
# )
# from diffusers import UniPCMultistepScheduler
# scheduler = UniPCMultistepScheduler.from_pretrained("CompVis/stable-diffusion-v1-4", subfolder="scheduler")
# torch_device = "cuda"
# vae.to(torch_device)
# text_encoder.to(torch_device)
# unet.to(torch_device)
# prompt = ["a photograph of an astronaut riding a horse"]
# height = 512 # default height of Stable Diffusion
# width = 512 # default width of Stable Diffusion
# num_inference_steps = 25 # Number of denoising steps
# guidance_scale = 7.5 # Scale for classifier-free guidance
# generator = torch.manual_seed(0) # Seed generator to create the inital latent noise
# batch_size = len(prompt)
# text_input = tokenizer(
# prompt, padding="max_length", max_length=tokenizer.model_max_length, truncation=True, return_tensors="pt"
# )
# with torch.no_grad():
# text_embeddings = text_encoder(text_input.input_ids.to(torch_device))[0]
# text_input = tokenizer(
# prompt, padding="max_length", max_length=tokenizer.model_max_length, truncation=True, return_tensors="pt"
# )
# with torch.no_grad():
# text_embeddings = text_encoder(text_input.input_ids.to(torch_device))[0]
# max_length = text_input.input_ids.shape[-1]
# uncond_input = tokenizer([""] * batch_size, padding="max_length", max_length=max_length, return_tensors="pt")
# uncond_embeddings = text_encoder(uncond_input.input_ids.to(torch_device))[0]
# text_embeddings = torch.cat([uncond_embeddings, text_embeddings])
# latents = torch.randn(
# (batch_size, unet.in_channels, height // 8, width // 8),
# generator=generator,
# )
# latents = latents.to(torch_device)
# latents = latents * scheduler.init_noise_sigma
# from tqdm.auto import tqdm
# scheduler.set_timesteps(num_inference_steps)
# for t in tqdm(scheduler.timesteps):
# # expand the latents if we are doing classifier-free guidance to avoid doing two forward passes.
# latent_model_input = torch.cat([latents] * 2)
# latent_model_input = scheduler.scale_model_input(latent_model_input, timestep=t)
# # predict the noise residual
# with torch.no_grad():
# noise_pred = unet(latent_model_input, t, encoder_hidden_states=text_embeddings).sample
# # perform guidance
# noise_pred_uncond, noise_pred_text = noise_pred.chunk(2)
# noise_pred = noise_pred_uncond + guidance_scale * (noise_pred_text - noise_pred_uncond)
# # compute the previous noisy sample x_t -> x_t-1
# latents = scheduler.step(noise_pred, t, latents).prev_sample
print('test') |