03-VQGAN+CLIP (z+quantize method con augmentations, interfaz amigable).ipynb

{"nbformat":4,"nbformat_minor":0,"metadata":{"colab":{"name":"03-VQGAN+CLIP (z+quantize method con augmentations, interfaz amigable).ipynb","private_outputs":true,"provenance":[{"file_id":"1go6YwMFe5MX6XM9tv-cnQiSTU50N9EeT","timestamp":1628143410339},{"file_id":"1L8oL-vLJXVcRzCFbPwOoMkPKJ8-aYdPN","timestamp":1621115030940},{"file_id":"15UwYDsnNeldJFHJ9NdgYBYeo6xPmSelP","timestamp":1618333741979}],"collapsed_sections":["Yp8ULTkU_PXa"],"machine_shape":"hm"},"kernelspec":{"name":"python3","display_name":"Python 3"},"language_info":{"name":"python"},"accelerator":"GPU"},"cells":[{"cell_type":"markdown","metadata":{"id":"MlvyvGSJ8ay7"},"source":["# VQGAN & CLIP\n","\n","Presenting piece with title :\n","_\"Power of AI,  DNA of the new digital creatures, new art\"_ "]},{"cell_type":"markdown","metadata":{"id":"6wtnF3dD9DK1"},"source":["### Notebook generates images from text phrases with VQGAN and CLIP (Z + Quantize method with augmentations).\n","you dont need to give pictures to transfer styles from one to the other\n","\n","---\n","\n","\n","\n","Notebook initially was made by Katherine Crowson (https://github.com/crowsonkb, https://twitter.com/rivershavewings). The Biggan + CLIP method was made by https://twitter.com/Advadnoun. Aggregated explanations, and modifications by Eleiber # 8347, and the friendly interface was made thanks to Abulafia # 3734.\n","\n","All tributes are to above authors,\n","I just went through to see how quickly new GAN CLIP etc models are taking over sphere of art.\n","Similarly like creating videos was previously reserved for big studios nowaday everybody with access to internet and handy could do it easily.\n"]},{"cell_type":"markdown","metadata":{"id":"mLQv-lEvGAO_"},"source":["###  Mounting google drive"]},{"cell_type":"code","metadata":{"id":"ybMmQNlYF_hY"},"source":["#Mount Google Drive as folder\n","from google.colab import drive\n","drive.mount('/content/drive', force_remount=True)"],"execution_count":null,"outputs":[]},{"cell_type":"code","metadata":{"id":"TkUfzT60ZZ9q"},"source":["!nvidia-smi"],"execution_count":null,"outputs":[]},{"cell_type":"markdown","metadata":{"id":"Yp8ULTkU_PXa"},"source":["##  Instalation of libraries"]},{"cell_type":"code","metadata":{"id":"wSfISAhyPmyp"},"source":["# @title Instalation of libraries\n","\n"," \n","print(\"downloading CLIP...\")\n","!git clone https://github.com/openai/CLIP                 &> /dev/null\n"," \n","print(\"installing libraries Python for AI...\")\n","!git clone https://github.com/CompVis/taming-transformers &> /dev/null\n","!pip install ftfy regex tqdm omegaconf pytorch-lightning  &> /dev/null\n","!pip install kornia                                       &> /dev/null\n","!pip install einops                                       &> /dev/null\n","!pip install wget                                         &> /dev/null\n"," \n","print(\"libraries for managing  metadata...\")\n","!pip install stegano                                      &> /dev/null\n","!apt install exempi                                       &> /dev/null\n","!pip install python-xmp-toolkit                           &> /dev/null\n","!pip install imgtag                                       &> /dev/null\n","!pip install pillow==7.1.2                                &> /dev/null\n"," \n","print(\"ffmpg libraries to generate video...\")\n","!pip install imageio-ffmpeg                               &> /dev/null\n","!mkdir steps\n","print(\"Done.\")"],"execution_count":null,"outputs":[]},{"cell_type":"code","metadata":{"cellView":"form","id":"W8264FRyD4M5"},"source":["#@title Model selections to download\n","\n","\n","imagenet_1024 = False #@param {type:\"boolean\"}\n","imagenet_16384 = True #@param {type:\"boolean\"}\n","gumbel_8192 = False #@param {type:\"boolean\"}\n","coco = False #@param {type:\"boolean\"}\n","faceshq = False #@param {type:\"boolean\"}\n","wikiart_1024 = False #@param {type:\"boolean\"}\n","wikiart_16384 = False #@param {type:\"boolean\"}\n","sflckr = False #@param {type:\"boolean\"}\n","ade20k = False #@param {type:\"boolean\"}\n","ffhq = False #@param {type:\"boolean\"}\n","celebahq = False #@param {type:\"boolean\"}\n","\n","if imagenet_1024:\n","  !curl -L -o vqgan_imagenet_f16_1024.yaml -C - 'http://mirror.io.community/blob/vqgan/vqgan_imagenet_f16_1024.yaml' #ImageNet 1024\n","  !curl -L -o vqgan_imagenet_f16_1024.ckpt -C - 'http://mirror.io.community/blob/vqgan/vqgan_imagenet_f16_1024.ckpt'  #ImageNet 1024\n","if imagenet_16384:\n","  !curl -L -o vqgan_imagenet_f16_16384.yaml -C - 'http://mirror.io.community/blob/vqgan/vqgan_imagenet_f16_16384.yaml' #ImageNet 16384\n","  !curl -L -o vqgan_imagenet_f16_16384.ckpt -C - 'http://mirror.io.community/blob/vqgan/vqgan_imagenet_f16_16384.ckpt' #ImageNet 16384\n","if gumbel_8192:\n","  !curl -L -o gumbel_8192.yaml -C - 'https://heibox.uni-heidelberg.de/d/2e5662443a6b4307b470/files/?p=%2Fconfigs%2Fmodel.yaml&dl=1' #Gumbel 8192\n","  !curl -L -o gumbel_8192.ckpt -C - 'https://heibox.uni-heidelberg.de/d/2e5662443a6b4307b470/files/?p=%2Fckpts%2Flast.ckpt&dl=1' #Gumbel 8192\n","if coco:\n","  !curl -L -o coco.yaml -C - 'https://dl.nmkd.de/ai/clip/coco/coco.yaml' #COCO\n","  !curl -L -o coco.ckpt -C - 'https://dl.nmkd.de/ai/clip/coco/coco.ckpt' #COCO\n","if faceshq:\n","  !curl -L -o faceshq.yaml -C - 'https://drive.google.com/uc?export=download&id=1fHwGx_hnBtC8nsq7hesJvs-Klv-P0gzT' #FacesHQ\n","  !curl -L -o faceshq.ckpt -C - 'https://app.koofr.net/content/links/a04deec9-0c59-4673-8b37-3d696fe63a5d/files/get/last.ckpt?path=%2F2020-11-13T21-41-45_faceshq_transformer%2Fcheckpoints%2Flast.ckpt' #FacesHQ\n","if wikiart_1024: \n","  !curl -L -o wikiart_1024.yaml -C - 'http://mirror.io.community/blob/vqgan/wikiart.yaml' #WikiArt 1024\n","  !curl -L -o wikiart_1024.ckpt -C - 'http://mirror.io.community/blob/vqgan/wikiart.ckpt' #WikiArt 1024\n","if wikiart_16384: \n","  !curl -L -o wikiart_16384.yaml -C - 'http://mirror.io.community/blob/vqgan/wikiart_16384.yaml' #WikiArt 16384\n","  !curl -L -o wikiart_16384.ckpt -C - 'http://mirror.io.community/blob/vqgan/wikiart_16384.ckpt' #WikiArt 16384\n","if sflckr:\n","  !curl -L -o sflckr.yaml -C - 'https://heibox.uni-heidelberg.de/d/73487ab6e5314cb5adba/files/?p=%2Fconfigs%2F2020-11-09T13-31-51-project.yaml&dl=1' #S-FLCKR\n","  !curl -L -o sflckr.ckpt -C - 'https://heibox.uni-heidelberg.de/d/73487ab6e5314cb5adba/files/?p=%2Fcheckpoints%2Flast.ckpt&dl=1' #S-FLCKR\n","if ade20k:\n","  !curl -L -o ade20k.yaml -C - 'https://static.miraheze.org/intercriaturaswiki/b/bf/Ade20k.txt' #ADE20K\n","  !curl -L -o ade20k.ckpt -C - 'https://app.koofr.net/content/links/0f65c2cd-7102-4550-a2bd-07fd383aac9e/files/get/last.ckpt?path=%2F2020-11-20T21-45-44_ade20k_transformer%2Fcheckpoints%2Flast.ckpt' #ADE20K\n","if ffhq:\n","  !curl -L -o ffhq.yaml -C - 'https://app.koofr.net/content/links/0fc005bf-3dca-4079-9d40-cdf38d42cd7a/files/get/2021-04-23T18-19-01-project.yaml?path=%2F2021-04-23T18-19-01_ffhq_transformer%2Fconfigs%2F2021-04-23T18-19-01-project.yaml&force' #FFHQ\n","  !curl -L -o ffhq.ckpt -C - 'https://app.koofr.net/content/links/0fc005bf-3dca-4079-9d40-cdf38d42cd7a/files/get/last.ckpt?path=%2F2021-04-23T18-19-01_ffhq_transformer%2Fcheckpoints%2Flast.ckpt&force' #FFHQ\n","if celebahq:\n","  !curl -L -o celebahq.yaml -C - 'https://app.koofr.net/content/links/6dddf083-40c8-470a-9360-a9dab2a94e96/files/get/2021-04-23T18-11-19-project.yaml?path=%2F2021-04-23T18-11-19_celebahq_transformer%2Fconfigs%2F2021-04-23T18-11-19-project.yaml&force' #CelebA-HQ\n","  !curl -L -o celebahq.ckpt -C - 'https://app.koofr.net/content/links/6dddf083-40c8-470a-9360-a9dab2a94e96/files/get/last.ckpt?path=%2F2021-04-23T18-11-19_celebahq_transformer%2Fcheckpoints%2Flast.ckpt&force' #CelebA-HQ"],"execution_count":null,"outputs":[]},{"cell_type":"code","metadata":{"id":"EXMSuW2EQWsd","cellView":"form"},"source":["# @title libraries and declarations\n"," \n","import argparse\n","import math\n","from pathlib import Path\n","import sys\n"," \n","sys.path.append('./taming-transformers')\n","from IPython import display\n","from base64 import b64encode\n","from omegaconf import OmegaConf\n","from PIL import Image\n","from taming.models import cond_transformer, vqgan\n","import torch\n","from torch import nn, optim\n","from torch.nn import functional as F\n","from torchvision import transforms\n","from torchvision.transforms import functional as TF\n","from tqdm.notebook import tqdm\n"," \n","from CLIP import clip\n","import kornia.augmentation as K\n","import numpy as np\n","import imageio\n","from PIL import ImageFile, Image\n","from imgtag import ImgTag    # metadatos \n","from libxmp import *         # metadatos\n","import libxmp                # metadatos\n","from stegano import lsb\n","import json\n","ImageFile.LOAD_TRUNCATED_IMAGES = True\n"," \n","def sinc(x):\n","    return torch.where(x != 0, torch.sin(math.pi * x) / (math.pi * x), x.new_ones([]))\n"," \n"," \n","def lanczos(x, a):\n","    cond = torch.logical_and(-a < x, x < a)\n","    out = torch.where(cond, sinc(x) * sinc(x/a), x.new_zeros([]))\n","    return out / out.sum()\n"," \n"," \n","def ramp(ratio, width):\n","    n = math.ceil(width / ratio + 1)\n","    out = torch.empty([n])\n","    cur = 0\n","    for i in range(out.shape[0]):\n","        out[i] = cur\n","        cur += ratio\n","    return torch.cat([-out[1:].flip([0]), out])[1:-1]\n"," \n"," \n","def resample(input, size, align_corners=True):\n","    n, c, h, w = input.shape\n","    dh, dw = size\n"," \n","    input = input.view([n * c, 1, h, w])\n"," \n","    if dh < h:\n","        kernel_h = lanczos(ramp(dh / h, 2), 2).to(input.device, input.dtype)\n","        pad_h = (kernel_h.shape[0] - 1) // 2\n","        input = F.pad(input, (0, 0, pad_h, pad_h), 'reflect')\n","        input = F.conv2d(input, kernel_h[None, None, :, None])\n"," \n","    if dw < w:\n","        kernel_w = lanczos(ramp(dw / w, 2), 2).to(input.device, input.dtype)\n","        pad_w = (kernel_w.shape[0] - 1) // 2\n","        input = F.pad(input, (pad_w, pad_w, 0, 0), 'reflect')\n","        input = F.conv2d(input, kernel_w[None, None, None, :])\n"," \n","    input = input.view([n, c, h, w])\n","    return F.interpolate(input, size, mode='bicubic', align_corners=align_corners)\n"," \n"," \n","class ReplaceGrad(torch.autograd.Function):\n","    @staticmethod\n","    def forward(ctx, x_forward, x_backward):\n","        ctx.shape = x_backward.shape\n","        return x_forward\n"," \n","    @staticmethod\n","    def backward(ctx, grad_in):\n","        return None, grad_in.sum_to_size(ctx.shape)\n"," \n"," \n","replace_grad = ReplaceGrad.apply\n"," \n"," \n","class ClampWithGrad(torch.autograd.Function):\n","    @staticmethod\n","    def forward(ctx, input, min, max):\n","        ctx.min = min\n","        ctx.max = max\n","        ctx.save_for_backward(input)\n","        return input.clamp(min, max)\n"," \n","    @staticmethod\n","    def backward(ctx, grad_in):\n","        input, = ctx.saved_tensors\n","        return grad_in * (grad_in * (input - input.clamp(ctx.min, ctx.max)) >= 0), None, None\n"," \n"," \n","clamp_with_grad = ClampWithGrad.apply\n"," \n"," \n","def vector_quantize(x, codebook):\n","    d = x.pow(2).sum(dim=-1, keepdim=True) + codebook.pow(2).sum(dim=1) - 2 * x @ codebook.T\n","    indices = d.argmin(-1)\n","    x_q = F.one_hot(indices, codebook.shape[0]).to(d.dtype) @ codebook\n","    return replace_grad(x_q, x)\n"," \n"," \n","class Prompt(nn.Module):\n","    def __init__(self, embed, weight=1., stop=float('-inf')):\n","        super().__init__()\n","        self.register_buffer('embed', embed)\n","        self.register_buffer('weight', torch.as_tensor(weight))\n","        self.register_buffer('stop', torch.as_tensor(stop))\n"," \n","    def forward(self, input):\n","        input_normed = F.normalize(input.unsqueeze(1), dim=2)\n","        embed_normed = F.normalize(self.embed.unsqueeze(0), dim=2)\n","        dists = input_normed.sub(embed_normed).norm(dim=2).div(2).arcsin().pow(2).mul(2)\n","        dists = dists * self.weight.sign()\n","        return self.weight.abs() * replace_grad(dists, torch.maximum(dists, self.stop)).mean()\n"," \n"," \n","def parse_prompt(prompt):\n","    vals = prompt.rsplit(':', 2)\n","    vals = vals + ['', '1', '-inf'][len(vals):]\n","    return vals[0], float(vals[1]), float(vals[2])\n"," \n"," \n","class MakeCutouts(nn.Module):\n","    def __init__(self, cut_size, cutn, cut_pow=1.):\n","        super().__init__()\n","        self.cut_size = cut_size\n","        self.cutn = cutn\n","        self.cut_pow = cut_pow\n","        self.augs = nn.Sequential(\n","            K.RandomHorizontalFlip(p=0.5),\n","            # K.RandomSolarize(0.01, 0.01, p=0.7),\n","            K.RandomSharpness(0.3,p=0.4),\n","            K.RandomAffine(degrees=30, translate=0.1, p=0.8, padding_mode='border'),\n","            K.RandomPerspective(0.2,p=0.4),\n","            K.ColorJitter(hue=0.01, saturation=0.01, p=0.7))\n","        self.noise_fac = 0.1\n"," \n"," \n","    def forward(self, input):\n","        sideY, sideX = input.shape[2:4]\n","        max_size = min(sideX, sideY)\n","        min_size = min(sideX, sideY, self.cut_size)\n","        cutouts = []\n","        for _ in range(self.cutn):\n","            size = int(torch.rand([])**self.cut_pow * (max_size - min_size) + min_size)\n","            offsetx = torch.randint(0, sideX - size + 1, ())\n","            offsety = torch.randint(0, sideY - size + 1, ())\n","            cutout = input[:, :, offsety:offsety + size, offsetx:offsetx + size]\n","            cutouts.append(resample(cutout, (self.cut_size, self.cut_size)))\n","        batch = self.augs(torch.cat(cutouts, dim=0))\n","        if self.noise_fac:\n","            facs = batch.new_empty([self.cutn, 1, 1, 1]).uniform_(0, self.noise_fac)\n","            batch = batch + facs * torch.randn_like(batch)\n","        return batch\n"," \n"," \n","def load_vqgan_model(config_path, checkpoint_path):\n","    config = OmegaConf.load(config_path)\n","    if config.model.target == 'taming.models.vqgan.VQModel':\n","        model = vqgan.VQModel(**config.model.params)\n","        model.eval().requires_grad_(False)\n","        model.init_from_ckpt(checkpoint_path)\n","    elif config.model.target == 'taming.models.cond_transformer.Net2NetTransformer':\n","        parent_model = cond_transformer.Net2NetTransformer(**config.model.params)\n","        parent_model.eval().requires_grad_(False)\n","        parent_model.init_from_ckpt(checkpoint_path)\n","        model = parent_model.first_stage_model\n","    elif config.model.target == 'taming.models.vqgan.GumbelVQ':\n","        model = vqgan.GumbelVQ(**config.model.params)\n","        print(config.model.params)\n","        model.eval().requires_grad_(False)\n","        model.init_from_ckpt(checkpoint_path)\n","    else:\n","        raise ValueError(f'unknown model type: {config.model.target}')\n","    del model.loss\n","    return model\n"," \n"," \n","def resize_image(image, out_size):\n","    ratio = image.size[0] / image.size[1]\n","    area = min(image.size[0] * image.size[1], out_size[0] * out_size[1])\n","    size = round((area * ratio)**0.5), round((area / ratio)**0.5)\n","    return image.resize(size, Image.LANCZOS)\n","\n","def download_img(img_url):\n","    try:\n","        return wget.download(img_url,out=\"input.jpg\")\n","    except:\n","        return\n"],"execution_count":null,"outputs":[]},{"cell_type":"markdown","metadata":{"id":"1tthw0YaispD"},"source":["## Parameters:\n"]},{"cell_type":"markdown","metadata":{"id":"t0MnTVTJKayY"},"source":["Mainly what you will have to modify will be texts:, there you can place the or texts you want to generate (separated with |). It is a list because you can put more than one text, and thus the IA try to 'mix' images, giving it the same priority to both texts.\n","\n","To use an initial image to the model, you just have to upload a file to the collection environment (in the section on the left), and then modifies image_name: putting the exact name of the file. Example: 'sample.png'.\n","\n","You can also modify the model by changing the line that says Model:. Currently, 1024, 16384, Wikiart, S-Flckr and Coco-Stuff are available. To activate them you have to have downloaded them first, and then you can simply select it.\n","\n","You can also use images_objective, which is basically to put one or more images that the AI will take as \"goal\", fulfilling the same function as to put a text. To put more than one you have to use | as a separator."]},{"cell_type":"code","metadata":{"id":"ZdlpRFL8UAlW","cellView":"form"},"source":["#@title Parameters\n","textos = \" spark AI,  spaceship solar systems planets, rainbow\" #@param {type:\"string\"}\n","ancho =  480#@param {type:\"number\"}\n","alto =  480#@param {type:\"number\"}\n","modelo = \"vqgan_imagenet_f16_16384\" #@param [\"vqgan_imagenet_f16_16384\", \"vqgan_imagenet_f16_1024\", \"wikiart_1024\", \"wikiart_16384\", \"coco\", \"faceshq\", \"sflckr\", \"ade20k\", \"ffhq\", \"celebahq\", \"gumbel_8192\"]\n","intervalo_imagenes =  50#@param {type:\"number\"}\n","imagen_inicial = None#@param {type:\"string\"}\n","imagenes_objetivo = None#@param {type:\"string\"}\n","seed = -1#@param {type:\"number\"}\n","max_iteraciones = -1#@param {type:\"number\"}\n","input_images = \"\"\n","\n","nombres_modelos={\"vqgan_imagenet_f16_16384\": 'ImageNet 16384',\"vqgan_imagenet_f16_1024\":\"ImageNet 1024\", \n","                 \"wikiart_1024\":\"WikiArt 1024\", \"wikiart_16384\":\"WikiArt 16384\", \"coco\":\"COCO-Stuff\", \"faceshq\":\"FacesHQ\", \"sflckr\":\"S-FLCKR\", \"ade20k\":\"ADE20K\", \"ffhq\":\"FFHQ\", \"celebahq\":\"CelebA-HQ\", \"gumbel_8192\": \"Gumbel 8192\"}\n","nombre_modelo = nombres_modelos[modelo]     \n","\n","if modelo == \"gumbel_8192\":\n","    is_gumbel = True\n","else:\n","    is_gumbel = False\n","\n","if seed == -1:\n","    seed = None\n","if imagen_inicial == \"None\":\n","    imagen_inicial = None\n","elif imagen_inicial and imagen_inicial.lower().startswith(\"http\"):\n","    imagen_inicial = download_img(imagen_inicial)\n","\n","\n","if imagenes_objetivo == \"None\" or not imagenes_objetivo:\n","    imagenes_objetivo = []\n","else:\n","    imagenes_objetivo = imagenes_objetivo.split(\"|\")\n","    imagenes_objetivo = [image.strip() for image in imagenes_objetivo]\n","\n","if imagen_inicial or imagenes_objetivo != []:\n","    input_images = True\n","\n","textos = [frase.strip() for frase in textos.split(\"|\")]\n","if textos == ['']:\n","    textos = []\n","\n","\n","args = argparse.Namespace(\n","    prompts=textos,\n","    image_prompts=imagenes_objetivo,\n","    noise_prompt_seeds=[],\n","    noise_prompt_weights=[],\n","    size=[ancho, alto],\n","    init_image=imagen_inicial,\n","    init_weight=0.,\n","    clip_model='ViT-B/32',\n","    vqgan_config=f'{modelo}.yaml',\n","    vqgan_checkpoint=f'{modelo}.ckpt',\n","    step_size=0.1,\n","    cutn=64,\n","    cut_pow=1.,\n","    display_freq=intervalo_imagenes,\n","    seed=seed,\n",")"],"execution_count":null,"outputs":[]},{"cell_type":"markdown","metadata":{"id":"dNLyTQWRKFUM"},"source":["## Generate"]},{"cell_type":"code","metadata":{"id":"g7EDme5RYCrt","cellView":"form"},"source":["#@title Generate pictures using  given text ...\n","device = torch.device('cuda:0' if torch.cuda.is_available() else 'cpu')\n","print('Using device:', device)\n","if textos:\n","    print('Using texts:', textos)\n","if imagenes_objetivo:\n","    print('Using image prompts:', imagenes_objetivo)\n","if args.seed is None:\n","    seed = torch.seed()\n","else:\n","    seed = args.seed\n","torch.manual_seed(seed)\n","print('Using seed:', seed)\n","\n","model = load_vqgan_model(args.vqgan_config, args.vqgan_checkpoint).to(device)\n","perceptor = clip.load(args.clip_model, jit=False)[0].eval().requires_grad_(False).to(device)\n","\n","cut_size = perceptor.visual.input_resolution\n","if is_gumbel:\n","    e_dim = model.quantize.embedding_dim\n","else:\n","    e_dim = model.quantize.e_dim\n","\n","f = 2**(model.decoder.num_resolutions - 1)\n","make_cutouts = MakeCutouts(cut_size, args.cutn, cut_pow=args.cut_pow)\n","if is_gumbel:\n","    n_toks = model.quantize.n_embed\n","else:\n","    n_toks = model.quantize.n_e\n","\n","toksX, toksY = args.size[0] // f, args.size[1] // f\n","sideX, sideY = toksX * f, toksY * f\n","if is_gumbel:\n","    z_min = model.quantize.embed.weight.min(dim=0).values[None, :, None, None]\n","    z_max = model.quantize.embed.weight.max(dim=0).values[None, :, None, None]\n","else:\n","    z_min = model.quantize.embedding.weight.min(dim=0).values[None, :, None, None]\n","    z_max = model.quantize.embedding.weight.max(dim=0).values[None, :, None, None]\n","\n","if args.init_image:\n","    pil_image = Image.open(args.init_image).convert('RGB')\n","    pil_image = pil_image.resize((sideX, sideY), Image.LANCZOS)\n","    z, *_ = model.encode(TF.to_tensor(pil_image).to(device).unsqueeze(0) * 2 - 1)\n","else:\n","    one_hot = F.one_hot(torch.randint(n_toks, [toksY * toksX], device=device), n_toks).float()\n","    if is_gumbel:\n","        z = one_hot @ model.quantize.embed.weight\n","    else:\n","        z = one_hot @ model.quantize.embedding.weight\n","    z = z.view([-1, toksY, toksX, e_dim]).permute(0, 3, 1, 2)\n","z_orig = z.clone()\n","z.requires_grad_(True)\n","opt = optim.Adam([z], lr=args.step_size)\n","\n","normalize = transforms.Normalize(mean=[0.48145466, 0.4578275, 0.40821073],\n","                                 std=[0.26862954, 0.26130258, 0.27577711])\n","\n","pMs = []\n","\n","for prompt in args.prompts:\n","    txt, weight, stop = parse_prompt(prompt)\n","    embed = perceptor.encode_text(clip.tokenize(txt).to(device)).float()\n","    pMs.append(Prompt(embed, weight, stop).to(device))\n","\n","for prompt in args.image_prompts:\n","    path, weight, stop = parse_prompt(prompt)\n","    img = resize_image(Image.open(path).convert('RGB'), (sideX, sideY))\n","    batch = make_cutouts(TF.to_tensor(img).unsqueeze(0).to(device))\n","    embed = perceptor.encode_image(normalize(batch)).float()\n","    pMs.append(Prompt(embed, weight, stop).to(device))\n","\n","for seed, weight in zip(args.noise_prompt_seeds, args.noise_prompt_weights):\n","    gen = torch.Generator().manual_seed(seed)\n","    embed = torch.empty([1, perceptor.visual.output_dim]).normal_(generator=gen)\n","    pMs.append(Prompt(embed, weight).to(device))\n","\n","def synth(z):\n","    if is_gumbel:\n","        z_q = vector_quantize(z.movedim(1, 3), model.quantize.embed.weight).movedim(3, 1)\n","    else:\n","        z_q = vector_quantize(z.movedim(1, 3), model.quantize.embedding.weight).movedim(3, 1)\n","    \n","    return clamp_with_grad(model.decode(z_q).add(1).div(2), 0, 1)\n","\n","def add_xmp_data(nombrefichero):\n","    imagen = ImgTag(filename=nombrefichero)\n","    imagen.xmp.append_array_item(libxmp.consts.XMP_NS_DC, 'creator', 'VQGAN+CLIP', {\"prop_array_is_ordered\":True, \"prop_value_is_array\":True})\n","    if args.prompts:\n","        imagen.xmp.append_array_item(libxmp.consts.XMP_NS_DC, 'title', \" | \".join(args.prompts), {\"prop_array_is_ordered\":True, \"prop_value_is_array\":True})\n","    else:\n","        imagen.xmp.append_array_item(libxmp.consts.XMP_NS_DC, 'title', 'None', {\"prop_array_is_ordered\":True, \"prop_value_is_array\":True})\n","    imagen.xmp.append_array_item(libxmp.consts.XMP_NS_DC, 'i', str(i), {\"prop_array_is_ordered\":True, \"prop_value_is_array\":True})\n","    imagen.xmp.append_array_item(libxmp.consts.XMP_NS_DC, 'model', nombre_modelo, {\"prop_array_is_ordered\":True, \"prop_value_is_array\":True})\n","    imagen.xmp.append_array_item(libxmp.consts.XMP_NS_DC, 'seed',str(seed) , {\"prop_array_is_ordered\":True, \"prop_value_is_array\":True})\n","    imagen.xmp.append_array_item(libxmp.consts.XMP_NS_DC, 'input_images',str(input_images) , {\"prop_array_is_ordered\":True, \"prop_value_is_array\":True})\n","    #for frases in args.prompts:\n","    #    imagen.xmp.append_array_item(libxmp.consts.XMP_NS_DC, 'Prompt' ,frases, {\"prop_array_is_ordered\":True, \"prop_value_is_array\":True})\n","    imagen.close()\n","\n","def add_stegano_data(filename):\n","    data = {\n","        \"title\": \" | \".join(args.prompts) if args.prompts else None,\n","        \"notebook\": \"VQGAN+CLIP\",\n","        \"i\": i,\n","        \"model\": nombre_modelo,\n","        \"seed\": str(seed),\n","        \"input_images\": input_images\n","    }\n","    lsb.hide(filename, json.dumps(data)).save(filename)\n","\n","@torch.no_grad()\n","def checkin(i, losses):\n","    losses_str = ', '.join(f'{loss.item():g}' for loss in losses)\n","    tqdm.write(f'i: {i}, loss: {sum(losses).item():g}, losses: {losses_str}')\n","    out = synth(z)\n","    TF.to_pil_image(out[0].cpu()).save('progress.png')\n","    add_stegano_data('progress.png')\n","    add_xmp_data('progress.png')\n","    display.display(display.Image('progress.png'))\n","\n","def ascend_txt():\n","    global i\n","    out = synth(z)\n","    iii = perceptor.encode_image(normalize(make_cutouts(out))).float()\n","\n","    result = []\n","\n","    if args.init_weight:\n","        result.append(F.mse_loss(z, z_orig) * args.init_weight / 2)\n","\n","    for prompt in pMs:\n","        result.append(prompt(iii))\n","    img = np.array(out.mul(255).clamp(0, 255)[0].cpu().detach().numpy().astype(np.uint8))[:,:,:]\n","    img = np.transpose(img, (1, 2, 0))\n","    filename = f\"steps/{i:04}.png\"\n","    imageio.imwrite(filename, np.array(img))\n","    add_stegano_data(filename)\n","    add_xmp_data(filename)\n","    return result\n","\n","def train(i):\n","    opt.zero_grad()\n","    lossAll = ascend_txt()\n","    if i % args.display_freq == 0:\n","        checkin(i, lossAll)\n","    loss = sum(lossAll)\n","    loss.backward()\n","    opt.step()\n","    with torch.no_grad():\n","        z.copy_(z.maximum(z_min).minimum(z_max))\n","\n","i = 0\n","try:\n","    with tqdm() as pbar:\n","        while True:\n","            train(i)\n","            if i == max_iteraciones:\n","                break\n","            i += 1\n","            pbar.update()\n","except KeyboardInterrupt:\n","    pass"],"execution_count":null,"outputs":[]},{"cell_type":"markdown","metadata":{"id":"02ZbcWw5YYnU"},"source":["## Generate video from frames\n","\n"]},{"cell_type":"code","metadata":{"id":"mFo5vz0UYBrF"},"source":["init_frame = 49 #Este es el frame donde el vídeo empezará\n","last_frame = i #Puedes cambiar i a el número del último frame que quieres generar. It will raise an error if that number of frames does not exist.\n","\n","min_fps = 10\n","max_fps = 30\n","\n","total_frames = last_frame-init_frame\n","\n","length = 15 #Tiempo deseado del vídeo en segundos\n","\n","frames = []\n","tqdm.write('Generando video...')\n","for i in range(init_frame,last_frame): #\n","    filename = f\"steps/{i:04}.png\"\n","    frames.append(Image.open(filename)) \n","\n","#fps = last_frame/10\n","fps = np.clip(total_frames/length,min_fps,max_fps)\n","\n","from subprocess import Popen, PIPE\n","p = Popen(['ffmpeg', '-y', '-f', 'image2pipe', '-vcodec', 'png', '-r', str(fps), '-i', '-', '-vcodec', 'libx264', '-r', str(fps), '-pix_fmt', 'yuv420p', '-crf', '17', '-preset', 'veryslow', 'video.mp4'], stdin=PIPE)\n","for im in tqdm(frames):\n","    im.save(p.stdin, 'PNG')\n","p.stdin.close()\n","\n","print(\"El vídeo está siendo ahora comprimido, espera...\")\n","p.wait()\n","print(\"El vídeo está listo\")"],"execution_count":null,"outputs":[]},{"cell_type":"markdown","metadata":{"id":"qD_kHshHYuF4"},"source":["\n","\n","## Copy paste video  to drive"]},{"cell_type":"code","execution_count":null,"metadata":{},"outputs":[],"source":["!cp -R /content/steps  /content/drive/MyDrive/VQGAN"]},{"cell_type":"code","metadata":{"id":"RheW6HY-Gwc9"},"source":["# !rm /content/steps/*"],"execution_count":null,"outputs":[]},{"cell_type":"code","metadata":{"id":"rfBqtvARbA-8"},"source":["!cp -R /content/video.mp4  /content/drive/MyDrive/VQGAN"],"execution_count":null,"outputs":[]},{"cell_type":"code","metadata":{"id":"E8lvN6b0mb-b","cellView":"form"},"source":["# @title Watch the video\n","\n","mp4 = open('video.mp4','rb').read()\n","data_url = \"data:video/mp4;base64,\" + b64encode(mp4).decode()\n","display.HTML(\"\"\"\n","<video width=400 controls>\n","      <source src=\"%s\" type=\"video/mp4\">\n","</video>\n","\"\"\" % data_url)"],"execution_count":null,"outputs":[]},{"cell_type":"markdown","metadata":{"id":"CxjI2CNIXVPF"},"source":["## Convert a video into an animated GIF\n","\n","FFmpeg is an excellent tool for converting videos into animated GIFs and the quality isn’t bad either. Use the scale filter to specify the width of the GIF, the -t parameter specific the duration while -r specifies the frame rate (fps)."]},{"cell_type":"code","metadata":{"id":"ejULQa0xas5y"},"source":["import os\n","from IPython.display import HTML\n","from IPython.display import Image"],"execution_count":null,"outputs":[]},{"cell_type":"code","metadata":{"id":"Jtn9zmvZJ-3V"},"source":["def convert_video_to_gif(input_video, scale, t, framerate):\n","\n","  output_gif= input_video[:-4]+'.gif'\n","  print('video will be  saved to {} ...'.format(output_gif))\n","  os.system(f\"ffmpeg -i {input_video} -vf scale={scale}:-1 -t {t} -r {framerate} {output_gif}\")\n","  return output_gif"],"execution_count":null,"outputs":[]},{"cell_type":"code","metadata":{"id":"cZsI3CT2XjNX"},"source":["#@title converting to gif with form { display-mode: \"form\" }\n","file_to_process = \"/content/drive/MyDrive/VQGAN/video.mp4\" #@param [\"\"] {allow-input: true}\n","scale =  300#@param {type:\"integer\"}\n","framerate = 10 #@param {type:\"integer\"}\n","t = 14 #@param {type:\"integer\"}\n","output_gif=convert_video_to_gif(file_to_process, scale, t, framerate)"],"execution_count":null,"outputs":[]},{"cell_type":"code","metadata":{"id":"-j5kqgjFXiuZ"},"source":["Image(open(output_gif,'rb').read())"],"execution_count":null,"outputs":[]}]}