diff --git a/.ci/spellcheck/.pyspelling.wordlist.txt b/.ci/spellcheck/.pyspelling.wordlist.txt index 0796b9d55bd..cc66de234b9 100644 --- a/.ci/spellcheck/.pyspelling.wordlist.txt +++ b/.ci/spellcheck/.pyspelling.wordlist.txt @@ -13,6 +13,7 @@ al Alibaba ALiBi AlpacaEval +aMUSEd analytics AnimeGAN api @@ -29,6 +30,7 @@ audiobooks audioldm AudioLDM autoencoder +autogenerated autoregressive autoregressively AutoTokenizer @@ -721,8 +723,10 @@ VM Vladlen VOC Vocoder +VQ VQA VQGAN +VQVAE waveform waveforms Wav @@ -742,6 +746,7 @@ XCode Xeon xl xvector +xxl XYWH Yiqin YOLO diff --git a/notebooks/277-amused-lightweight-text-to-image/277-amused-lightweight-text-to-image.ipynb b/notebooks/277-amused-lightweight-text-to-image/277-amused-lightweight-text-to-image.ipynb new file mode 100644 index 00000000000..3adb5774f7d --- /dev/null +++ b/notebooks/277-amused-lightweight-text-to-image/277-amused-lightweight-text-to-image.ipynb @@ -0,0 +1,689 @@ +{ + "cells": [ + { + "cell_type": "markdown", + "id": "ed3140bd-24c7-4eb3-9a1a-2b9ece1e2e76", + "metadata": {}, + "source": [ + "# Lightweight image generation with aMUSEd and OpenVINO\n", + "\n", + "[Amused](https://huggingface.co/docs/diffusers/api/pipelines/amused) is a lightweight text to image model based off of the [muse](https://arxiv.org/pdf/2301.00704.pdf) architecture. Amused is particularly useful in applications that require a lightweight and fast model such as generating many images quickly at once.\n", + "\n", + "Amused is a VQVAE token based transformer that can generate an image in fewer forward passes than many diffusion models. In contrast with muse, it uses the smaller text encoder CLIP-L/14 instead of t5-xxl. Due to its small parameter count and few forward pass generation process, amused can generate many images quickly. This benefit is seen particularly at larger batch sizes.\n", + "\n", + " \n" + ] + }, + { + "cell_type": "markdown", + "id": "836f7a88-8d7f-43b7-b0c7-394a7483d932", + "metadata": {}, + "source": [ + "#### Table of contents:\n", + "- [Prerequisites](#Prerequisites)\n", + "- [Load and run the original pipeline](#Load-and-run-the-original-pipeline)\n", + "- [Convert the model to OpenVINO IR](#Convert-the-model-to-OpenVINO-IR)\n", + " - [Convert the Text Encoder](#Convert-the-Text-Encoder)\n", + " - [Convert the U-ViT transformer](#Convert-the-U-ViT-transformer)\n", + " - [Convert VQ-GAN decoder (VQVAE)](#Convert-VQ-GAN-decoder-(VQVAE))\n", + "- [Compiling models and prepare pipeline](#Compiling-models-and-prepare-pipeline)\n", + "- [Interactive inference](#Interactive-inference)" + ] + }, + { + "cell_type": "markdown", + "id": "6e8f0c42-62f4-44f1-90a3-2bf33d797aa3", + "metadata": {}, + "source": [ + "## Prerequisites\n", + "[back to top ⬆️](#Table-of-contents:)" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "acba1777-2480-4f55-922b-a61c2d3be0ce", + "metadata": {}, + "outputs": [], + "source": [ + "%pip install -q \"diffusers>=0.25.0\" \"openvino>=2023.2.0\" \"accelerate>=0.20.3\" gradio torch --extra-index-url https://download.pytorch.org/whl/cpu" + ] + }, + { + "cell_type": "markdown", + "id": "31b4f27a-c164-499f-8cfe-4e94509b5384", + "metadata": {}, + "source": [ + "## Load and run the original pipeline\n", + "[back to top ⬆️](#Table-of-contents:)" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "740ff68e-2468-4a40-a51e-04f2e5f80a2d", + "metadata": { + "scrolled": true + }, + "outputs": [], + "source": [ + "import torch\n", + "from diffusers import AmusedPipeline\n", + "\n", + "\n", + "pipe = AmusedPipeline.from_pretrained(\n", + " \"amused/amused-256\",\n", + ")\n", + "\n", + "prompt = \"kind smiling ghost\"\n", + "image = pipe(prompt, generator=torch.Generator('cpu').manual_seed(8)).images[0]\n", + "image.save('text2image_256.png')" + ] + }, + { + "cell_type": "code", + "execution_count": 2, + "id": "539c80bf-c17f-4601-beb2-cbd847b2e728", + "metadata": { + "ExecuteTime": { + "end_time": "2024-01-18T00:48:48.361730700Z", + "start_time": "2024-01-18T00:48:48.268841300Z" + } + }, + "outputs": [ + { + "data": { + "text/plain": "", + "image/png": "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" + }, + "execution_count": 2, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "image" + ] + }, + { + "cell_type": "markdown", + "id": "9c38f8d4-fa96-4ba0-abe0-8f6050bb1c22", + "metadata": {}, + "source": [ + "## Convert the model to OpenVINO IR\n", + "[back to top ⬆️](#Table-of-contents:)\n", + "\n", + "aMUSEd consists of three separately trained components: a pre-trained CLIP-L/14 text encoder, a VQ-GAN, and a U-ViT.\n", + "\n", + "![image_png](https://cdn-uploads.huggingface.co/production/uploads/5dfcb1aada6d0311fd3d5448/97ca2Vqm7jBfCAzq20TtF.png)\n", + "\n", + "During inference, the U-ViT is conditioned on the text encoder’s hidden states and iteratively predicts values for all masked tokens. The cosine masking schedule determines a percentage of the most confident token predictions to be fixed after every iteration. After 12 iterations, all tokens have been predicted and are decoded by the VQ-GAN into image pixels." + ] + }, + { + "cell_type": "markdown", + "id": "be642b08-96d3-437d-8057-21f37777a9e6", + "metadata": {}, + "source": [ + "Define paths for converted models:" + ] + }, + { + "cell_type": "code", + "execution_count": 3, + "id": "a8801bd8-96e3-4db4-8cd1-362ccb6c7e99", + "metadata": { + "ExecuteTime": { + "end_time": "2024-01-18T00:48:48.378379700Z", + "start_time": "2024-01-18T00:48:48.366766300Z" + } + }, + "outputs": [], + "source": [ + "from pathlib import Path\n", + "\n", + "\n", + "TRANSFORMER_OV_PATH = Path('models/transformer_ir.xml')\n", + "TEXT_ENCODER_OV_PATH = Path('models/text_encoder_ir.xml')\n", + "VQVAE_OV_PATH = Path('models/vqvae_ir.xml')" + ] + }, + { + "cell_type": "markdown", + "id": "24868d33-c539-454c-ab27-5cbe99091dba", + "metadata": {}, + "source": [ + "Define the conversion function for PyTorch modules. We use `ov.convert_model` function to obtain OpenVINO Intermediate Representation object and `ov.save_model` function to save it as XML file." + ] + }, + { + "cell_type": "code", + "execution_count": 4, + "id": "1e7fb475-fd84-46e9-9ced-6b50628df8e2", + "metadata": { + "ExecuteTime": { + "end_time": "2024-01-18T00:48:48.536587700Z", + "start_time": "2024-01-18T00:48:48.377865700Z" + } + }, + "outputs": [], + "source": [ + "import torch\n", + "\n", + "import openvino as ov\n", + "\n", + "\n", + "def convert(model: torch.nn.Module, xml_path: str, example_input):\n", + " xml_path = Path(xml_path)\n", + " if not xml_path.exists():\n", + " xml_path.parent.mkdir(parents=True, exist_ok=True)\n", + " with torch.no_grad():\n", + " converted_model = ov.convert_model(model, example_input=example_input)\n", + " ov.save_model(converted_model, xml_path, compress_to_fp16=False)\n", + " \n", + " # cleanup memory\n", + " torch._C._jit_clear_class_registry()\n", + " torch.jit._recursive.concrete_type_store = torch.jit._recursive.ConcreteTypeStore()\n", + " torch.jit._state._clear_class_state()" + ] + }, + { + "cell_type": "markdown", + "id": "a3fbfa19-293c-4a64-9d32-9fa58df2062e", + "metadata": {}, + "source": [ + "### Convert the Text Encoder\n", + "[back to top ⬆️](#Table-of-contents:)" + ] + }, + { + "cell_type": "code", + "execution_count": 5, + "id": "a095363b-24b3-436d-8399-2797494829fb", + "metadata": { + "ExecuteTime": { + "end_time": "2024-01-18T00:48:48.555751Z", + "start_time": "2024-01-18T00:48:48.536587700Z" + } + }, + "outputs": [], + "source": [ + "class TextEncoderWrapper(torch.nn.Module):\n", + " def __init__(self, text_encoder):\n", + " super().__init__()\n", + " self.text_encoder = text_encoder\n", + "\n", + " def forward(self, input_ids=None, return_dict=None, output_hidden_states=None):\n", + " \n", + " outputs = self.text_encoder(\n", + " input_ids=input_ids,\n", + " return_dict=return_dict,\n", + " output_hidden_states=output_hidden_states, \n", + " )\n", + "\n", + " return outputs.text_embeds, outputs.last_hidden_state, outputs.hidden_states\n", + "\n", + "\n", + "input_ids = pipe.tokenizer(\n", + " prompt,\n", + " return_tensors=\"pt\",\n", + " padding=\"max_length\",\n", + " truncation=True,\n", + " max_length=pipe.tokenizer.model_max_length,\n", + ")\n", + "\n", + "input_example = {\n", + " 'input_ids': input_ids.input_ids,\n", + " 'return_dict': torch.tensor(True), \n", + " 'output_hidden_states': torch.tensor(True)\n", + "}\n", + "\n", + "convert(TextEncoderWrapper(pipe.text_encoder), TEXT_ENCODER_OV_PATH, input_example)" + ] + }, + { + "cell_type": "markdown", + "id": "1f91cd05-3b5b-46ec-89a9-bdaa711d4665", + "metadata": {}, + "source": [ + "### Convert the U-ViT transformer\n", + "[back to top ⬆️](#Table-of-contents:)" + ] + }, + { + "cell_type": "code", + "execution_count": 6, + "id": "b928ba09-b7dd-4071-9c64-51290c5b0461", + "metadata": { + "ExecuteTime": { + "end_time": "2024-01-18T00:48:48.598421100Z", + "start_time": "2024-01-18T00:48:48.553243600Z" + } + }, + "outputs": [], + "source": [ + "class TransformerWrapper(torch.nn.Module):\n", + " def __init__(self, transformer):\n", + " super().__init__()\n", + " self.transformer = transformer\n", + "\n", + " def forward(self, latents=None, micro_conds=None, pooled_text_emb=None, encoder_hidden_states=None):\n", + " \n", + " return self.transformer(\n", + " latents,\n", + " micro_conds=micro_conds, \n", + " pooled_text_emb=pooled_text_emb, \n", + " encoder_hidden_states=encoder_hidden_states,\n", + " )\n", + "\n", + "\n", + "shape = (1, 16, 16)\n", + "latents = torch.full(\n", + " shape, pipe.scheduler.config.mask_token_id, dtype=torch.long\n", + ")\n", + "latents = torch.cat([latents] * 2)\n", + "\n", + "\n", + "example_input = {\n", + " 'latents': latents,\n", + " 'micro_conds': torch.rand([2, 5], dtype=torch.float32),\n", + " 'pooled_text_emb': torch.rand([2, 768], dtype=torch.float32),\n", + " 'encoder_hidden_states': torch.rand([2, 77, 768], dtype=torch.float32), \n", + "}\n", + "\n", + "\n", + "pipe.transformer.eval()\n", + "w_transformer = TransformerWrapper(pipe.transformer)\n", + "convert(w_transformer, TRANSFORMER_OV_PATH, example_input)" + ] + }, + { + "cell_type": "markdown", + "id": "fb1c619c-b134-4a45-bed6-061da6b298a4", + "metadata": {}, + "source": [ + "### Convert VQ-GAN decoder (VQVAE)\n", + "[back to top ⬆️](#Table-of-contents:)\n", + "Function `get_latents` is needed to return real latents for the conversion. Due to the VQVAE implementation autogenerated tensor of the required shape is not suitable. This function repeats part of `AmusedPipeline`." + ] + }, + { + "cell_type": "code", + "execution_count": 7, + "id": "19d5aab3-a28c-4688-a567-3c2141c75487", + "metadata": { + "ExecuteTime": { + "end_time": "2024-01-18T00:48:53.564889700Z", + "start_time": "2024-01-18T00:48:48.586566100Z" + } + }, + "outputs": [], + "source": [ + "def get_latents():\n", + " shape = (1, 16, 16)\n", + " latents = torch.full(\n", + " shape, pipe.scheduler.config.mask_token_id, dtype=torch.long\n", + " )\n", + " model_input = torch.cat([latents] * 2)\n", + " \n", + " \n", + " model_output = pipe.transformer(\n", + " model_input,\n", + " micro_conds=torch.rand([2, 5], dtype=torch.float32),\n", + " pooled_text_emb=torch.rand([2, 768], dtype=torch.float32),\n", + " encoder_hidden_states=torch.rand([2, 77, 768], dtype=torch.float32),\n", + " )\n", + " guidance_scale = 10.0\n", + " uncond_logits, cond_logits = model_output.chunk(2)\n", + " model_output = uncond_logits + guidance_scale * (cond_logits - uncond_logits)\n", + " \n", + " \n", + " latents = pipe.scheduler.step(\n", + " model_output=model_output,\n", + " timestep=torch.tensor(0),\n", + " sample=latents,\n", + " ).prev_sample\n", + "\n", + " return latents\n", + "\n", + "\n", + "class VQVAEWrapper(torch.nn.Module):\n", + " def __init__(self, vqvae):\n", + " super().__init__()\n", + " self.vqvae = vqvae\n", + "\n", + " def forward(self, latents=None, force_not_quantize=True, shape=None):\n", + " outputs = self.vqvae.decode(\n", + " latents,\n", + " force_not_quantize=force_not_quantize,\n", + " shape=shape.tolist(), \n", + " )\n", + "\n", + " return outputs\n", + "\n", + "\n", + "latents = get_latents()\n", + "example_vqvae_input = {\n", + " 'latents': latents,\n", + " 'force_not_quantize': torch.tensor(True),\n", + " 'shape': torch.tensor((1, 16, 16, 64))\n", + "}\n", + "\n", + "convert(VQVAEWrapper(pipe.vqvae), VQVAE_OV_PATH, example_vqvae_input)" + ] + }, + { + "cell_type": "markdown", + "id": "b8c30389-9cc3-486e-93e8-03474161b8e9", + "metadata": {}, + "source": [ + "## Compiling models and prepare pipeline\n", + "[back to top ⬆️](#Table-of-contents:)" + ] + }, + { + "cell_type": "markdown", + "id": "113b5a88-8b21-43a8-b453-88065ef06e8b", + "metadata": {}, + "source": [ + "Select device from dropdown list for running inference using OpenVINO." + ] + }, + { + "cell_type": "code", + "execution_count": 8, + "id": "54f6f251-589b-49a8-baec-a6b94ddd55e4", + "metadata": { + "ExecuteTime": { + "end_time": "2024-01-18T00:48:53.709861300Z", + "start_time": "2024-01-18T00:48:53.705489700Z" + } + }, + "outputs": [ + { + "data": { + "text/plain": "Dropdown(description='Device:', index=1, options=('CPU', 'AUTO'), value='AUTO')", + "application/vnd.jupyter.widget-view+json": { + "version_major": 2, + "version_minor": 0, + "model_id": "743b26c5e45349bebd8406b18182d7b9" + } + }, + "execution_count": 8, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "import ipywidgets as widgets\n", + "\n", + "\n", + "core = ov.Core()\n", + "DEVICE = widgets.Dropdown(\n", + " options=core.available_devices + [\"AUTO\"],\n", + " value='AUTO',\n", + " description='Device:',\n", + " disabled=False,\n", + ")\n", + "\n", + "DEVICE" + ] + }, + { + "cell_type": "code", + "execution_count": 9, + "id": "e8b94b29-a65b-42ae-974d-52bb28090fc6", + "metadata": { + "ExecuteTime": { + "end_time": "2024-01-18T00:50:07.311462700Z", + "start_time": "2024-01-18T00:48:53.721372800Z" + } + }, + "outputs": [], + "source": [ + "ov_text_encoder = core.compile_model(TEXT_ENCODER_OV_PATH, DEVICE.value)\n", + "ov_transformer = core.compile_model(TRANSFORMER_OV_PATH, DEVICE.value)\n", + "ov_vqvae = core.compile_model(VQVAE_OV_PATH, DEVICE.value)" + ] + }, + { + "cell_type": "markdown", + "id": "1a05be62-e609-4a9a-9aec-243550d9e523", + "metadata": {}, + "source": [ + "Let's create callable wrapper classes for compiled models to allow interaction with original `AmusedPipeline` class. Note that all of wrapper classes return `torch.Tensor`s instead of `np.array`s.\n" + ] + }, + { + "cell_type": "code", + "execution_count": 10, + "id": "79dc24a0-5a0e-4e76-8c79-621e402a5633", + "metadata": { + "ExecuteTime": { + "end_time": "2024-01-18T00:50:07.323994600Z", + "start_time": "2024-01-18T00:50:07.318482500Z" + } + }, + "outputs": [], + "source": [ + "from collections import namedtuple\n", + "\n", + "\n", + "class ConvTextEncoderWrapper(torch.nn.Module):\n", + " def __init__(self, text_encoder, config):\n", + " super().__init__()\n", + " self.config = config\n", + " self.text_encoder = text_encoder\n", + "\n", + " def forward(self, input_ids=None, return_dict=None, output_hidden_states=None):\n", + " inputs = {\n", + " 'input_ids': input_ids,\n", + " 'return_dict': return_dict,\n", + " 'output_hidden_states': output_hidden_states\n", + " }\n", + " \n", + " outs = self.text_encoder(inputs)\n", + "\n", + " outputs = namedtuple('CLIPTextModelOutput', ('text_embeds', 'last_hidden_state', 'hidden_states'))\n", + " \n", + " text_embeds = torch.from_numpy(outs[0])\n", + " last_hidden_state = torch.from_numpy(outs[1])\n", + " hidden_states = list(torch.from_numpy(out) for out in outs.values())[2:]\n", + " \n", + " return outputs(text_embeds, last_hidden_state, hidden_states)" + ] + }, + { + "cell_type": "code", + "execution_count": 11, + "id": "fb328c35-80a6-4650-8c17-82e8b8b50b93", + "metadata": { + "ExecuteTime": { + "end_time": "2024-01-18T00:50:07.323994600Z", + "start_time": "2024-01-18T00:50:07.323994600Z" + } + }, + "outputs": [], + "source": [ + "class ConvTransformerWrapper(torch.nn.Module):\n", + " def __init__(self, transformer, config):\n", + " super().__init__()\n", + " self.config = config\n", + " self.transformer = transformer\n", + "\n", + " def forward(self, latents=None, micro_conds=None, pooled_text_emb=None, encoder_hidden_states=None, **kwargs):\n", + " outputs = self.transformer(\n", + " {\n", + " 'latents': latents,\n", + " 'micro_conds': micro_conds, \n", + " 'pooled_text_emb': pooled_text_emb, \n", + " 'encoder_hidden_states': encoder_hidden_states,\n", + " },\n", + " share_inputs=False\n", + " )\n", + "\n", + " return torch.from_numpy(outputs[0])" + ] + }, + { + "cell_type": "code", + "execution_count": 12, + "id": "e19f4ab7-85a7-41b2-b5bb-a5e544a3660c", + "metadata": { + "ExecuteTime": { + "end_time": "2024-01-18T00:50:07.355740600Z", + "start_time": "2024-01-18T00:50:07.340727100Z" + } + }, + "outputs": [], + "source": [ + "class ConvVQVAEWrapper(torch.nn.Module):\n", + " def __init__(self, vqvae, dtype, config):\n", + " super().__init__()\n", + " self.vqvae = vqvae\n", + " self.dtype = dtype\n", + " self.config = config\n", + "\n", + " def decode(self, latents=None, force_not_quantize=True, shape=None):\n", + " inputs = {\n", + " 'latents': latents,\n", + " 'force_not_quantize': force_not_quantize,\n", + " 'shape': torch.tensor(shape)\n", + " }\n", + " \n", + " outs = self.vqvae(inputs)\n", + " outs = namedtuple('VQVAE', 'sample')(torch.from_numpy(outs[0]))\n", + " \n", + " return outs" + ] + }, + { + "cell_type": "markdown", + "id": "6752651b-53a4-4f93-8910-6a2aa02ae69c", + "metadata": {}, + "source": [ + "And insert wrappers instances in the pipeline:" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "2a0067c1-d2ba-4e7d-9643-117f7c9e9c3c", + "metadata": { + "scrolled": true + }, + "outputs": [], + "source": [ + "prompt = \"kind smiling ghost\"\n", + "\n", + "transformer = pipe.transformer\n", + "vqvae = pipe.vqvae\n", + "text_encoder = pipe.text_encoder\n", + "\n", + "pipe.__dict__[\"_internal_dict\"]['_execution_device'] = pipe._execution_device # this is to avoid some problem that can occur in the pipeline \n", + "pipe.register_modules(\n", + " text_encoder=ConvTextEncoderWrapper(ov_text_encoder, text_encoder.config),\n", + " transformer=ConvTransformerWrapper(ov_transformer, transformer.config),\n", + " vqvae=ConvVQVAEWrapper(ov_vqvae, vqvae.dtype, vqvae.config),\n", + ")\n", + "\n", + "image = pipe(prompt, generator=torch.Generator('cpu').manual_seed(8)).images[0]\n", + "image.save('text2image_256.png')" + ] + }, + { + "cell_type": "code", + "execution_count": 14, + "id": "353aed47-2199-494a-a472-3f06c01eecc7", + "metadata": { + "ExecuteTime": { + "end_time": "2024-01-18T00:50:49.850162500Z", + "start_time": "2024-01-18T00:50:49.796282300Z" + } + }, + "outputs": [ + { + "data": { + "text/plain": "", + "image/png": "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" + }, + "execution_count": 14, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "image" + ] + }, + { + "cell_type": "markdown", + "id": "281ca3bd-651c-4cc8-bcee-22fa3fbb3636", + "metadata": {}, + "source": [ + "## Interactive inference\n", + "[back to top ⬆️](#Table-of-contents:)" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "5bf32074-c955-4210-84a3-0714bd960247", + "metadata": {}, + "outputs": [], + "source": [ + "import numpy as np\n", + "import gradio as gr\n", + "\n", + "\n", + "def generate(prompt, seed, _=gr.Progress(track_tqdm=True)):\n", + " image = pipe(prompt, generator=torch.Generator('cpu').manual_seed(seed)).images[0]\n", + " return image\n", + "\n", + "\n", + "demo = gr.Interface(\n", + " generate,\n", + " [\n", + " gr.Textbox(label=\"Prompt\"),\n", + " gr.Slider(0, np.iinfo(np.int32).max, label=\"Seed\")\n", + " ],\n", + " \"image\",\n", + " examples=[\n", + " [\"happy snowman\", 88],\n", + " [\"green ghost rider\", 0],\n", + " [\"kind smiling ghost\", 8],\n", + " ],\n", + " allow_flagging=\"never\",\n", + ")\n", + "try:\n", + " demo.queue().launch(debug=True)\n", + "except Exception:\n", + " demo.queue().launch(debug=True, share=True)\n", + "# if you are launching remotely, specify server_name and server_port\n", + "# demo.launch(server_name='your server name', server_port='server port in int')\n", + "# Read more in the docs: https://gradio.app/docs/" + ] + } + ], + "metadata": { + "kernelspec": { + "display_name": "Python 3 (ipykernel)", + "language": "python", + "name": "python3" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 3 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython3", + "version": "3.10.12" + } + }, + "nbformat": 4, + "nbformat_minor": 5 +} diff --git a/notebooks/277-amused-lightweight-text-to-image/README.md b/notebooks/277-amused-lightweight-text-to-image/README.md new file mode 100644 index 00000000000..5b98dc4b2ee --- /dev/null +++ b/notebooks/277-amused-lightweight-text-to-image/README.md @@ -0,0 +1,32 @@ +# Lightweight image generation with aMUSEd and OpenVINO™ + +[![Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/openvinotoolkit/openvino_notebooks/blob/main/notebooks/277-amused-lightweight-text-to-image/277-amused-lightweight-text-to-image.ipynb) + + + + +[Amused](https://huggingface.co/docs/diffusers/api/pipelines/amused) is a lightweight text to image model based off +of the [muse](https://arxiv.org/pdf/2301.00704.pdf) architecture. Amused is particularly useful in applications that +require a lightweight and fast model such as generating many images quickly at once. + +Amused is a VQVAE token based transformer that can generate an image in fewer forward passes than many diffusion models. + In contrast with muse, it uses the smaller text encoder CLIP-L/14 instead of t5-xxl. Due to its small parameter count + and few forward pass generation process, amused can generate many images quickly. This benefit is seen particularly at + larger batch size + +## Notebook contents +The tutorial consists from following steps: + +- Prerequisites +- Load and run the original pipeline +- Convert the model to OpenVINO IR + - Convert the Text Encoder + - Convert the U-ViT transformer + - Convert VQ-GAN decoder (VQVAE) +- Compiling models and prepare pipeline +- Interactive inference + +## Installation instructions +This is a self-contained example that relies solely on its own code.
+We recommend running the notebook in a virtual environment. You only need a Jupyter server to start. +For details, please refer to [Installation Guide](../../README.md). \ No newline at end of file