You signed out in another tab or window. Daily Challenge: https://bit. Click on “Refresh”. The 2 billion parameter variant of Stable Diffusion 3, our latest base model. Stable Diffusion consists of three parts: A text encoder, which turns your prompt into a latent vector. This stable-diffusion-2-depth model is resumed from stable-diffusion-2-base ( 512-base-ema. Stable Diffusion is a text-to-image latent diffusion model created by the researchers and engineers from CompVis, Stability AI and LAION . Some commonly used blocks are Loading a Checkpoint Model, entering a prompt, specifying a sampler, etc. Sep 15, 2022 · Sep 15, 2022, 5:30 AM PDT. DALL·E 3 can sometimes produce better results from shorter prompts than Stable Diffusion does. Install Stable Video Diffusion on Windows. Jul 6, 2024 · ComfyUI is a node-based GUI for Stable Diffusion. Key points: It is running at 6 tokens/sec. Mar 29, 2024 · Stable Diffusion 2. An optimized development notebook using the HuggingFace diffusers library. Stable Diffusion Web UI is a browser interface based on the Gradio library for Stable Diffusion. Added an extra input channel to process the (relative) depth prediction produced by MiDaS ( dpt_hybrid) which is used as an additional conditioning. Jan 12, 2023 · I am trying to install locally Stable Diffusion. Open AUTOMATIC1111 WebUI. The generative artificial intelligence technology is the premier product of Stability AI and is considered to be a part of the ongoing artificial intelligence boom . A random selection of images created using AI text to image generator Stable Diffusion. 1 was released shortly after the release of Stable Diffusion 2. The "locked" one preserves your model. Stable Diffusion. Stable Diffusion XL (SDXL) is a powerful text-to-image generation model that iterates on the previous Stable Diffusion models in three key ways: the UNet is 3x larger and SDXL combines a second text encoder (OpenCLIP ViT-bigG/14) with the original text encoder to significantly increase the number of parameters. ckpt) with an additional 55k steps on the same dataset (with punsafe=0. You switched accounts on another tab or window. Gradio app for Stable Diffusion 2 by Stability AI (v2-1_768-ema-pruned. SD 2. (SVD) Image-to-Video is a latent diffusion model trained to generate short video clips from an image conditioning. She wears a medieval dress. Core. In this post, we want to show how to use Stable Feb 11, 2023 · ControlNet is a neural network structure to control diffusion models by adding extra conditions. Stable Diffusion 2. Model checkpoints were publicly released at the end of August 2022 by a collaboration of Stability AI, CompVis, and Runway with support from EleutherAI and LAION. 2, Fig. 9, the full version of SDXL has been improved to be the world's best open image generation model. Step 1: Clone the repository. Image: The Verge via Lexica. We provide a reference script for sampling. The Web UI offers various features, including generating images from text prompts (txt2img), image-to-image processing (img2img Stable Diffusion v2. Midjourney, though, gives you the tools to reshape your images. The SD 2-v model produces 768x768 px outputs. zip from here, this package is from v1. This is likely the benefit of the larger language model which increases the expressiveness of the network. x series includes versions 2. Table of Contents. 0 is here and it bring big improvements and amazing new features. 1. 1 image. Step 4: Second img2img. Gen-2 represents yet another of our pivotal steps forward in this mission. This specific type of diffusion model was proposed in Stable Diffusion v2-base Model Card. from diffusers import AutoPipelineForImage2Image. Stable Diffusion 3: A comparison with SDXL and Stable Cascade. Stable Video Diffusion is released in the form of two image-to-video models, capable of generating 14 and 25 frames at customizable frame rates between 3 and 30 frames per second. We recommend using the DPMSolverMultistepScheduler as it gives a reasonable speed/quality trade-off and can be run with as little as 20 steps. Extract the zip file at your desired location. This is part 2 of the beginner’s guide series. bat to update web UI to the latest version, wait till Streamlined interface for generating images with AI in Krita. from diffusers. Released in late 2022, the 2. The model and the code that uses the model to generate the image (also known as inference code). ckpt). I follow the presented steps but when I get to the last one "run webui-use file" it opens the terminal and it's saying "Press any key to continue". 0 - What you need to know! table Diffusion 2. 1 ), and then fine-tuned for another 155k extra steps with punsafe=0. Read part 1: Absolute beginner’s This model card focuses on the model associated with the Stable Diffusion v2-1 model, codebase available here. Step 2: Enter the text-to-image setting. SDXL 1. I went to the SB folder, right-clicked open in the terminal and used . Currently supported pipelines are text-to-image, image-to-image, inpainting, 4x upscaling and depth-to-image. While users can interactively change Stable Diffusion’s two key hyperparameters, guidance scale and random seed, we fix the number of timesteps as 50, Feb 16, 2023 · Key Takeaways. 2; No token limit for prompts (original stable diffusion lets you use up to 75 tokens) DeepDanbooru integration, creates danbooru style tags for anime prompts; xformers, major speed increase for select cards: (add --xformers to commandline args) Jan 16, 2024 · Stable Diffusion—at least through Clipdrop and DreamStudio—is simpler to use, and can make great AI-generated images from relatively complex prompts. It provides a user-friendly way to interact with Stable Diffusion, an open-source text-to-image generation model. Jan 4, 2024 · The CLIP model Stable Diffusion automatically converts the prompt into tokens, a numerical representation of words it knows. Jul 8, 2024 · 상세 [편집] Stable Diffusion은 독일 뮌헨 대학교 Machine Vision & Learning Group (CompVis) 연구실의 "잠재 확산 모델을 이용한 고해상도 이미지 합성 연구" [1] 를 기반으로 하여, Stability AI 와 Runway ML 등의 지원을 받아 개발된 딥러닝 인공지능 모델이다. You can construct an image generation workflow by chaining different blocks (called nodes) together. Stable Diffusion v2 are two official Stable Diffusion models. 5 for certain prompts, but given the right prompt engineering 2. 0 images. 1, trained for real-time synthesis. Stable Diffusion can take an English text as an input, called the "text prompt", and generate images that match the text description. The SD 2. A diffusion model, which repeatedly "denoises" a 64x64 latent image patch. g. Navigate to the PNG Info page. k. These models have an increased resolution of 768x768 pixels and use a different CLIP model called You signed in with another tab or window. 0 = 1 step in our example below. utils import load_image. To run Stable Diffusion locally on your PC, download Stable Diffusion from GitHub and the latest checkpoints from HuggingFace. 0 and 2. * New Text-to-Image Diffusion Models using a new OpenCLIP Prompt examples : Prompt: cartoon character of a person with a hoodie , in style of cytus and deemo, ork, gold chains, realistic anime cat, dripping black goo, lineage revolution style, thug life, cute anthropomorphic bunny, balrog, arknights, aliased, very buff, black and red and yellow paint, painting illustration collage style, character Fooocus. ----- Which is the BEST AI Art Generator? We compare Dall E 2 vs Midjourney vs Stable Diffusion with a Mar 19, 2024 · Sample 2. Method 2: Generate a QR code with the tile resample model in image-to-image. x, SDXL, Stable Video Diffusion, Stable Cascade, SD3 and Stable Audio; Asynchronous Queue system; Many optimizations: Only re-executes the parts of the workflow that changes between executions. 85 billion image-text pairs, as well as LAION-High-Resolution, another subset of LAION-5B with 170 million images greater than 1024×1024 resolution (downsampled to Nov 26, 2023 · Step 1: Load the text-to-video workflow. First, save the image to your local storage. Highly accessible: It runs on a consumer grade laptop/computer. Stable Diffusion image 2 using 3D rendering. 5 * 2. Stable Diffusion image 1 using 3D rendering. Run python stable_diffusion. AI systems for image and video synthesis are quickly becoming more precise, realistic and controllable. Step 4: Run the workflow. 0 launch, made with forthcoming image Our most powerful and flexible workflow, leveraging state of the art models like Stable Diffusion 3. 1 LMU Munich, 2 IWR, Heidelberg University, 3 Runway CVPR 2022 (ORAL) Nov 22, 2023 · Step 2: Use the LoRA in the prompt. Step 4: Press Generate. That’s the basic Apr 3, 2024 · Here in our prompt, I used “3D Rendering” as my medium. 0 relative to 1. a CompVis. 1 is intended to address many of the relative shortcomings of 2. This model was trained to generate 25 frames at resolution 576x1024 given a context frame of the same size, finetuned from SVD Image-to-Video [14 frames] . This script has been tested with the following: CompVis/stable-diffusion-v1-4; runwayml/stable-diffusion-v1-5 (default) sayakpaul/sd-model-finetuned-lora-t4 Stable-Diffusion-v2. C Sep 22, 2022 · delete the venv directory (wherever you cloned the stable-diffusion-webui, e. 2 AND a dog AND a penguin :2. What is img2img? Software setup. Step 1: Create a background. That tends to prime the AI to include hands with good details. At the time of release in their foundational form, we have found these models surpass the leading closed models in user preference studies. Or continue to part 3 below. Just like the ones you would learn in the introductory course on neural networks. This model uses CLIP ViT-L/14 as text encoder, U-Net based latent denoising, and VAE based decoder to generate the final image. I find it's better able to parse longer, more nuanced instructions and get more details right. This weights here are intended to be used with the 🧨 Stable Diffusion 2 is a latent diffusion model conditioned on the penultimate text embeddings of a CLIP ViT-H/14 text encoder. 0 and fine-tuned on 2. Step-by-step guide to Img2img. The image-to-image pipeline will run for int(num_inference_steps * strength) steps, e. Stable Diffusion is a text-to-image model that uses a frozen CLIP ViT-L/14 text encoder to tune the model at text prompts. Stable Diffusion 3 Medium. also supports weights for prompts: a cat :1. Create a folder in the root of any drive (e. name is the name of the LoRA model. The main change in v2 models are. Mar 19, 2024 · This should be used as a guide rather than a rule. The Stability AI team takes great pride in introducing SDXL 1. 5. Jun 22, 2023 · This gives rise to the Stable Diffusion architecture. A very basic guide to get Stable Diffusion web UI up and running on Windows 10/11 NVIDIA GPU. Step 1: Select a checkpoint model. There is also a smaller RedPyjama 3B model requiring 4GM RAM. 0, the flagship image model developed by Stability AI, stands as the pinnacle of open models for image generation. This is a place to share your love, passion and knowledge about We compare Dall E 2 vs Midjourney vs Stable Diffusion with a series of prompts and styles. x Models. For more information, you can check out We would like to show you a description here but the site won’t allow us. It can be different from the filename. (If you use this option, make sure to select “ Add Python to 3. Generates high resolution images from text prompts using a latent diffusion model. It excels in photorealism, processes complex prompts, and generates clear text. In addition to 512×512 pixels, a higher resolution version of 768×768 pixels is available. x, SD2. Step 3: Remove the triton package in requirements. 1 seem to be better. py --help for additional options. settings. 1-v, HuggingFace) at 768x768 resolution and (Stable Diffusion 2. Nov 24, 2023 · Img2img (image-to-image) can improve your drawing while keeping the color and composition. Step 3: Enter img2img settings. C:\Users\you\stable-diffusion-webui\venv) check the environment variables (click the Start button, then type “environment properties” into the search bar and hit Enter. Fully supports SD1. webui. XL. First, remove all Python versions you have previously installed. People mentioned that 2. Stable Diffusion is a text-to-image latent diffusion model created by the researchers and engineers from CompVis, Stability AI and LAION. A Chinese website that provides answers to various questions. Aug 30, 2022 · Stable Diffusion’s initial training was on low-resolution 256×256 images from LAION-2B-EN, a set of 2. K. Version 2. Artificial Intelligence (AI) art is currently all the rage, but most AI image generators run in the cloud. SD-Turbo is based on a novel training method called Adversarial Diffusion Distillation (ADD) (see the technical report ), which allows sampling large-scale foundational image diffusion models in 1 to 4 steps at high image quality. Stability AI 는 영국인 Oct 28, 2023 · Method 1: Get prompts from images by reading PNG Info. Fooocus is a rethinking of Stable Diffusion and Midjourney’s designs: Learned from Stable Diffusion, the software is offline, open source, and free. 1 Newer versions don’t necessarily mean better image quality with the same parameters. 2. If you put in a word it has not seen before, it will be broken up into 2 or more sub-words until it knows what it is. Step 3: Enter ControlNet Setting. 0, on a less restrictive NSFW Feb 22, 2024 · Announcing Stable Diffusion 3 in early preview, our most capable text-to-image model with greatly improved performance in multi-subject prompts, image quality, and spelling abilities. Jan 4, 2024 · The first fix is to include keywords that describe hands and fingers, like “beautiful hands” and “detailed fingers”. 1 model was introduced towards the end of 2022. Learned from Midjourney, the manual tweaking is not needed, and users only need to focus on the prompts and images. Dec 6, 2022 · Finally, Stable Diffusion 2 now offers support for 768 x 768 images - over twice the area of the 512 x 512 images of Stable Diffusion 1. They hijack the cross-attention module by inserting two networks to transform the key and query vectors. 3. Step 2: Enter a prompt and a negative prompt. Stable Diffusion is a text-to-image model that generates photo-realistic images given any text input. Create a mask in the problematic area. Additionally, the enhancements made for transformer models , like MobileBERT, to dramatically speed up inference play a key role here as multi-head attention is Jul 8, 2023 · From now on, to run WebUI server, just open up Terminal and type runsd, and to exit or stop running server of WebUI, press Ctrl+C, it also removes unecessary temporary files and folders because we This repository comprises: StableDiffusion, a Swift package that developers can add to their Xcode projects as a dependency to deploy image generation capabilities in their apps. Humans read at 5 tokens/sec. Stable Diffusion pipelines. SD-Turbo is a distilled version of Stable Diffusion 2. In the System Properties window, click “Environment Variables. Jul 26, 2023 · 26 Jul. SDXL - The Best Open Source Image Model. Download the sd. Feb 18, 2022 · Step 3 – Copy Stable Diffusion webUI from GitHub. Reload to refresh your session. Stable Diffusion 3 is the latest and largest image Stable Diffusion model. First, describe what you want, and Clipdrop Stable Diffusion will generate four pictures for you. 7 Dec 2022: Stable-Diffusion 2. Step 2: Update ComfyUI. We would like to show you a description here but the site won’t allow us. The second fix is to use inpainting. 0版本後來引入了以768×768分辨率圖像生成的能力。 [16] 每一個txt2img的生成過程都會涉及到一個影響到生成圖像的隨機種子；用戶可以選擇隨機化種子以探索不同生成結果，或者使用相同的種子來獲得與之前生成的圖像相同的結果。 Stable Diffusion. The model was pretrained on 256x256 images and then finetuned on 512x512 images. Prompt: A beautiful ((Ukrainian Girl)) with very long straight hair, full lips, a gentle look, and very light white skin. bat ( #13638) add an option to not print stack traces on ctrl+c. . If the AI image is in PNG format, you can try to see if the prompt and other setting information were written in the PNG metadata field. Advanced workflow for generating high quality images quickly. 0 shines: It generates higher quality images in the sense that they matches the prompt more closely. Colab by anzorq. ”. Option 2: Use the 64-bit Windows installer provided by the Python website. It is trained on 512x512 images from a subset of the LAION-5B database. It offer's an improved resolution of 768x768 and with 860 million parameters. 0, the next iteration in the evolution of text-to-image generation models. DALL·E 3. Select the desired LoRA, which will add a tag in the prompt, like <lora:FilmGX4:1>. When using SDXL-Turbo for image-to-image generation, make sure that num_inference_steps * strength is larger or equal to 1. Oct 9, 2023 · Step 1: Install the QR Code Control Model. High-Resolution Image Synthesis with Latent Diffusion Models (A. Stable Diffusion 3 Medium is the latest and most advanced text-to-image AI model in our Stable Diffusion 3 series, comprising two billion parameters. This will save each sample individually as well as a grid of size n_iter x n_samples at the specified output location (default: outputs/txt2img-samples). Apr 2, 2024 · Stable Diffusion 2. It separates the imaging process into a “diffusion” process at runtime- it starts with only noise and gradually improves the image until it is entirely free of noise, progressively approaching the provided text description. weight is the emphasis applied to the LoRA model. The model is trained from scratch 550k steps at resolution 256x256 on a subset of LAION-5B filtered for explicit pornographic material, using the LAION-NSFW classifier with punsafe=0. co. Nov 25, 2023 · Llama 2 on iPhone. Double click the update. A public demonstration space can be found here. The words it knows are called tokens, which are represented as numbers. It promises to outperform previous models like Stable …. 1 use's LAION’s OpenCLIP-ViT/H for prompt interpretation and require more detailed negative prompts. Quality, sampling speed and diversity are best controlled via the scale, ddim_steps and ddim_eta arguments. 0. Step 2: Draw an apple. Parameters. With Git on your computer, use it copy across the setup files for Stable Diffusion webUI. The Stable Diffusion model is very flexible. A widgets-based interactive notebook for Google Colab that lets users generate AI images from prompts (Text2Image) using Stable Diffusion (by Stability AI, Runway & CompVis). 10 Comments. ly/3m5QejE This is a unofficial Group of Image Creation AIs. Note: Stable Diffusion v1 is a general text-to-image diffusion Model Description. A. Type and ye shall receive. Fooocus is an image generating software (based on Gradio ). 1 State-of-the-art generative AI model used to generate detailed images conditioned on text descriptions. Step 2: Create a virtual environment. Although generating images from text already feels like ancient technology, Stable Diffusion ，【2024最新版】Stable Diffusion汉化版安装包安装教程（附SD安装包下载）完全免费，拿走不谢！ 最强的AI绘画软件~，【AI绘画】清北大佬用250小时讲完的Stable diffusion最新教程，零基础到进阶AI绘画，全程干货，学不会我退出AI绘画圈！ Explore thousands of high-quality Stable Diffusion models, share your AI-generated art, and engage with a vibrant community of creators Nov 14, 2022 · Stable Diffusion. It copys the weights of neural network blocks into a "locked" copy and a "trainable" copy. 0. 1 and an aesthetic Stable Diffusion 3 Medium. Runway Research is dedicated to building the multimodal AI systems that will enable new forms of creativity. Jan 16, 2024 · Option 1: Install from the Microsoft store. Latent diffusion applies the diffusion process over a lower dimensional latent space to reduce memory and compute complexity. 3). To add a LoRA with weight in AUTOMATIC1111 Stable Diffusion WebUI, use the following syntax in the prompt or the negative prompt: <lora: name: weight>. It's designed for designers, artists, and creatives who need quick and easy image creation. Stable Diffusion XL. . The architecture of Stable Diffusion 2 is more or less identical to the original Stable Diffusion model so check out it’s API documentation for how to use Stable Diffusion 2. This notebook aims to be an alternative to WebUIs while offering a simple and lightweight GUI for anyone to get started Explainer provides an overview of Stable Diffusion’s archi-tecture, which can be expanded into details via user interac-tions (Fig. Nov 25, 2023 · The hypernetwork is usually a straightforward neural network: A fully connected linear network with dropout and activation. A decoder, which turns the final 64x64 latent patch into a higher-resolution 512x512 image. Though, again, the results you get really depend on what you ask for—and how much prompt engineering you're prepared to do. Then run Stable Diffusion in a special python environment using Miniconda. If you run into issues during installation or runtime, please refer to support for webui. You can find the weights, model card, and code here. 3 billion English-captioned images from LAION-5B‘s full collection of 5. /webui-user to run the file. 1 . Step 3: Download models. LDM & Stable Diffusion) Robin Rombach 1,2, Andreas Blattmann 1,2, Dominik Lorenz 1,2, Patrick Esser 3, Björn Ommer 1,2. For commercial use, please contact Model Description. The weights are available under a community license. Feb 6, 2023 · Image: Getty Images. Following the limited, research-only release of SDXL 0. It uses Hugging Face Diffusers🧨 implementation. Use inpainting to generate multiple images and choose the one you like. 4. Aug 24, 2023 · Stable Diffusionの使い方を初心者の方にも分かりやすく丁寧に説明します。Stable Diffusionの基本操作や設定方法に加えて、モデル・LoRA・拡張機能の導入方法やエラーの対処法・商用利用についてもご紹介します！ Stable Diffusion is a Latent Diffusion model developed by researchers from the Machine Vision and Learning group at LMU Munich, a. If you like it, please consider supporting me: [ ] Dec 21, 2022 · v2. co, and install them. We also finetune the widely used f8-decoder for temporal Aug 30, 2022 · Aug 30, 2022. Note: Stable Diffusion v1 is a general text-to-image diffusion AI Revolution - MidJourney AI, DALL-E 2, Stable Diffusion. What makes Stable Diffusion unique ? It is completely open source. Stable Diffusion 3 Large. The Swift package relies on the Core ML model files generated by python_coreml_stable_diffusion. - Acly/krita-ai-diffusion Nodes/graph/flowchart interface to experiment and create complex Stable Diffusion workflows without needing to code anything. 1 is out! Here's the announcement and here's where you can download the 768 model and here is 512 model "New stable diffusion model (Stable Diffusion 2. Use it with the stablediffusion repository: download the 512-depth-ema The latest Snapdragon 8 Gen 2 with micro tile inferencing helps enable large models like Stable Diffusion to run efficiently — expect more improvements with the next-gen Snapdragon. The Stability AI team is proud to release as an open model SDXL 1. ComfyUI breaks down a workflow into rearrangeable elements so you can easily make your own. 0 is slightly worse than 1. 0 is able to understand text prompt a lot better than v1 models and allow you to design prompts with higher precision. 0, an open model representing the next evolutionary step in text-to-image generation models. 98. Inpaint and outpaint with optional text prompt, no tweaking required. Using LoRA in Prompts: Continue to write your prompts as usual, and the selected LoRA will influence the output. 8. Thanks to this, training with small dataset of image pairs will not destroy Stable Diffusion Interactive Notebook 📓 🤖. The "trainable" one learns your condition. The Sep 25, 2023 · Stable Diffusionの実写・リアル系おすすめモデル. Stable Diffusion in pure C/C++. Aug 22, 2022 · You can join our dedicated community for Stable Diffusion here, where we have areas for developers, creatives, and just anyone inspired by this. 10 to PATH “) I recommend installing it from the Microsoft store. Aug 22, 2022 · Stable Diffusion with 🧨 Diffusers. Let it surprise you with some creative combination of keywords! Check out the Stable Diffusion Course for a step-by-step guided course. If I do so the terminal instantly closes. cpp development by creating an account on GitHub. Stable Diffusion v2 refers to a specific configuration of the model architecture that uses a downsampling-factor 8 autoencoder with an 865M UNet and OpenCLIP ViT-H/14 text encoder for the diffusion model. 0-pre we will update it to the latest webui version in step 3. Stable Diffusion is a deep learning, text-to-image model released in 2022 based on diffusion techniques. Created by the researchers and engineers from Stability AI, CompVis, and LAION, “Stable Diffusion” claims the crown from Craiyon, formerly known as DALL·E-Mini, to be the new state-of-the-art, text-to-image, open-source model. Llama 2 is a 7B model and needs 6GB RAM. Whether you're looking to visualize concepts, explore new creative avenues, or enhance A New Era for Motion (and) Pictures. ckpt) and finetuned for 200k steps. Apr 17, 2024 · DALL·E 3 feels better "aligned," so you may see less stereotypical results. 1-base, HuggingFace) at 512x512 resolution, both based on the same number of parameters and architecture as 2. Stable Diffusion v1 refers to a specific configuration of the model architecture that uses a downsampling-factor 8 autoencoder with an 860M UNet and CLIP ViT-L/14 text encoder for the diffusion model. LAION-5B is the largest, freely accessible multi-modal dataset that currently exists. Getty Images has filed a lawsuit in the US against Stability AI, creators of open-source AI art generator Stable Diffusion, escalating its legal battle against the firm. AI美女を生成するのにおすすめのモデルを紹介します。 こちらで紹介するのは日本人(アジア人)の美女に対応しているモデルですが、もし日本人っぽくならない場合は「Japanese actress」「Korean idol」といったプロンプトを入れるのがおすすめです。 The Stable-Diffusion-v1-4 checkpoint was initialized with the weights of the Stable-Diffusion-v1-2 checkpoint and subsequently fine-tuned on 225k steps at resolution 512x512 on "laion-aesthetics v2 5+" and 10% dropping of the text-conditioning to improve classifier-free guidance sampling. No Account Required! Stable Diffusion Online is a free Artificial Intelligence image generator that efficiently creates high-quality images from simple text prompts. You can no longer generate explicit content because pornographic materials were removed from training. This model card focuses on the model associated with the Stable Diffusion v2-base model, available here. Navigate to the 'Lora' section. start/restart generation by Ctrl (Alt) + Enter ( #13644) update prompts_from_file script to allow concatenating entries with the general prompt ( #13733) added a visible checkbox to input accordion. Contribute to leejet/stable-diffusion. 3D rendering. Here’s where Stable Diffusion 2. These kinds of algorithms are called "text-to-image". This stable-diffusion-2-1 model is fine-tuned from stable-diffusion-2 ( 768-v-ema. A few particularly relevant ones:--model_id <string>: name of a stable diffusion model ID hosted by huggingface. ch uw nl up ec od ot ul ek kv