Hires. SDXLベースモデルなので、SD1. Sticker-art. Waifu Diffusion - Beta 03. --> (Model-EX N-Embedding) Copy the file in C:Users***DocumentsAIStable-Diffusion automatic. I suggest WD Vae or FT MSE. The Civitai Link Key is a short 6 character token that you'll receive when setting up your Civitai Link instance (you can see it referenced here in this Civitai Link installation video). Simply copy paste to the same folder as selected model file. This is a checkpoint that's a 50% mix of AbyssOrangeMix2_hard and 50% Cocoa from Yohan Diffusion. Deep Space Diffusion. The resolution should stay at 512 this time, which is normal for Stable Diffusion. This is the fine-tuned Stable Diffusion model trained on screenshots from a popular animation studio. 1 to make it work you need to use . Be aware that some prompts can push it more to realism like "detailed". This model has been trained on 26,949 high resolution and quality Sci-Fi themed images for 2 Epochs. . This model is very capable of generating anime girls with thick linearts. xのLoRAなどは使用できません。. 45 GB) Verified: 14 days ago. Am i Real - Photo Realistic Mix Thank you for all Reviews, Great Trained Model/Great Merge Model/Lora Creator, and Prompt Crafter!!!1. Vaguely inspired by Gorillaz, FLCL, and Yoji Shin. SDXL consists of a two-step pipeline for latent diffusion: First, we use a base model to generate latents of the desired output size. They are committed to the exploration and appreciation of art driven by artificial intelligence, with a mission to foster a dynamic, inclusive, and supportive atmosphere. These are optional files, producing similar results to the official ControlNet models, but with added Style and Color functions. 8>a detailed sword, dmarble, intricate design, weapon, no humans, sunlight, scenery, light rays, fantasy, sharp focus, extreme details. Shinkai Diffusion is a LORA trained on stills from Makoto Shinkai's beautiful anime films made at CoMix Wave Films. 1 to make it work you need to use . 8I know there are already various Ghibli models, but with LoRA being a thing now it's time to bring this style into 2023. Install stable-diffusion-webui Download Models And download the ChilloutMix LoRA（Low-Rank Adaptation. 增强图像的质量，削弱了风格。. 5 with Automatic1111's checkpoint merger tool (Couldn't remember exactly the merging ratio and the interpolation method)About This LoRA is intended to generate an undressed version of the subject (on the right) alongside a clothed version (on the left). models. AingDiffusion (read: Ah-eeng Diffusion) is a merge of a bunch of anime models. Installation: As it is model based on 2. Using 'Add Difference' method to add some training content in 1. Robo-Diffusion 2. If you are the person or a legal representative of the person depicted, and would like to request the removal of this resource, you can do so here. Copy as single line prompt. 7 here) >, Trigger Word is ' mix4 ' . 5. 0 to 1. I am a huge fan of open source - you can use it however you like with only restrictions for selling my models. This extension allows you to seamlessly. This is a lora meant to create a variety of asari characters. Stable Diffusion Models, sometimes called checkpoint models, are pre-trained Stable Diffusion weights for generating a particular style of images. Very versatile, can do all sorts of different generations, not just cute girls. Usually this is the models/Stable-diffusion one. . Browse cyberpunk Stable Diffusion models, checkpoints, hypernetworks, textual inversions, embeddings, Aesthetic Gradients, and LORAsMarch 17, 2023 edit: quick note on how to use a negative embeddings. The only thing V5 doesn't do well most of the time are eyes, if you don't get decent eyes try adding perfect eyes or round eyes to the prompt and increase the weight till you are happy. Please support my friend's model, he will be happy about it - "Life Like Diffusion". Things move fast on this site, it's easy to miss. Read the rules on how to enter here!Komi Shouko (Komi-san wa Komyushou Desu) LoRA. You can download preview images, LORAs,. This one's goal is to produce a more "realistic" look in the backgrounds and people. 1, FFUSION AI converts your prompts into captivating artworks. It tends to lean a bit towards BoTW, but it's very flexible and allows for most Zelda versions. Donate Coffee for Gtonero >Link Description< This LoRA has been retrained from 4chanDark Souls Diffusion. 0 is suitable for creating icons in a 3D style. Vampire Style. The yaml file is included here as well to download. The information tab and the saved model information tab in the Civitai model have been merged. This embedding will fix that for you. AI一下子聪明起来，目前好看又实用。 merged a real2. Sci Fi is probably where it struggles most but it can do apocalyptic stuff. 31. I don't remember all the merges I made to create this model. Enter our Style Capture & Fusion Contest! Join Part 1 of our two-part Style Capture & Fusion Contest! Running NOW until November 3rd, train and submit any artist's style as a LoRA for a chance to win $5,000 in prizes! Read the rules on how to enter here!mix of many models, VAE is baked，good at NSFW 很多模型的混合，vae已经烘焙，擅长nsfw setting: Denoising strength: 0. Huggingface is another good source though the interface is not designed for Stable Diffusion models. models. Black Area is the selected or "Masked Input". Restart you Stable. For more example images, just take a look at More attention on shades and backgrounds compared with former models ( Andromeda-Mix | Stable Diffusion Checkpoint | Civitai) Hands-fix is still waiting to be improved. WD 1. Recommended settings: weight=0. stable Diffusion models, embeddings, LoRAs and more. Browse civitai Stable Diffusion models, checkpoints, hypernetworks, textual inversions, embeddings, Aesthetic Gradients, and LORAs360 Diffusion v1. It shouldn't be necessary to lower the weight. Just another good looking model with a sad feeling . 在使用v1. 자체 그림 생성 서비스를 제공하는데, 학습 및 LoRA 파일 제작 기능도 지원하고 있어서 학습에 대한 진입장벽을. Click Generate, give it a few seconds, and congratulations, you have generated your first image using Stable Diffusion! (you can track the progress of the image generation under the Run Stable Diffusion cell at the bottom of the collab notebook as well!) Click on the image, and you can right-click save it. This includes Nerf's Negative Hand embedding. Choose from a variety of subjects, including animals and. Use it at around 0. 4-0. Copy the file 4x-UltraSharp. LORA: For anime character LORA, the ideal weight is 1. Copy this project's url into it, click install. ago. 1_realistic: Hello everyone! These two are merge models of a number of other furry/non furry models, they also have mixed in a lot. 5 for a more authentic style, but it's also good on AbyssOrangeMix2. The split was around 50/50 people landscapes. Posted first on HuggingFace. The Civitai Discord server is described as a lively community of AI art enthusiasts and creators. 0 is suitable for creating icons in a 2D style, while Version 3. 2. Try the Stable Diffusion, and ChilloutMix, and LoRA to generate the images on Apple M1. Usage: Put the file inside stable-diffusion-webuimodelsVAE. Known issues: Stable Diffusion is trained heavily on binary genders and amplifies. 5 using +124000 images, 12400 steps, 4 epochs +32 training hours. Recommend: DPM++2M Karras, Clip skip 2 Sampler, Steps: 25-35+. Sensitive Content. NeverEnding Dream (a. These models are the TencentARC T2I-Adapters for ControlNet ( TT2I Adapter research paper here ), converted to Safetensor. Give your model a name and then select ADD DIFFERENCE (This will make sure to add only the parts of the inpainting model that will be required) Select ckpt or safetensors. 4 - Enbrace the ugly, if you dare. So veryBadImageNegative is the dedicated negative embedding of viewer-mix_v1. . It gives you more delicate anime-like illustrations and a lesser AI feeling. Counterfeit-V3 (which has 2. Space (main sponsor) and Smugo. Please use it in the "\stable-diffusion-webui\embeddings" folder. Check out for more -- Ko-Fi or buymeacoffee LORA network trained on Stable Diffusion 1. Install Stable Diffusion Webui's Extension tab, go to Install from url sub-tab. I used CLIP skip and AbyssOrangeMix2_nsfw for all the examples. ”. Copy this project's url into it, click install. It’s GitHub for AI. When using a Stable Diffusion (SD) 1. Highest Rated. This version has gone though over a dozen revisions before I decided to just push this one for public testing. It also has a strong focus on NSFW images and sexual content with booru tag support. This upscaler is not mine, all the credit go to: Kim2091 Official WiKi Upscaler page: Here License of use it: Here HOW TO INSTALL: Rename the file from: 4x-UltraSharp. Stable Diffusion Models, or checkpoint models, are pre-trained Stable Diffusion weights for generating a particular style of images. I apologize as the preview images for both contain images generated with both, but they do produce similar results, try both and see which works. Step 2. Trained on 70 images. It is a Latent Diffusion Model that uses two fixed, pretrained text encoders ( OpenCLIP-ViT/G and CLIP-ViT/L ). Negative Embeddings: unaestheticXL use stable-diffusion-webui v1. I spent six months figuring out how to train a model to give me consistent character sheets to break apart in Photoshop and animate. IF YOU ARE THE CREATOR OF THIS MODEL PLEASE CONTACT US TO GET IT TRANSFERRED TO YOU! This is the fine-tuned Stable Diffusion model trained on screenshots from a popular animation studio. The resolution should stay at 512 this time, which is normal for Stable Diffusion. NAI is a model created by the company NovelAI modifying the Stable Diffusion architecture and training method. You can use some trigger words (see Appendix A) to generate specific styles of images. art. This checkpoint includes a config file, download and place it along side the checkpoint. Follow me to make sure you see new styles, poses and Nobodys when I post them. Civitai là một nền tảng cho phép người dùng tải xuống và tải lên các hình ảnh do AI Stable Diffusion tạo ra. In addition, although the weights and configs are identical, the hashes of the files are different. Sampler: DPM++ 2M SDE Karras. Usage: Put the file inside stable-diffusion-webui\models\VAE. Yuzu. It may also have a good effect in other diffusion models, but it lacks verification. Please support my friend's model, he will be happy about it - "Life Like Diffusion". So, it is better to make comparison by yourself. 3 + 0. 增强图像的质量，削弱了风格。. SCMix_grc_tam | Stable Diffusion LORA | Civitai. v8 is trash. Guaranteed NSFW or your money back Fine-tuned from Stable Diffusion v2-1-base 19 epochs of 450,000 images each, co. 41: MothMix 1. It proudly offers a platform that is both free of charge and open source. Warning: This model is NSFW. He was already in there, but I never got good results. Install Stable Diffusion Webui's Extension tab, go to Install from url sub-tab. Once you have Stable Diffusion, you can download my model from this page and load it on your device. This checkpoint recommends a VAE, download and place it in the VAE folder. 0 Status (Updated: Nov 14, 2023): - Training Images: +2300 - Training Steps: +460k - Approximate percentage of completion: ~58%. My Discord, for everything related. But for some "good-trained-model" may hard to effect. . Simply copy paste to the same folder as selected model file. Auto Stable Diffusion Photoshop插件教程，释放轻薄本AI潜力，这4个stable diffusion模型，让Stable diffusion生成写实图片,100%简单!10分钟get新姿. This model is capable of generating high-quality anime images. If your characters are always wearing jackets/half off jackets, try adding "off shoulder" in negative prompt. 8-1，CFG=3-6. You can swing it both ways pretty far out from -5 to +5 without much distortion. v5. Submit your Part 2 Fusion images here, for a chance to win $5,000 in prizes!Trained on Stable Diffusion v1. articles. All the images in the set are in png format with the background removed, making it possible to use multiple images in a single scene. Use the same prompts as you would for SD 1. Submit your Part 2 Fusion images here, for a chance to win $5,000 in prizes!Dynamic Studio Pose. 3. The Civitai Discord server is described as a lively community of AI art enthusiasts and creators. k. Sci-Fi Diffusion v1. You can view the final results with. Description. The model is now available in mage, you can subscribe there and use my model directly. Installation: As it is model based on 2. Its main purposes are stickers and t-shirt design. merging another model with this one is the easiest way to get a consistent character with each view. 5. If you can find a better setting for this model, then good for you lol. 0+RPG+526, accounting for 28% of DARKTANG. V6. 5 model to create isometric cities, venues, etc more precisely. That is why I was very sad to see the bad results base SD has connected with its token. posts. The v4 version is a great improvement in the ability to adapt multiple models, so without further ado, please refer to the sample image and you will understand immediately. Civitai is the go-to place for downloading models. This embedding can be used to create images with a "digital art" or "digital painting" style. Hello my friends, are you ready for one last ride with Stable Diffusion 1. I will continue to update and iterate on this large model, hoping to add more content and make it more interesting. PEYEER - P1075963156. Performance and Limitations. images. 0 (B1) Status (Updated: Nov 18, 2023): - Training Images: +2620 - Training Steps: +524k - Approximate percentage of completion: ~65%. Civitai . Browse touhou Stable Diffusion models, checkpoints, hypernetworks, textual inversions, embeddings, Aesthetic Gradients, and LORAsBrowse tattoo Stable Diffusion models, checkpoints, hypernetworks, textual inversions, embeddings, Aesthetic Gradients, and LORAsBrowse breast Stable Diffusion models, checkpoints, hypernetworks, textual inversions, embeddings, Aesthetic Gradients, and LORAsThis is already baked into the model but it never hurts to have VAE installed. V7 is here. Ligne claire is French for "clear line" and the style focuses on strong lines, flat colors and lack of gradient shading. 直接Civitaiを使わなくても、Web UI上でサムネイル自動取得やバージョン管理ができるようになります。. 5 and 10 CFG Scale and between 25 and 30 Steps with DPM++ SDE Karras. Thank you for your support!CitrineDreamMix is a highly versatile model capable of generating many different types of subjects in a variety of styles. 5. I used CLIP skip and AbyssOrangeMix2_nsfw for all the examples. Hires upscaler: ESRGAN 4x or 4x-UltraSharp or 8x_NMKD-Superscale_150000_G Hires upscale: 2+ Hires steps: 15+Cheese Daddy's Landscapes mix - 4. To reproduce my results you MIGHT have to change these settings: Set "Do not make DPM++ SDE deterministic across different batch sizes. If faces apear more near the viewer, it also tends to go more realistic. If you gen higher resolutions than this, it will tile. Version 4 is for SDXL, for SD 1. When comparing stable-diffusion-howto and civitai you can also consider the following projects: stable-diffusion-webui-colab - stable diffusion webui colab. Additionally, if you find this too overpowering, use it with weight, like (FastNegativeEmbedding:0. In this video, I explain:1. Stable Diffusion Webui Extension for Civitai, to help you handle models much more easily. 5 for generating vampire portraits! Using a variety of sources such as movies, novels, video games, and cosplay photos, I've trained the model to produce images with all the classic vampire features like fangs and glowing eyes. What kind of. This model is a 3D merge model. This model uses the core of the Defacta 3rd series, but has been largely converted to a realistic model. SD XL. To mitigate this, weight reduction to 0. Western Comic book styles are almost non existent on Stable Diffusion. Steps and CFG: It is recommended to use Steps from “20-40” and CFG scale from “6-9”, the ideal is: steps 30, CFG 8. 1. Cmdr2's Stable Diffusion UI v2. If you use Stable Diffusion, you probably have downloaded a model from Civitai. This model has been archived and is not available for download. 5 version now is available in tensor. Since this embedding cannot drastically change the artstyle and composition of the image, not one hundred percent of any faulty anatomy can be improved. Install Stable Diffusion Webui's Extension tab, go to Install from url sub-tab. This is a simple extension to add a Photopea tab to AUTOMATIC1111 Stable Diffusion WebUI. It has been trained using Stable Diffusion 2. 5 and 10 CFG Scale and between 25 and 30 Steps with DPM++ SDE Karras. Soda Mix. The first step is to shorten your URL. The information tab and the saved model information tab in the Civitai model have been merged. Support☕ more info. Recommendation: clip skip 1 (clip skip 2 sometimes generate weird images) 2:3 aspect ratio (512x768 / 768x512) or 1:1 (512x512) DPM++ 2M CFG 5-7. Just put it into SD folder -> models -> VAE folder. It merges multiple models based on SDXL. The word "aing" came from informal Sundanese; it means "I" or "My". AS-Elderly: Place at the beginning of your positive prompt at strength of 1. 💡 Openjourney-v4 prompts. Although these models are typically used with UIs, with a bit of work they can be used with the. Set the multiplier to 1. また、実在する特定の人物に似せた画像を生成し、本人の許諾を得ることなく公に公開することも禁止事項とさせて頂きます。. . Noosphere - v3 | Stable Diffusion Checkpoint | Civitai. This checkpoint recommends a VAE, download and place it in the VAE folder. Browse from thousands of free Stable Diffusion models, spanning unique anime art styles, immersive 3D renders, stunning. Things move fast on this site, it's easy to miss. Sticker-art. Not intended for making profit. This model was finetuned with the trigger word qxj. 有问题/错误请及时联系 千秋九yuno779 修改，谢谢。 备用同步链接： Stable Diffusion 从入门到卸载 ② Stable Diffusion 从入门到卸载 ③ Civitai | Stable Diffusion 从入门到卸载 【中文教程】 前言 介绍说明 Stable D. fix is needed for prompts where the character is far away in order to make decent images, it drastically improve the quality of face and eyes! Sampler: DPM++ SDE Karras: 20 to 30 steps. This is a fine-tuned variant derived from Animix, trained with selected beautiful anime images. SafeTensor. This upscaler is not mine, all the credit go to: Kim2091 Official WiKi Upscaler page: Here License of use it: Here HOW TO INSTALL: Rename the file from: 4x-UltraSharp. Please let me know if there is a model where both "Share merges of this model" and "Use different permissions on merges" are not allowed. CarDos Animated. Updated: Oct 31, 2023. >Initial dimensions 512x615 (WxH) >Hi-res fix by 1. pth inside the folder: "YOUR ~ STABLE ~ DIFFUSION ~ FOLDERmodelsESRGAN"). ComfyUI is a super powerful node-based, modular, interface for Stable Diffusion. Hey! My mix is a blend of models which has become quite popular with users of Cmdr2's UI. Download (1. 8 is often recommended. 1 and V6. It creates realistic and expressive characters with a "cartoony" twist. I have created a set of poses using the openpose tool from the Controlnet system. If you want a portrait photo, try using a 2:3 or a 9:16 aspect ratio. Create stunning and unique coloring pages with the Coloring Page Diffusion model! Designed for artists and enthusiasts alike, this easy-to-use model generates high-quality coloring pages from any text prompt. This method is mostly tested on landscape. Now I am sharing it publicly. It is advisable to use additional prompts and negative prompts. (avoid using negative embeddings unless absolutely necessary) From this initial point, experiment by adding positive and negative tags and adjusting the settings. Three options are available. 2. Final Video Render. If you like the model, please leave a review! This model card focuses on Role Playing Game portrait similar to Baldur's Gate, Dungeon and Dragon, Icewindale, and more modern style of RPG character. This is the fine-tuned Stable Diffusion model trained on screenshots from a popular animation studio. Which includes characters, background, and some objects. Join us on our Discord: collection of OpenPose skeletons for use with ControlNet and Stable Diffusion. KayWaii. Therefore: different name, different hash, different model. 3 here: RPG User Guide v4. If you want to get mostly the same results, you definitely will need negative embedding: EasyNegative, it's better to use it at 0. While we can improve fitting by adjusting weights, this can have additional undesirable effects. iCoMix - Comic style Mix! Thank you for all Reviews, Great Model/Lora Creator, and Prompt Crafter!!!Step 1: Make the QR Code. The yaml file is included here as well to download. Civitai. It allows users to browse, share, and review custom AI art models, providing a space for creators to showcase their work and for users to find inspiration. 0 updated. com (using ComfyUI) to make sure the pipelines were identical and found that this model did produce better. The first version I'm uploading is a fp16-pruned with no baked vae, which is less than 2 GB, meaning you can get up to 6 epochs in the same batch on a colab. 5 version please pick version 1,2,3 I don't know a good prompt for this model, feel free to experiment i also have. 5) trained on screenshots from the film Loving Vincent. And it contains enough information to cover various usage scenarios. Clip Skip: It was trained on 2, so use 2. Please consider to support me via Ko-fi. 6/0. For more information, see here . Trained isometric city model merged with SD 1. 適用すると、キャラを縁取りしたような絵になります。. Plans Paid; Platforms Social Links Visit Website Add To Favourites. Instead, the shortcut information registered during Stable Diffusion startup will be updated. Load pose file into ControlNet, make sure to set preprocessor to "none" and model to "control_sd15_openpose". If using the AUTOMATIC1111 WebUI, then you will. Choose the version that aligns with th. It has the objective to simplify and clean your prompt. 8 is often recommended. 404 Image Contest. I am a huge fan of open source - you can use it however you like with only restrictions for selling my models. This model was finetuned with the trigger word qxj. Submit your Part 2 Fusion images here, for a chance to win $5,000 in prizes!Browse lora Stable Diffusion models, checkpoints, hypernetworks, textual inversions, embeddings, Aesthetic Gradients, and LORAsUPDATE DETAIL (中文更新说明在下面) Hello everyone, this is Ghost_Shell, the creator. For instance: On certain image-sharing sites, many anime character LORAs are overfitted. 0 | Stable Diffusion Checkpoint | Civitai. How to use: A preview of each frame is generated and outputted to \stable-diffusion-webui\outputs\mov2mov-images\<date> if you interrupt the generation, a video is created with the current progress. For next models, those values could change. So far so good for me. Look no further than our new stable diffusion model, which has been trained on over 10,000 images to help you generate stunning fruit art surrealism, fruit wallpapers, banners, and more! You can create custom fruit images and combinations that are both beautiful and unique, giving you the flexibility to create the perfect image for any occasion. v5. 0 significantly improves the realism of faces and also greatly increases the good image rate. r/StableDiffusion. 5 weight. While we can improve fitting by adjusting weights, this can have additional undesirable effects. 1 | Stable Diffusion Checkpoint | Civitai. The overall styling is more toward manga style rather than simple lineart. Posting on civitai really does beg for portrait aspect ratios. It excels at creating beautifully detailed images in a style somewhere in the middle between anime and realism. 4 + 0. 55, Clip skip: 2, ENSD: 31337, Hires upscale: 4. This lora was trained not only on anime but also fanart so compared to my other loras it should be more versatile. These are the concepts for the embeddings. This Stable diffusion checkpoint allows you to generate pixel art sprite sheets from four different angles. co. This is a Dreamboothed Stable Diffusion model trained on the DarkSouls series Style. Eastern Dragon - v2 | Stable Diffusion LoRA | Civitai-----Old versions (not recommended): Description below is for v4. Download (2. Download the User Guide v4. 5D/3D images) Steps : 30+ (I strongly suggest 50 for complex prompt) AnimeIllustDiffusion is a pre-trained, non-commercial and multi-styled anime illustration model. pth. Through this process, I hope not only to gain a deeper. 3. Colorfulxl is out! Thank you so much for the feedback and examples of your work! It's very motivating. 推荐设置：权重=0. Upscaler: 4x-Ultrasharp or 4X NMKD Superscale. Architecture is ok, especially fantasy cottages and such. fix is needed for prompts where the character is far away in order to make decent images, it drastically improve the quality of face and eyes! Sampler: DPM++ SDE Karras: 20 to 30 steps. Join. Style model for Stable Diffusion. 現時点でLyCORIS. This is a fine-tuned Stable Diffusion model designed for cutting machines. Stable Difussion Web UIでCivitai Helperを使う方法まとめ. Pixar Style Model. It's also very good at aging people so adding an age can make a big difference. 0. I did not want to force a model that uses my clothing exclusively, this is. Use the negative prompt: "grid" to improve some maps, or use the gridless version. 5 (general), 0. This embedding will fix that for you. 1_realistic: Hello everyone! These two are merge models of a number of other furry/non furry models, they also have mixed in a lot. In the interest of honesty I will disclose that many of these pictures here have been cherry picked, hand-edited and re-generated. The recommended sampling is k_Euler_a or DPM++ 2M Karras on 20 steps, CFGS 7. lora weight : 0. Are you enjoying fine breasts and perverting the life work of science researchers?Set your CFG to 7+. This model imitates the style of Pixar cartoons. 4 denoise for better results). Space (main sponsor) and Smugo. This includes models such as Nixeu, WLOP, Guweiz, BoChen, and many others. 特にjapanese doll likenessとの親和性を意識しています。. Speeds up workflow if that's the VAE you're going to use anyway. ranma_diffusion. Please Read Description Important : Having multiple models uploaded here on civitai has made it difficult for me to respond to each and every comme. Explore thousands of high-quality Stable Diffusion models, share your AI-generated art, and engage with a vibrant community of creators. Civitai Helper. This will give you the exactly same style as the sample images above. He is not affiliated with this. I have a brief overview of what it is and does here. If you gen higher resolutions than this, it will tile the latent space. PEYEER - P1075963156. pth <. You may further add "jackets"/ "bare shoulders" if the issue persists. Highres-fix (upscaler) is strongly recommended (using the SwinIR_4x,R-ESRGAN 4x+anime6B by myself) in order to not make blurry images. Usage. xやSD2. Though this also means that this LoRA doesn't produce the natural look of the character from the show that easily so tags like dragon ball, dragon ball z may be required. 在使用v1. I'm just collecting these.