20 shown - 255 total matches
<p>Major alternative merge, changes in overall style, lighting and prompt adherence.</p>
Source context: 234 downloads · Type Checkpoint · Base model Illustrious
Note: If you have ANY issues with nodes not downloading, read the notes or reach out. There's nothing that special about any of them that aren't co...
Create
This uses a lora to outpaint extended black frames. It works really well and I've gotten better results than the wan workflow I posted. You will ne...
Create
<ul><li><p><a rel="ugc" href="https://civitai.com/models/2458426?modelVersionId=2836417">Anima preview 3</a> based.</p></li><li><p>Added 1792px resolution dataset for learning. (multi-resolution datasets with 1280px,1536px and 1792px)</p></li></ul>
Source context: 241 downloads · Type Checkpoint · Base model Anima
全身换装
服装提取
This is the workflow that was made with Lustify V8 model in mind, although other models would obviously work with it. Please, read all the notes I'...
<p>マージに使用しているモデルのバージョンアップを反映&一部使用モデル変更</p><p>Reflected the version upgrade of the model used for merging and some models used have been changed</p>
<p>New instructions for v8. Workflow in "Training Data" download. The workflow is for seed hunting efficiently - the key is to use your brain to quickly curate the AI generations at low resolution.</p><p>The model is basically tuned for ddpm at cfg 1, 20 steps. However, Euler a works almost as well, and LCM is particularly good as a first pass for architecture, strong shapes, followed by a ddpm pass to add more detail.</p><p>If you want to use cfg > 1 then add the cfg norm node in comfyui to stop burn!</p><p>You don't need to add masterpiece, high score, great score, absurdres to the end of the prompt - it is tuned to work without it. Only add it if you want more anime style.</p>
Source context: 411 downloads · Type Checkpoint · Base model SDXL 1.0
a workflow that use Ultimate SD Upscale to upscale with anima model. this is just a example plz feel free to replace node to the version u are usin...
Create
<p>EH ZIT 2.0 Codename: "Firestarter".</p><p> Much better at details, composition, aesthetics than V 1.0. and better anatomy. Better at NSFW. Overall IQ vastly improved. </p>
Source context: 14 downloads · Type Checkpoint · Base model ZImageTurbo
<div data-youtube-video><iframe width="640" height="480" allowfullscreen="true" autoplay="false" disablekbcontrols="false" enableiframeapi="false" endtime="0" ivloadpolicy="0" loop="false" modestbranding="false" origin playlist src="https://www.youtube.com/embed/dfEZfvcQ1vU" start="0"></iframe></div><p></p>
<p><span style="color:rgb(250, 82, 82)"><strong>Recommend VAE:</strong></span></p><p><a target="_blank" rel="ugc" href="https://huggingface.co/Owen777/UltraFlux-v1/blob/main/vae/diffusion_pytorch_model.safetensors">https://huggingface.co/Owen777/UltraFlux-v1/blob/main/vae/diffusion_pytorch_model.safetensors</a></p><p><span style="color:rgb(250, 176, 5)"><...
Source context: 458 downloads · Type Checkpoint · Base model ZImageTurbo
<p><em>I'm working on two models under the title LusicDreamer: an anime-style model and a semi-realistic model. While I plan to integrate them in the future, I'm currently conducting extensive experiments with both models through full fine-tuning.</em></p><p><em>The latest version of the anime model is </em><a target="_blank" rel="ugc" href="https://civit...
Source context: 164 downloads · Type Checkpoint · Base model ZImageBase
<div data-youtube-video><iframe width="640" height="480" allowfullscreen="true" autoplay="false" disablekbcontrols="false" enableiframeapi="false" endtime="0" ivloadpolicy="0" loop="false" modestbranding="false" origin playlist src="https://www.youtube.com/embed/GjbU7z0EuX8?rel=1" start="0"></iframe></div><p>Online Workflow：</p><p><a target="_blank" rel="...
ZRune Echo Driver 是一张基于 EchoMimic V2的workflow，主要用于本地驱动视频口播、半身人物动作和音频驱动视频生成。定位是展示用分享，不是零依赖可复现整包。 适用方向： - 本地驱动视频口播 - 半身人物动作视频 - 音频驱动人像视频 - EchoMimic ...
<p>A merge of Simple Cuteness + Mergestein-Reborn + LoRas and a very little of <a target="_blank" rel="ugc" href="https://civitai.com/models/2237480?modelVersionId=2820738">Mugen 0.5</a> just to make the Mugen VAE works, i don't know if it has the benefits of it due to merging an SD3 model with SDXL but it generates things without problems (with the few test i made) so... It's a true Mergestein Model now >:)</p><p>Due to being a test model, it can have problems and i don't know if Mugen database works but it generates the ones i like, so you need to test it, i just made this one cuz i was bored, so don't expect an excellent quality model.</p>
Flux2App is my personal simple APP MODE Conversion of the Flux.2 DEV Comfyui Template using the same models. I used this to make my ongoing band/br...
Create
<h3 id="i.-introduction"><strong>I. Introduction</strong></h3><p><strong>AnimaYume</strong> is a <strong>text-to-image</strong> model fine-tuned from <a target="_blank" rel="ugc" href="https://huggingface.co/circlestone-labs/Anima"><strong>Anima</strong></a>, a high-quality anime-style image generation model developed by <a target="_blank" rel="ugc" href=...
Source context: 3405 downloads · Type Checkpoint · Base model Anima
Smoking cigarettes with style
Create
