20 shown - 159 total matches
Github | Civitai New feature: seamless looping ComfyUI Frontend Compatibility Notice Recent ComfyUI frontend updates have introduced significant is...
Create
Important Notice Optimized to work with the latest version of ComfyUI (v0.18.1 + Frontend 1.42.8). The latent upscaler ltx-2.3-spatial-upscaler-x2-...
Create
UPDATE: WAN 2.2 Smooth SVI Pro Workflow V.2 (03/25/2026) Updated the workflow to use the ComfyUI-NAG. I tried to give more control over every video...
Create
<p><span style="color:rgb(230, 73, 128)">Wan 2.7 will become available on the Civitai Generator soon!</span></p><p></p><h2 id="overview">Overview</h2><p><strong>Wan 2.7</strong> is a next-generation video generation model in Alibaba’s Wan series, designed for high-quality text-to-video and image-to-video creation. It builds on earlier versions with strong...
Source context: 0 downloads · Type Checkpoint · Base model Wan Video 2.7
Important Notice Optimized to work with the latest version of ComfyUI (v0.18.1 + Frontend 1.42.8). The latent upscaler ltx-2.3-spatial-upscaler-x2-...
Create
Welcome to my 💫🎦 Friendly LTX-2.3 T2V+I2V+Lipsync ✨ Less mess, more magic Unified Light - Lipsync all-in one version with single-stage video genera...
Create
Note: This is a call to Runninghub's seedance2.0 API. No download is required, as the model won't run if downloaded locally since this was a custom...
Create
Online Workflow： https://www.runninghub.ai/post/2035372598938308610/?inviteCode=rh-v1121 https://www.runninghub.ai/post/2035376634013949954/?invite...
Create
Video tutorial: How to use: 1. Choose whether to use LORA transition. 2. Enter the length of the video (with 24GB of video memory, a 640 can produc...
Create
Models Used model = wan2.1_vace_14B_fp16.safetensors (WAN 2.1 Video Diffusion – core generation model) lora = Wan21_CausVid_14B_T2V_lora_rank32.saf...
Create
<p>Sampler: heunpp2 + linear_quadratic schedule</p><p>seeds_3 + normal is better sampler.</p><p>CFG Scale: 1 – 2，Steps: 8 – 20</p><p>Recommended Speed: CFG: 1, Step: 10</p><p>Recommended Quality: CFG: 1.5, Step: 20</p><p>Prompting Tip: The more detailed and fluent your prompt, the closer the result matches your vision. Please ensure your prompts are well-structured.</p>
Source context: 289 downloads · Type Checkpoint · Base model ZImageTurbo
Restore and upscale any video to 4X and beyond in a single step with ByteDance's revolutionary SeedVR2. Tutorial update for SeedVR2.5 💙 Support our...
Create
Fixes blur instantly. Better than Keep/PMRF. Who it's for: creators who want this pipeline in ComfyUI without assembling nodes from scratch. Not fo...
Create
Extract camera movements and human motions from reference videos for professional video generation Who it's for: creators who want this pipeline in...
Create
Model repo on Hugging Face Hub.
Source context: 0 downloads · 0 likes · Repo nikiakbar/my-models
This workflow implements SAM3 for character masking. It uses looping to process long videos, and while it can theoretically generate infinitely lon...
Create
Turn your low-resolution, low-framerate videos into high-quality, high-FPS videos. **What’s Interpolation?** A method that adds extra frames betwee...
Create
Optimized workflow for running LTX 2.3 (22B Distilled) on 8GB VRAM GPUs (e.g., RTX 3070 Laptop), focusing on stability, memory efficiency, and high...
Create
A simple workflow for Klein family models in the first row was developed for 9b and 4b distilled versions, but it should work for base models with ...
Create
SUPER FAST! 5-second video in 45 seconds! **Who it's for:** creators who want this pipeline in ComfyUI without assembling nodes from scratch. **Not...
Create
