Image-to-Video workflow in ComfyUI
ComfyUI
Demo summary
A demonstration of the image-to-video workflow in ComfyUI, including uploading a source image, setting crop dimensions, and generating an animated anime scene.
Step-by-step
- Drag and drop the image-to-video workflow file onto the ComfyUI interface
- Download the Clip Vision model and place it in the 'models/clip_vision' folder
- Download the Hunyuan image-to-video model and place it in 'models/diffusion_models'
- Press the R key to refresh the model list
- Select the downloaded models from the dropdown menus in Step 1
- Upload a source image to serve as the first frame in Step 2
- Enter positive and negative prompts in Step 3
- Set the width, height, and frame count in Step 4
- Click Run to generate the video
Options
- Download the FP8 quantized version of the model to save VRAM
- Enable the Easy Cache node using Ctrl+B to speed up generation
- Use the 'crop at center' setting to fit non-16:9 images to output dimensions
- Adjust batch size to generate multiple videos simultaneously
Watch out for
- The full Hunyuan image-to-video model requires 15.5 GB of space
- The Clip Vision model is a mandatory additional download specifically for image-to-video workflows
- Activating the Easy Cache node speeds up generation but sacrifices some quality
Tips
- Refresh the model list after downloading new files to ensure they appear in dropdowns
- Set the video length to 2 seconds (around 50 frames) for faster testing and demos
- Use the FP8 version if you have lower VRAM, as it is roughly half the size of the standard model
Highlights
“Again, it's super simple. You just need to take the image to video workflow which you just downloaded and then drag and drop it onto your interface.”
All demos from “We have a new #1 open-source AI video generator!”
- 7:500:28Image-to-Video action testThe creator demonstrates image-to-video capabilities by uploading a static image and prompting for an intense fight scene in both Hunyuan and Wan models.ComfyUI· Image to Video
- 16:361:56Setting up HunyuanVideo 1.5 in ComfyUIThe video demonstrates how to update ComfyUI and import the HunyuanVideo 1.5 JSON workflow files to create a node-based generation environment.ComfyUI· AI Animation Generator
- 20:151:53Text-to-Video generation in ComfyUIA step-by-step demo of configuring the Hunyuan nodes in ComfyUI, entering a prompt for a 'giant cat', and rendering the final 720p video.ComfyUI· AI Animation Generator
- 22:461:42Upscaling video to 1080p in ComfyUIThe creator demonstrates how to activate and configure the 1080p super-resolution upscaler nodes within the ComfyUI workflow.ComfyUI· AI Video Upscaler
- 24:303:12Image-to-Video workflow in ComfyUICurrentA demonstration of the image-to-video workflow in ComfyUI, including uploading a source image, setting crop dimensions, and generating an animated anime scene.ComfyUI· Image to Video
- 29:151:33Running HunyuanVideo with GGUF (Low VRAM)The video shows how to use the GGUF loader node to run a compressed version of HunyuanVideo 1.5, enabling video generation on GPUs with as little as 6GB of VRAM.ComfyUI· AI Animation Generator
- Watch “We have a new #1 open-source AI video generator!” →
Image to Video
10:194:27Image-to-Video with LTX 2.3The creator demonstrates bringing a static image of a vampire warlord to life by using an image input node and a descriptive prompt to guide the animation and environmental effects.AIKnowledge2Go
3:070:38Image to Video with LTX DirectorThe creator demonstrates dragging an image into the LTX Director timeline and entering a text prompt to generate a video of a woman waving her hand.What Dreams Cost
8:242:33Multi-image to video generation with LTX 2.3 and IC-LoRAThe creator demonstrates how to use a ComfyUI workflow to generate video from multiple reference images using LTX 2.3, explaining how to align image sizes and write descriptions for each reference frame.WuYangfeng
5:244:57Image-to-video generation with Wan 2.2The user demonstrates how to use the Wan 2.2 GGUF model in ComfyUI to animate a static image of a woman based on a detailed text prompt.pixaroma
0:171:00LTX-2 Image-to-Video distilled workflow setupThe demonstrator walks through loading the LTX-2 distilled checkpoint, upscaling models, and Gemma CLIP text encoder, while configuring resolution and frame rates for video generation.LTX
6:300:17Advanced multi-node AI workflowsThe video shows a complex Roboneo setup where an image is generated, passed through an image editing node, and finally converted into a video.Malva AI
10:012:01Image-to-Video generation using Hunyuan 1.5 DistilledThe user demonstrates an I2V workflow in ComfyUI using the Hunyuan 1.5 distilled model, Google's Clip Vision for image encoding, and the 'image to video' node to animate a portrait.AI老腊肉- 7:500:28Image-to-Video action testThe creator demonstrates image-to-video capabilities by uploading a static image and prompting for an intense fight scene in both Hunyuan and Wan models.AI Search
- 24:303:12Image-to-Video workflow in ComfyUICurrentA demonstration of the image-to-video workflow in ComfyUI, including uploading a source image, setting crop dimensions, and generating an animated anime scene.AI Search
23:511:57Animate 3D renders with Wan 2.1The creator walks through a Wan 2.1 video generation workflow in ComfyUI, using the Painterly I2V node to control motion speed and animate a static 3D render.Matt Hallett Visual
5:064:11Animate an image using Wan 2.1 in ComfyUIThe creator demonstrates loading a 'native image to video' workflow in ComfyUI, uploading a source image, and using the Wan 2.1 14B model to generate a high-quality video of a woman walking.Danish Sofi- 10:201:00Generate AI video of a horse with Wan 2.1A second demonstration showing the image-to-video process where a static image of a horse is animated into a walking sequence using the Wan 2.1 model in ComfyUI.Danish Sofi