Image to Video
This app generates a high quality video with sound. All you need is to upload an input image and write prompt.
About
This ComfyUI workflow turns a single still image into a short video guided by a text prompt. It uses LoadImage to bring in your source frame, passes it to a dedicated Image-to-Video generator node (ID: 770dde0e-f342-49aa-ad1e-184724671c5d), and then encodes the resulting frame sequence with SaveVideo. The generator node conditions on both the input image (as a visual anchor) and your prompt (to suggest motion, style, or scene changes), producing a coherent set of frames that evolve over time.
What you provide
- Reading the workflow
Runs in ComfyUI. This workflow can't run on this page. Open it in Comfy Cloud with everything loaded, or download it for your own ComfyUI.
Try in CloudQuestions & answers
Length is determined by the number of frames and FPS. For example, 48 frames at 12 FPS ≈ 4 seconds. Longer clips require more VRAM and time; increase frames gradually and consider lowering resolution or FPS if you hit memory limits.
Use a conservative prompt and reduce the node’s motion/denoise strength so it deviates less from the source. Also try increasing guidance strength and using a fixed seed. If available, choose a sampler or setting that favors stronger conditioning.
Lower motion/denoise strength, reduce resolution, and try a different seed. You can also decrease the number of frames or use a slightly higher guidance value. Subtle, specific prompts often produce more stable motion than broad or conflicting ones.
SaveVideo can assemble the frames into a video container like MP4 or WebM (options depend on your node’s settings and installed encoders). Match FPS between the generator and SaveVideo to avoid timing issues.