PAN2 ComfyUI Workflow for Text and Image to Video
PAN2 turns text or images into short videos with timed prompts.
PAN2 turns text or images into short videos with timed prompts.
LongCat Avatar turns photos and speech into lip-synced solo or duo videos.
CROWN MiniMax H3 makes videos with stereo audio in four steps.
Swap a person with your character's face, hair, clothes and style.
Use Canny edges to restyle photos while keeping key outlines.
MOSS-Image follows your reference pose while changing subjects, outfits, and scenes.
Replace one to four characters in a still image using separate references.
Generate photos and illustrations from text with Prompt Enhancer.
MiniMax H3 turns your text instructions into targeted image edits.
Create transparent RGBA assets from text. Preview edges before compositing.
Turn one image into 3D splats, GLB meshes, and orbit previews.
P-H3-Image edits your photo with guidance from a reference image.
P-H3-Image turns short prompts into 8MP images in eight steps.
Pika H3 Flex turns two images into video with stereo audio.
H3 turns your ideas into consistent anime scenes with synced sound.
Restyle clips with MiniMax H3. Change lighting, materials, and overall look.
Swap video characters with MiniMax H3, keeping your original audio.
Swap video characters with MiniMax H3 and SAM3 while following the original motion.
MOSS editor: Change lighting, materials, and styles with text or references.
Pose studio gives your characters new poses with adjustable 3D guidance.
Animate your character beside a source video with H3 motion outpainting.
Edit masked areas with MOSS inpainting. Keep your scene consistent.
FastH3 Omni turns reference images into cinematic videos with audio.
Turn text into portraits, food images, and watercolors with Fibo Turbo.
Bria's turbo editor transforms photos with text in just four steps.
Rapid-MOSS turns your text into images in just four sampling steps.
Qwen Turbo: Change scenes, adjust lighting, and replace text with prompts.
Qwen Turbo turns your words into product visuals in eight steps.
Turn text and drawn boxes into images with controlled layouts.
Turn prompts into posters with controlled text and object placement.
MOSS-Image Base turns your words into realistic scenes and poster designs.
MOSS-Image turns your words into scenes, portraits, and product visuals.
Flux 3 Klein edits your photos with text, keeping the surrounding composition intact.
Flux 3 Klein Distilled turns prompts into polished portraits and cinematic scenes fast.
Flux 3 Klein Distilled edits photos with text: change outfits, labels, materials, and lighting.
Flux 3 Klein turns your prompts into polished portraits, landscapes, and concept art.
Turn existing songs into AI covers with new vocals and arrangements guided by the original melody.
Expand image borders into wider scenes, taller portraits, and continuous backgrounds.
Veda-accelerated reference videos: 3x faster, sharper, with synchronized audio.
H3 capture turns your acting into new characters, audio stays intact.
H3 turns references into hard-hitting action videos with native audio.
MiniMax H3 makes seamless long video takes with consistent characters and native audio.
TOTAL CONTROL! Qwen-powered reposing keeps characters consistent in every action.
Qwen 2.1 local edits add or replace details with precision.
Powerful multi-reference editing creates precise scenes from separate images.
Qwen 2.1 face swaps deliver natural faces while keeping every scene.
Qwen Image 2.1 swaps outfits fast with precise, realistic detail.
Qwen 2.1 Edit delivers precise image changes fast.
Qwen Image 2.1 Makes Detailed 2K Images Fast
FastH3 V2 makes smooth videos with audio in just eight steps.
RunComfy is the premier ComfyUI platform, offering ComfyUI online environment and services, along with ComfyUI workflows featuring stunning visuals. RunComfy also provides AI Models, enabling artists to harness the latest AI tools to create incredible art.