image-to-video AI Models

🤖 Model 🖼️ → 🎥

jichengdu/wan-i2v

Generates videos from input images with text prompts. Supports 720p video generation with up to 81 frames at configurabl...

🖼️ → 🎥 • image-to-video • 342 runs

🤖 Model 🖼️ → 🎥

fofr/frames-to-video

Assemble a sequence of images into a video at a specified frame rate. Accepts a ZIP of frames or a list of frame images...

🖼️ → 🎥 • image-to-video • video-post-processing • 1.6K runs

🤖 Model 🖼️ → 🎥

thudm/cogvideox-i2v

Generate short videos from a single image, guided by an optional text prompt. Animate stills into coherent motion while...

🖼️ → 🎥 • image-to-video • 1.1K runs

🤖 Model 📝 → 🎥

pranavsekhar/nano-banana-slideshow

Generate slideshow videos from a text prompt or an input image. Produce a base scene and iterate foreground variations,...

📝 → 🎥 • text-to-video • image-to-video • slideshow • 19 runs

🤖 Model 📝 → 🎥

google/veo-3

Generates videos with synchronized audio from text prompts. Produces cinematic quality videos with realistic physics sim...

📝 → 🎥 • text-to-video-with-audio • image-to-video-with-audio • lipsync • 235.6K runs

🤖 Model 🖼️ → 🎥

lucataco/seine

Generate videos from a single image. Animate static photos using a short-to-long video diffusion method for generative t...

🖼️ → 🎥 • image-to-video • 13.8K runs

🤖 Model 📝 → 🎥

luma/ray-2-540p

Generate 5–9s 540p videos from a text prompt. Control camera motion using concepts such as pan_left, pan_right, zoom_in,...

📝 → 🎥 • text-to-video • 10.3K runs

🤖 Model 📝 → 🎥

zsxkib/pyramid-flow

Generate short videos from text prompts or animate a single image into a video. Control clip length (1–10 s, with a 1–3...

📝 → 🎥 • text-to-video • image-to-video • 9.0K runs

🤖 Model 📝 → 🎥

haiper-ai/haiper-video-2

Generate short videos from text prompts or a reference image. Accepts a prompt and optional frame image to guide motion,...

📝 → 🎥 • text-to-video • image-to-video • 10.8K runs

🤖 Model 📝 → 🎥

nightmareai/cogvideo

Generate short videos from a text prompt. Optionally condition on a starting image to guide the scene. Uses a two-stage...

📝 → 🎥 • text-to-video • image-to-video • 32.8K runs

🤖 Model 📝 → 🎥

prunaai/vace-1.3b

Generate and edit videos from a text prompt, reference images, or a source video. Input a prompt to synthesize new clips...

📝 → 🎥 • text-to-video • video-editing • image-to-video • 649 runs

🤖 Model 📝 → 🎥

wan-video/wan-2.2-5b-fast

Generates videos from text prompts or input images, optimized for fast inference speed. Supports both text-to-video and...

📝 → 🎥 • text-to-video • image-to-video • 627.9K runs

🤖 Model 🖼️ → 🎥

lucataco/wan2.1-4step

Animates static images into videos using text prompts to control motion and animation. Utilizes a distilled version of W...

🖼️ → 🎥 • image-to-video • video-lora-training • 5.0K runs

🤖 Model 🖼️ → 🎥

lucataco/wan-2.2-first-last-frame

Generate video transitions between two input images using 8-step inference with Lightning LoRA. Takes a start image and...

🖼️ → 🎥 • image-to-video • video-frame-interpolation • 90.1K runs

🤖 Model 🖼️ → 🎥

lucataco/wan2.1-i2v-lora

Generate videos from input images using the Wan2.1 14B model with LoRA fine-tuning support. Takes an input image, text p...

🖼️ → 🎥 • image-to-video • video-lora-training • 742 runs

🤖 Model 🖼️ → 🎥

douwantech/musepose

Generates videos of virtual humans by transferring poses from an input video to a reference person image. Takes a refere...

🖼️ → 🎥 • image-to-video • pose-estimation • video-consistent-character-generation • 1.0K runs

🤖 Model 📝 → 🎥

zsxkib/wan-cakeify

Generate short videos in a CAKEIFY style where everyday objects appear as hyper-realistic cakes, from a text prompt or a...

📝 → 🎥 • text-to-video • image-to-video • cake • 127 runs

🤖 Model 📝 → 🎥

fofr/wan-14b-cyberpunk-realistic

Generate cyberpunk-themed videos from text prompts, optionally animating a starting image. Output short clips (1–5 secon...

📝 → 🎥 • text-to-video • image-to-video • cyberpunk • 76 runs

🤖 Model 📝 → 🎥

fofr/wan-14b-my-subconscious

Generate short videos (1–5 seconds) from text prompts, with optional image-to-video starting frame. Control frame count...

📝 → 🎥 • text-to-video • image-to-video • lora • 74 runs

🤖 Model 🖼️ → 🎥

douwantech/musev

Generates videos from image input using MuseV technology for image-to-video conversion.

🖼️ → 🎥 • image-to-video • 434 runs