pruna

high-quality text-to-image generation with strong typography and prompt understanding, built with ideogram

ai-powered image upscaling up to 128 megapixels with detail and realism enhancement

edit images using text instructions with multi-image support and pose transfer

lightweight 4b parameter model with excellent speed-to-quality ratio

fast generation with lora support for unique styles and personalized outputs

ultra-fast turbo image generation with minimal latency

fast qwen-based image generation with creativity control

advanced text-to-image generation with optional lora weights and prompt enhancement

fast, efficient text-to-image optimized for rapid prototyping and batch generation

text-to-image and image-to-image generation with custom lora weights from huggingface

advanced text-to-image generation with multiple aspect ratios, speed optimizations, and high-quality outputs

fast image editing with custom lora styles for unique transformations

pruna's flagship fast text-to-image with custom lora style support

pruna's flagship fast text-to-image with multiple aspect ratios and prompt enhancement

fast image editing with text instructions and multi-image support

vace-14b video generation and editing from a prompt, with optional source video, mask and up to 3 reference images for consistent characters.

animate the subject of a reference image with the motion and audio of a source video, at 720p or 1080p.

upscale a video to 720p, 1080p, 2k or 4k, keeping its aspect ratio and audio, with optional frame interpolation up to 60 fps.

talking video from one portrait and uploaded audio or a script on minimax h3. lip sync, 30 voices in 10 languages, 1s to 3 min, 480p to 4k.

video from a prompt plus up to 9 image, 3 video and 3 audio references on minimax h3. consistent characters, motion transfer, 5-15s, 480p to 4k.

text-to-video and first/last-frame image-to-video on minimax h3, 5-15s with generated audio, 480p to 4k, in cost, speed or quality mode.

text-to-video and image-to-video up to 1080p and 20s, with audio conditioning, last-frame control and 24/48 fps. built on ltx-2.

edit videos from text prompts with optional reference images. up to 15s input, standard or draft quality.

replace characters in videos using reference images. preserves motion, timing, camera, and scene.

generate talking head videos from a portrait image with text or audio-driven speech

transform static images into animated videos with text prompts

generate videos directly from text descriptions in 480p or 720p

fast text-to-video and image-to-video in 720p/1080p with audio support