191
models
Wan 2.5 is Alibaba's high-performance intermediate video generation release, offering meaningful improvements in motion quality, generation speed, and scene complexity handling over the 2.2 series. Available in text-to-video and image-to-video variants, Wan 2.5 supports high-resolution video output with smooth, natural motion synthesis and accurate prompt following. The model shows particular strength in handling scenes with multiple objects and characters, complex camera movements, and nuanced lighting conditions. Wan 2.5 builds on the open-weight foundation of earlier Wan models while incorporating architectural refinements that improve the balance between generation quality and computational efficiency — making it a practical choice for production workflows that need both visual quality and throughput. On Segmind, Wan 2.5 models are available as pay-per-use APIs with no infrastructure management. Use them standalone or chain with other video tools in Segmind Workflows for automated content production pipelines.
Pruna's reference-to-video model, built on MiniMax H3: a prompt plus reference images, videos and audio in, 480p or 768p video with generated audio out, 5 to 15 seconds at 24 fps.
Turn a portrait and speech into a lip-synced talking video, from an audio file or a typed script.
Generate transparent PNGs; edit with up to 10 references.
Generate and edit images with legible text and infographics.
Generate transparent PNGs and edit with 10 reference images.
Bounding-box layout control, native 4K text-to-image.
Image To Image
Text To Image
LLM
LLM
Image To Video
Video To Video
Text To Image
Text To Image
Text To Image
Text To Image
Text To Video
Image To Video
Text To Video
LLM
LLM
LLM
Text To Video
Text To Image
Text To Image
LLM
Text To Audio
Image To Video
Image To Video
Image To Image
Image To Video
Image To Video
Image To Image
Image To Video
LLM
Image To Video
Image To Video
Text To Video
LLM
LLM
Text To Image
Image To Image
Image To Image
Image To Image
Image To Video
Image To Video
Image To Video
Text To Embed
LLM
LLM