SkyReels-V1-Hunyuan-I2V

Model overview

SkyReels-V1-Hunyuan-I2V is published by Skywork as an image-to-video model. Safetensors metadata reports 12,821,209,152 parameters, and the tags identify diffusers with base_model tencent/HunyuanVideo. According to the model card, it was fine-tuned on on the order of 10M film and television clips and this repo holds the Diffusers-format Image-to-Video weights.

Recorded capabilities

Use cases in the source record

• Image-to-video generation workflows using the publisher-documented Diffusers weights and inference code.
• Human-centric clip experiments building on the publisher-described facial-animation and cinematic-lighting focus, subject to independent validation.

Limitations and unknowns

• No license value was extracted from this record.
• No architecture or model-type values were extracted from this record.
• No evaluation results were extracted from this record.
• Publisher performance and quality claims, including facial-expression counts and cinematic-quality descriptions, come from the model card and were not independently verified.
• Provider state is historical snapshot data, not independently refreshed current availability.

Source and provenance

Source: Skywork/SkyReels-V1-Hunyuan-I2V

Captured: Unknown. Processed: 2026-09-07T19:35:16.074894+00:00.

Skyreels V1: Human-Centric Video Foundation Model 🌐 Github · 👋 Playground · 💬 Discord This repo contains Diffusers-format model weights for SkyReels V1 Image-to-Video models. You can find the inference code on our github repository SkyReels-V1 . Introduction SkyReels V1 is the first and most advanced open-source human-centric video foundation model. By fine-tuning HunyuanVideo on O(10M) high-quality film and television clips, Skyreels V1 offers three key advantages: Open-Source Leadership : Our Text-to-Video model achieves state-of-the-art (SOTA) performance among open-source models, comparable to proprietary models like Kling an…