Model reference · open weights
SkyReels-T2V-720P is an open-weight video model from Skywork. SkyReels-V2-T2V-14B-720P (FP32) weighs 40.4 GB; the smallest configuration that runs it is RTX 5090 32 GB.
For self-hosting, compare this build's requirements below with the GPU you plan to rent.
Summary of the Skywork/SkyReels-V2-T2V-14B-720P model card, 2026-10-01
What it is
| Released by | Skywork |
|---|---|
| Released | 2025-04-18 |
| Parameters | 14.3B |
| VRAM | 40.4 GB for the weights |
What it runs on
| Card | Weights | Memory |
|---|---|---|
| RTX 3060 12 GB … RTX 4090 24 GB | does not fit | |
| RTX 5090 32 GB | tight (encoders offloaded) | 31.0 GB |
| L40S 48 GB | tight | 44.0 GB |
| A100 80 GB | fits | 78.2 GB |
| H100 80 GB | fits | 78.1 GB |
| RTX PRO 6000 Blackwell 96 GB | fits | 93.8 GB |
| DGX Spark (GB10) 128 GB unified | fits | 107 GB |
| H200 141 GB | fits | 138 GB |
| B200 180 GB | fits | 176 GB |
Running it yourself
Rent a machine by the hour. ComfyUI is installed on it. Open ComfyUI through the tunnel and load the workflow from the model's card on Hugging Face; choose this model's file in its loader.
# on your rented machine (the ssh line is on its page in the console)
# get REPO FILE FOLDER: one file into /workspace/models/FOLDER, where ComfyUI loads it from
get() { hf download "$1" "$2" --local-dir /workspace/hf-files && mkdir -p "/workspace/models/$3" && mv "/workspace/hf-files/$2" "/workspace/models/$3/$4"; }
# the model (7.1 GB)
get Skywork/SkyReels-V2-T2V-14B-720P diffusion_pytorch_model-00006-of-00006.safetensors diffusion_models
start-comfyui# on your computer, in a second terminal: ComfyUI in your browser at http://localhost:8188
# HOST, PORT and BOOKING are your machine's, from its page in the console
ssh -o HostKeyAlias=axforge-BOOKING -o StrictHostKeyChecking=accept-new -L 8188:localhost:8188 dev@HOST -p PORT