Video models · Zhipu AI

SCAIL-2 14B (character animation)

Name: SCAIL-2 14B (character animation)
Author: Zhipu AI

Backbone: 16.4B
Native output: 896×512, 81 frames
Default steps: 40
License: mit
Released: 2026-06

How to run it

Original weights · Hugging Face

Full-precision files from Zhipu AI, for fine-tuning, vLLM, Transformers, Diffusers or ComfyUI.

huggingface.co/zai-org/SCAIL-2 (opens in a new tab)

No sign-in needed.

Official repo · GitHub

Reference code, inference scripts and docs from Zhipu AI. The weights themselves download from Hugging Face.

github.com/zai-org/SCAIL-2 (opens in a new tab)

git clone https://github.com/zai-org/SCAIL-2

Links checked 5 days ago against Hugging Face, Ollama and GitHub.

Apps that run SCAIL-2 14B (character animation)

Our pick for each kind of computer, assuming the model fits in its memory. Pick your own GPU or device in the Model Finder for an exact answer.

Mac (Apple silicon)

ComfyUI

Runs this model with built-in or popular custom nodes; GGUF files load with ComfyUI-GGUF.

Also good:

Windows PC, NVIDIA GPU

ComfyUI

Runs this model with built-in or popular custom nodes; GGUF files load with ComfyUI-GGUF.

Also good:

Linux, NVIDIA or AMD GPU

ComfyUI

Runs this model with built-in or popular custom nodes; GGUF files load with ComfyUI-GGUF.

Also good:

App	Type	Opens it as	Systems	Engine	Start
ComfyUI	Desktop app	Built-in support	macOSWindowsLinux	PyTorch, GGUF via ComfyUI-GGUF	Get ComfyUI
SwarmUI	Desktop app	Built-in support	macOSWindowsLinux	ComfyUI	Get SwarmUI
SD.Next	Desktop app	Built-in support	macOSWindowsLinux	PyTorch	Get SD.Next
Stability Matrix	Desktop app	Built-in support	macOSWindowsLinux	installs ComfyUI, Forge, InvokeAI, SwarmUI, SD.Next or Fooocus	Get Stability Matrix

Which apps can open a model depends on the files published for it: GGUF for llama.cpp-based apps, MLX for Apple’s engine, the original weights for vLLM and SGLang. Compare every app.

Memory needed

Peak GPU memory at the native output size. Offloading moves the text encoder, or the whole pipeline, to system RAM between steps.

Precision	Everything on GPU	Text encoder offloaded	Sequential offload	Download
`FP16`	52.5 GB	39.8 GB	18.3 GB	Original weights (opens in a new tab)
`FP8`	29.8 GB	23.4 GB	12.5 GB	Original weights (opens in a new tab)

Components

Backbone: 16.4B
VAE: 0.127B
umT5-XXL: 5.7B
CLIP ViT-H (image): 0.63B

Best hardware for SCAIL-2 14B (character animation)

The least expensive GPU in our catalog that runs it without offloading is the AMD Radeon RX 7600 XT (launch price $329) at FP8.

Quality	Hardware	Quant	Memory	Speed	Runs
78Great quality (A) · 78 of 100: how capable the model is at FP8, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking.	NVIDIA B200	`FP8`	29.8 GB / 180 GB	11.0 min	Runs well
80Great quality (A) · 80 of 100: how capable the model is at FP16, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking.	NVIDIA RTX PRO 6000 Blackwell	`FP16`	52.5 GB / 96.0 GB	14.7 min	Slow
78Great quality (A) · 78 of 100: how capable the model is at FP8, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking.	NVIDIA GeForce RTX 5090	`FP8`	29.8 GB / 32.0 GB	15.1 min	Slowtight fit
80Great quality (A) · 80 of 100: how capable the model is at FP16, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking.	AMD Ryzen AI Max+ 395 (128 GB)	`FP16`	52.5 GB / 96.0 GB	38.4 min	Slow
78Great quality (A) · 78 of 100: how capable the model is at FP8, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking.	NVIDIA RTX Spark N1X (6144-core GPU) (128 GB)	`FP8`	29.8 GB / 102 GB	39.7 min	Slow
78Great quality (A) · 78 of 100: how capable the model is at FP8, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking.	NVIDIA GB10 (128 GB)	`FP8`	29.8 GB / 115 GB	37.5 min	Slow
80Great quality (A) · 80 of 100: how capable the model is at FP16, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking.	NVIDIA GeForce RTX 4090	`FP16`	18.3 GB / 24.0 GB	26.0 min	SlowCPU offload
80Great quality (A) · 80 of 100: how capable the model is at FP16, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking.	AMD Radeon RX 7900 XTX	`FP16`	18.3 GB / 24.0 GB	29.0 min	SlowCPU offload
78Great quality (A) · 78 of 100: how capable the model is at FP8, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking.	AMD Radeon RX 9070 XT	`FP8`	12.5 GB / 16.0 GB	31.0 min	SlowCPU offload
78Great quality (A) · 78 of 100: how capable the model is at FP8, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking.	NVIDIA GeForce RTX 5080	`FP8`	12.5 GB / 16.0 GB	31.2 min	SlowCPU offload

Check it on your own hardware

Estimates come from published hardware specs and our open formulas, not from running the model on your machine. Real speed varies with runtime, drivers and settings. Numbers marked “Measured” come from a linked benchmark.