on

Can the NVIDIA GeForce RTX 4070 SUPER run AnimateDiff v3 (SD 1.5)?

64 ptsGood (B) · 64 of 100 points: Model quality 15.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 9.1/15

Yes, it runs well

Runs well. At FP16 it needs about 4.7 GB of 12.0 GB usable, with an estimated speed of 38 s.

Best precision
FP16
Memory mode
Everything on GPU
Time per clip
38 s
Output
512×512, 16 frames, 25 steps

Download AnimateDiff v3 (SD 1.5)

Original weights · Hugging Face

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

huggingface.co/guoyww/animatediff-motion-adapter-v1-5-3 (opens in a new tab)

No sign-in needed.

Official repo · GitHub

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

github.com/guoyww/AnimateDiff (opens in a new tab)

git clone https://github.com/guoyww/AnimateDiff

How the B grade is scored

Every result gets up to 100 points from four parts. The points decide the letter grade.

Model qualityEditorial quality tier of the model, scaled by the quantization or precision used.15.8 / 45
Memory fitFull marks when everything sits in GPU or unified memory; fewer when part spills to system RAM.25.0 / 25
SpeedGeneration speed against a 40 tokens/s target for LLMs, or render time against a target for image and video.15.0 / 15
Memory useRewards using the memory you have, so a bigger, better variant beats a tiny one that leaves most memory idle.9.1 / 15
Total64.8 / 10064 ptsGood (B) · 64 of 100 points: Model quality 15.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 9.1/15

Grade scale: S 85+ · A 72+ · B 58+ · C 42+ · D 25+ · F under 25 points.

Every precision on the NVIDIA GeForce RTX 4070 SUPER

Precision Memory needed Available Time per output Memory mode Fit Grade · points Download
FP16 4.7 GB 12.0 GB 38 s Everything on GPU Runs well 64 ptsGood (B) · 64 of 100 points: Model quality 15.8/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 9.1/15 Original weights (opens in a new tab)

Other hardware that runs it

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.