60-second AI short film

Script it, generate every keyframe, then render the clips. The full text-to-video pipeline end to end.

The pipeline

Write the script and shot list, qwen3-32b
Generate 15 keyframes, stable-diffusion-xl
Render 15 clips (~4s each), ltx-video

Fastest card where every stage is a real measurement: NVIDIA B200, 1.9 min for the whole job.

Every GPU, slowest job to fastest

GPU	Total time	Compute	Energy	Basis
NVIDIA B100	1.7 min	1.7 min	n/a	anchored estimate (0/3 stages measured)
NVIDIA B200	1.9 min	85 s	16.03 Wh	all 3 stages measured
NVIDIA GH200 Grace Hopper	2 min	2 min	n/a	anchored estimate (0/3 stages measured)
NVIDIA H100 NVL	2 min	2 min	n/a	anchored estimate (0/3 stages measured)
NVIDIA H800 80GB	2 min	2 min	n/a	anchored estimate (0/3 stages measured)
NVIDIA B300	2.2 min	87 s	14.29 Wh	all 3 stages measured
NVIDIA H100 PCIe	2.4 min	2.4 min	n/a	anchored estimate (0/3 stages measured)
NVIDIA H100 80GB HBM3	2.5 min	2 min	17.46 Wh	all 3 stages measured
NVIDIA RTX PRO 6000 Blackwell Server Edition	2.7 min	2.4 min	19.22 Wh	all 3 stages measured
NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition	2.8 min	2.8 min	n/a	anchored estimate (0/3 stages measured)
NVIDIA H200	3.9 min	2 min	18.03 Wh	all 3 stages measured
NVIDIA A800 80GB	4 min	4 min	n/a	anchored estimate (0/3 stages measured)
NVIDIA A100 40GB SXM4	4 min	3.9 min	6.39 Wh	anchored estimate (2/3 stages measured)
NVIDIA A100 40GB PCIe	4.2 min	4.2 min	n/a	anchored estimate (0/3 stages measured)
NVIDIA RTX PRO 6000 Blackwell Workstation Edition	4.5 min	2.2 min	19.26 Wh	all 3 stages measured
NVIDIA A100 80GB PCIe	4.6 min	4.1 min	18.6 Wh	all 3 stages measured
NVIDIA A100 80GB SXM4	4.7 min	4 min	23.61 Wh	all 3 stages measured
NVIDIA L40S	4.9 min	4.3 min	22.52 Wh	all 3 stages measured
NVIDIA RTX PRO 5000 Blackwell	6.7 min	6.4 min	20.33 Wh	all 3 stages measured
NVIDIA GeForce RTX 4090	7.9 min	6.4 min	30.54 Wh	all 3 stages measured
NVIDIA RTX 5880 Ada Generation	8.6 min	8.6 min	n/a	anchored estimate (0/3 stages measured)
NVIDIA RTX 5000 Ada Generation	9.5 min	9.3 min	27.06 Wh	all 3 stages measured
NVIDIA GeForce RTX 3090 Ti	9.9 min	9.7 min	50.99 Wh	all 3 stages measured
NVIDIA RTX PRO 4000 Blackwell	10.2 min	10.1 min	20.63 Wh	all 3 stages measured
NVIDIA RTX PRO 4500 Blackwell	10.6 min	8.3 min	18.99 Wh	all 3 stages measured
NVIDIA RTX A5000	11.8 min	11.5 min	36.17 Wh	all 3 stages measured
NVIDIA L40	13 min	11.1 min	36.37 Wh	all 3 stages measured
NVIDIA RTX A5500	13.1 min	13.1 min	n/a	anchored estimate (0/3 stages measured)
NVIDIA RTX 4500 Ada Generation	15.1 min	15.1 min	n/a	anchored estimate (0/3 stages measured)
NVIDIA GeForce RTX 3090	15.2 min	13.6 min	57.1 Wh	all 3 stages measured
AMD Radeon RX 7900 XTX	16.1 min	16.1 min	n/a	anchored estimate (0/3 stages measured)
AMD Radeon Pro W7900	18.6 min	18.6 min	n/a	anchored estimate (0/3 stages measured)
AMD Radeon RX 7900 XT	20.7 min	20.7 min	n/a	anchored estimate (0/3 stages measured)
AMD Radeon Pro W7800	24.3 min	24.3 min	n/a	anchored estimate (0/3 stages measured)
AMD Radeon Pro W6800	28.8 min	28.8 min	n/a	anchored estimate (0/3 stages measured)

Cards that can't run this pipeline

Every one of these fails on the same kind of wall, a stage that will not fit in VRAM.

AMD Radeon RX 6700, blocked at "Write the script and shot list" (Qwen3 32B)
AMD Radeon RX 6800, blocked at "Write the script and shot list" (Qwen3 32B)
AMD Radeon RX 6800 XT, blocked at "Write the script and shot list" (Qwen3 32B)
AMD Radeon RX 6900 XT, blocked at "Write the script and shot list" (Qwen3 32B)
AMD Radeon RX 6950 XT, blocked at "Write the script and shot list" (Qwen3 32B)
AMD Radeon RX 7600, blocked at "Write the script and shot list" (Qwen3 32B)
AMD Radeon RX 7700 XT, blocked at "Write the script and shot list" (Qwen3 32B)
AMD Radeon RX 7800 XT, blocked at "Write the script and shot list" (Qwen3 32B)
AMD Radeon RX 9070, blocked at "Write the script and shot list" (Qwen3 32B)
AMD Radeon RX 9070 XT, blocked at "Write the script and shot list" (Qwen3 32B)
GeForce GTX 1080 Ti, blocked at "Write the script and shot list" (Qwen3 32B)
GeForce RTX 4060, blocked at "Write the script and shot list" (Qwen3 32B)
GeForce RTX 4080 Super, blocked at "Write the script and shot list" (Qwen3 32B)
GeForce RTX 5060 Ti, blocked at "Write the script and shot list" (Qwen3 32B)
GeForce RTX 5070, blocked at "Write the script and shot list" (Qwen3 32B)
GeForce RTX 5070 Ti, blocked at "Write the script and shot list" (Qwen3 32B)
GeForce RTX 5080, blocked at "Write the script and shot list" (Qwen3 32B)
Intel Arc A750, blocked at "Write the script and shot list" (Qwen3 32B)
Intel Arc A770 Limited Edition, blocked at "Write the script and shot list" (Qwen3 32B)
Intel Arc B580, blocked at "Write the script and shot list" (Qwen3 32B)
Intel Arc Pro A60, blocked at "Write the script and shot list" (Qwen3 32B)
NVIDIA GeForce GTX 1070 Ti, blocked at "Write the script and shot list" (Qwen3 32B)
NVIDIA GeForce GTX 1080, blocked at "Write the script and shot list" (Qwen3 32B)
NVIDIA GeForce GTX 1660, blocked at "Write the script and shot list" (Qwen3 32B)
NVIDIA GeForce GTX 1660 Super, blocked at "Write the script and shot list" (Qwen3 32B)
NVIDIA GeForce GTX 1660 Ti, blocked at "Write the script and shot list" (Qwen3 32B)
NVIDIA GeForce RTX 2060, blocked at "Write the script and shot list" (Qwen3 32B)
NVIDIA GeForce RTX 2060 Super, blocked at "Write the script and shot list" (Qwen3 32B)
NVIDIA GeForce RTX 2070, blocked at "Write the script and shot list" (Qwen3 32B)
NVIDIA GeForce RTX 2070 SUPER, blocked at "Write the script and shot list" (Qwen3 32B)
NVIDIA GeForce RTX 2080 Founders Edition, blocked at "Write the script and shot list" (Qwen3 32B)
NVIDIA GeForce RTX 2080 Super, blocked at "Write the script and shot list" (Qwen3 32B)
NVIDIA GeForce RTX 2080 Ti Founders Edition, blocked at "Write the script and shot list" (Qwen3 32B)
NVIDIA GeForce RTX 3050, blocked at "Write the script and shot list" (Qwen3 32B)
NVIDIA GeForce RTX 3060, blocked at "Write the script and shot list" (Qwen3 32B)
NVIDIA GeForce RTX 3060 Ti, blocked at "Write the script and shot list" (Qwen3 32B)
NVIDIA GeForce RTX 3070 Founders Edition, blocked at "Write the script and shot list" (Qwen3 32B)
NVIDIA GeForce RTX 3070 Ti, blocked at "Write the script and shot list" (Qwen3 32B)
NVIDIA GeForce RTX 3080, blocked at "Write the script and shot list" (Qwen3 32B)
NVIDIA GeForce RTX 3080 Ti, blocked at "Write the script and shot list" (Qwen3 32B)

…and 18 more.

How these numbers are built

Each stage time is the quantity of work divided by that card's measured throughput for that model, from our own bench. The pipeline is assumed to run batched, every image, then every clip, so each model loads once. Model load time is added where we recorded it; our text-generation runs don't carry a load measurement yet, so pipelines with a language-model stage are slightly optimistic. Nothing here is a single timed run of the whole pipeline, and we don't present it as one.