CGCan I Generate?
ComfyUI · Local image & video models · 100% private

Can I generateimages and videoon this machine?

We read your GPU through your browser, then check it against every local image and video model ComfyUI supports — FLUX, SDXL, SD 3.5, Wan 2.2, HunyuanVideo, LTX-Video, Mochi, Qwen-Image and more. No sign-ups. No uploads. Just an answer.

Reading hardware…
GPU not auto-detected
VRAM
Bandwidth
System RAM
16 GB
estimated
CPU cores
Pick a GPU aboveto score every model against your specific hardware. Without that, you’re just looking at the catalog.
Image

Stable Cascade

Stability AI · 5.9B · 2024
5
F
Too heavyFP8 · ~6.5 GB
VRAM headroomInfinity% used · ~0.0 steps/s proxy

3-stage cascade (Würstchen architecture). Strong prompt adherence, lighter than its 5.9B suggests.

1024×102413 GB disk16 GB RAM ✓Stability AI Non-Commercial
Image

Z-Image Turbo

Tongyi Lab · 6B · 2025
5
F
Too heavyFP8 · ~8.0 GB
VRAM headroomInfinity% used · ~0.0 steps/s proxy

Distilled few-step model. FP16 fits comfortably in 16GB. Apache-licensed.

1024×1024fast14 GB disk16 GB RAM ✓Apache 2.0
ImageMost popular community model

Stable Diffusion XL

Stability AI · 3.5B · 2023
4
F
Too heavyQ4 GGUF · ~3.5 GB
VRAM headroomInfinity% used · ~0.0 steps/s proxy

The workhorse. Sharp 1024px output, huge fine-tune ecosystem (Pony, Illustrious, Juggernaut).

1024×10247 GB disk16 GB RAM ✓CreativeML Open RAIL++-M
Image

SDXL Turbo

Stability AI · 3.5B · 2023
4
F
Too heavyFP8 · ~5.0 GB
VRAM headroomInfinity% used · ~0.0 steps/s proxy

1-step distilled SDXL. Generates in under a second on midrange GPUs. Lower fidelity than full SDXL.

512×512real-time7 GB disk16 GB RAM ✓Stability AI Non-Commercial
Edit

OmniGen 2

BAAI · 3.8B · 2025
4
F
Too heavyFP8 · ~6.0 GB
VRAM headroomInfinity% used · ~0.0 steps/s proxy

Unified text-to-image and image-editing model. One model handles generate, edit, compose.

1024×102411 GB disk16 GB RAM ✓MIT
Video

CogVideoX-5B

THUDM (Tsinghua) · 5B · 2024
4
F
Too heavyQ4 GGUF · ~5.5 GB
VRAM headroomInfinity% used · ~0.0 steps/s proxy

5B T2V/I2V from Tsinghua. Mid-range hardware target. 6-second clips at 720p.

720p · 6s16 GB disk16 GB RAM ✓CogVideoX (open)
Image

Stable Diffusion 3 Medium

Stability AI · 2B · 2024
3
F
Too heavyFP8 · ~4.0 GB
VRAM headroomInfinity% used · ~0.0 steps/s proxy

MMDiT architecture with triple text encoders. Better text rendering than SDXL.

1024×102411 GB disk16 GB RAM ✓Stability AI Community
Image

Stable Diffusion 3.5 Medium

Stability AI · 2.5B · 2024
3
F
Too heavyFP8 · ~5.0 GB
VRAM headroomInfinity% used · ~0.0 steps/s proxy

Improved 3.5 generation with better composition and aesthetics than SD3 Medium.

1024×102412.5 GB disk16 GB RAM ✓Stability AI Community
Image

Lumina Image 2.0

Alpha-VLLM · 2.6B · 2025
3
F
Too heavyFP8 · ~4.5 GB
VRAM headroomInfinity% used · ~0.0 steps/s proxy

Compact next-gen DiT with strong photographic realism. Apache-licensed for commercial use.

1024×102412 GB disk16 GB RAM ✓Apache 2.0
Video

LTX-Video

Lightricks · 2B · 2024
3
F
Too heavyFP8 · ~7.0 GB
VRAM headroomInfinity% used · ~0.0 steps/s proxy

Realtime-capable video model. Generates faster than playback on a 4090. The speed champion.

768×512real-time11 GB disk16 GB RAM ✓Lightricks Open License
Image

Hunyuan-DiT

Tencent · 1.5B · 2024
2
F
Too heavyFP8 · ~4.0 GB
VRAM headroomInfinity% used · ~0.0 steps/s proxy

Bilingual (Chinese + English) DiT. Strong at Chinese text rendering, light to run.

1024×102411 GB disk16 GB RAM ✓Tencent Hunyuan Community
Video

Stable Video Diffusion

Stability AI · 1.5B · 2023
2
F
Too heavyFP8 · ~6.0 GB
VRAM headroomInfinity% used · ~0.0 steps/s proxy

Image-to-video, ~14–25 frames at 576×1024. The original consumer-friendly local video model.

576×1024 · 25 frames10 GB disk16 GB RAM ✓Stability AI Non-Commercial
Video

Wan 2.1 T2V 1.3B

Alibaba · 1.3B · 2025
2
F
Too heavyFP8 · ~5.5 GB
VRAM headroomInfinity% used · ~0.0 steps/s proxy

Tiny T2V. The most compatible video model — fits on 8GB GPUs. Apache-licensed.

480p9 GB disk16 GB RAM ✓Apache 2.0
Image

Stable Diffusion 1.5

Stability AI / RunwayML · 0.86B · 2022
1
F
Too heavyFP8 · ~1.2 GB
VRAM headroomInfinity% used · ~0.0 steps/s proxy

The classic. Tiny, fast, runs on almost anything. Massive ecosystem of LoRAs and fine-tunes.

512×512very fast4.5 GB disk8 GB RAM ✓CreativeML Open RAIL-M
Image

Stable Diffusion 2.1

Stability AI · 0.86B · 2022
1
F
Too heavyFP8 · ~1.4 GB
VRAM headroomInfinity% used · ~0.0 steps/s proxy

Successor to SD 1.5 with native 768px training. Smaller community than 1.5 but still light on hardware.

768×768very fast5.5 GB disk8 GB RAM ✓CreativeML Open RAIL++-M
Image

PixArt-Σ

PixArt-α team · 0.6B · 2024
1
F
Too heavyFP8 · ~4.0 GB
VRAM headroomInfinity% used · ~0.0 steps/s proxy

Featherweight 0.6B DiT with T5-XXL encoder. Beautiful 4K output for the param count.

Up to 4K11.5 GB disk16 GB RAM ✓OpenRAIL++
Image

Stable Diffusion 3.5 Large

Stability AI · 8B · 2024
0
F
Too heavyQ4 GGUF · ~8.0 GB
VRAM headroomInfinity% used · ~0.0 steps/s proxy

Stability's flagship 8B MMDiT. Sharp text, strong composition. Triple text encoder (CLIP-L, CLIP-G, T5-XXL).

1024×102420 GB diskRAM tight · −15Stability AI Community
Image

AuraFlow v0.3

Fal.ai · 6.8B · 2024
0
F
Too heavyFP8 · ~9.5 GB
VRAM headroomInfinity% used · ~0.0 steps/s proxy

Truly open-source flow-matching model. The largest fully Apache-licensed image model.

1024×102416 GB diskRAM tight · −15Apache 2.0
Image

FLUX.1 schnell

Black Forest Labs · 12B · 2024
0
F
Too heavyQ4 GGUF · ~7.0 GB
VRAM headroomInfinity% used · ~0.0 steps/s proxy

4-step distilled FLUX. The fastest way to get FLUX-tier quality. Apache-licensed.

1024×1024fast33 GB diskRAM tight · −15Apache 2.0
ImageFlagship FLUX

FLUX.1 dev

Black Forest Labs · 12B · 2024
0
F
Too heavyQ4 GGUF · ~7.0 GB
VRAM headroomInfinity% used · ~0.0 steps/s proxy

The model to beat. State-of-the-art prompt adherence and photorealism. Hungry but worth it.

1024×102433 GB diskRAM tight · −15FLUX.1 Non-Commercial
Edit

FLUX.1 Kontext dev

Black Forest Labs · 12B · 2025
0
F
Too heavyQ4 GGUF · ~7.5 GB
VRAM headroomInfinity% used · ~0.0 steps/s proxy

Image editing variant of FLUX. Reference image + prompt → edited result.

1024×102433 GB diskRAM tight · −15FLUX.1 Non-Commercial
Image

HiDream-I1

HiDream-ai · 17B (8.5B active) · 2025
0
F
Too heavyQ4 GGUF · ~11.0 GB
VRAM headroomInfinity% used · ~0.0 steps/s proxy

Hybrid DiT + MoE. Beats Flux on several benchmarks. MIT-licensed for any use.

1024×102438 GB diskRAM tight · −15MIT
Image

Qwen-Image

Alibaba · 20B · 2025
0
F
Too heavyQ4 GGUF · ~14.0 GB
VRAM headroomInfinity% used · ~0.0 steps/s proxy

20B MMDiT from Alibaba. Best-in-class text rendering — handles paragraphs of text in images.

1328×132845 GB diskRAM low · −25Apache 2.0
Edit

Qwen-Image-Edit

Alibaba · 20B · 2025
0
F
Too heavyQ4 GGUF · ~14.0 GB
VRAM headroomInfinity% used · ~0.0 steps/s proxy

Edit variant of Qwen-Image. Replace, add, restyle objects via natural prompts.

1328×132845 GB diskRAM low · −25Apache 2.0
Image

Hunyuan Image 2.1

Tencent · 17B · 2025
0
F
Too heavyQ4 GGUF · ~11.0 GB
VRAM headroomInfinity% used · ~0.0 steps/s proxy

Tencent's 17B image flagship. Strong at composition and Chinese text.

1024×102436 GB diskRAM tight · −15Tencent Hunyuan Community
Image84B MoE giant

Hunyuan Image 3

Tencent · 84B (13B active) · 2025
0
F
Too heavyQ4 GGUF · ~32.0 GB
VRAM headroomInfinity% used · ~0.0 steps/s proxy

Massive 84B MoE image model with 13B active. Quality rivals closed-source flagships. Needs serious hardware.

1024×1024180 GB diskRAM low · −25Tencent Hunyuan Community
ImageNext-gen FLUX

FLUX.2 dev

Black Forest Labs · 32B · 2025
0
F
Too heavyQ4 GGUF · ~22.0 GB
VRAM headroomInfinity% used · ~0.0 steps/s proxy

Successor to FLUX.1 dev. Higher fidelity, longer context. Heavy hardware required.

1024×102472 GB diskRAM low · −25FLUX.2 Non-Commercial
Image

ERNIE-Image

Baidu · 10B · 2025
0
F
Too heavyFP8 · ~12.0 GB
VRAM headroomInfinity% used · ~0.0 steps/s proxy

Baidu's 10B image model. Strong at Chinese prompts and stylized output.

1024×102422 GB diskRAM tight · −15Baidu Community
Edit

HiDream-E1.1

HiDream-ai · 17B (8.5B active) · 2025
0
F
Too heavyQ4 GGUF · ~11.0 GB
VRAM headroomInfinity% used · ~0.0 steps/s proxy

Editing variant of HiDream-I1. Same MoE backbone tuned for image editing.

1024×102436 GB diskRAM tight · −15MIT
Video

Wan 2.1 T2V 14B

Alibaba · 14B · 2025
0
F
Too heavyQ4 GGUF · ~12.0 GB
VRAM headroomInfinity% used · ~0.0 steps/s proxy

Full-size Wan T2V. Strong motion, 720p output. Quantization makes it viable down to 12GB.

720p30 GB diskRAM tight · −15Apache 2.0
Video

Wan 2.1 I2V 14B

Alibaba · 14B · 2025
0
F
Too heavyQ4 GGUF · ~12.0 GB
VRAM headroomInfinity% used · ~0.0 steps/s proxy

Image-to-video flagship. Best open I2V motion in early 2025.

720p30 GB diskRAM tight · −15Apache 2.0
VideoBest open video < 8B

Wan 2.2 TI2V 5B

Alibaba · 5B · 2025
0
F
Too heavyQ4 GGUF · ~7.0 GB
VRAM headroomInfinity% used · ~0.0 steps/s proxy

Unified text + image to video. Best-in-class T2V/I2V at 5B. Fits on a 24GB GPU at FP16.

720p13 GB diskRAM tight · −15Apache 2.0
Video

Wan 2.2 T2V A14B (MoE)

Alibaba · 27B (14B active) · 2025
0
F
Too heavyQ4 GGUF · ~18.0 GB
VRAM headroomInfinity% used · ~0.0 steps/s proxy

MoE flagship — 27B total / 14B active. Top open-video quality.

720p56 GB diskRAM low · −25Apache 2.0
Video

LTX-2

Lightricks · 8B · 2026
0
F
Too heavyDistilled FP8 · ~12.0 GB
VRAM headroomInfinity% used · ~0.0 steps/s proxy

Successor to LTX-Video. 4K-capable on high-end hardware. Distilled variants run on 12GB.

1080p–4K28 GB diskRAM tight · −15Lightricks Open License
Video

HunyuanVideo

Tencent · 13B · 2024
0
F
Too heavyQ4 GGUF · ~12.0 GB
VRAM headroomInfinity% used · ~0.0 steps/s proxy

13B T2V — closest open rival to Sora at release. Slow but cinematic.

720p50 GB diskRAM tight · −15Tencent Hunyuan Community
VideoConsumer-friendly Hunyuan

HunyuanVideo 1.5

Tencent · 8.3B · 2025
0
F
Too heavyQ4 GGUF · ~9.0 GB
VRAM headroomInfinity% used · ~0.0 steps/s proxy

Lighter, sharper successor. 8.3B params, 14GB minimum, runs on consumer GPUs.

720p22 GB diskRAM tight · −15Tencent Hunyuan Community
Video

Mochi 1

Genmo · 10B · 2024
0
F
Too heavyQ4 GGUF · ~9.0 GB
VRAM headroomInfinity% used · ~0.0 steps/s proxy

10B asymmetric DiT. Ambitious motion. Apache-licensed for any use.

480p–720p22 GB diskRAM tight · −15Apache 2.0
Video

Pyramid Flow

Pyramid Flow team · 2B · 2024
0
F
Too heavyFP8 · ~8.5 GB
VRAM headroomInfinity% used · ~0.0 steps/s proxy

Pyramidal flow-matching for efficient long videos. Strong T2V quality at 2B.

768p · 10s11 GB diskRAM tight · −15MIT
Methodology

No magic. Just math you can audit.

We compute every model’s VRAM at FP16, FP8, and Q4 GGUF; add a 10% KV-cache safety margin and a 0.5 GB runtime overhead; then check fit against your GPU. Speed comes from a bandwidth-bound model (steps/s ≈ bandwidth ÷ model size × efficiency). All client-side.

See the formulas
Models tracked
38
GPUs in DB
50+
Apple chips
14
Quant levels
FP16 · FP8 · Q4