Versions Compared

Old Version 91

changes.mady.by.user Oleksandr Liutyi

Saved on

compared with

New Version 92

changes.mady.by.user Oleksandr Liutyi

Saved on

Key

  • This line was added.
  • This line was removed.
  • Formatting was changed.

Intro

Test of what and how slow could be generated on a modern (as for the year 2025) mini PC without discrete graphics

  • Intel Core Ultra 9 185H (95W Power limit) with internal Intel Arc 
  • Crucial 128GB (2x64GB) 5600MT/s CL46 DDR5
  • WD_BLACK SN850X 8TB NVMe Gen 4x4

Photorealism and limbs test

...

  1. photorealistic girl in bookshop choosing the book in romantic stories shelf. smiling
  2. Generate a photo of a woman's legs, with her feet crossed and wearing white high-heeled shoes with ribbons tied around her ankles. The shoes should have a pointed toe and a stiletto heel. The woman's legs should be smooth and tanned, with a slight sheen to them. The background should be a light gray color. The photo should be taken from a low angle, looking up at the woman's legs. The ribbons should be tied in a bow shape around the ankles. The shoes should have a red sole. The woman's legs should be slightly bent at the knee.
  3. Create a close-up photograph of a woman's face and hand, with her hand raised to her chin. She is wearing a white blazer and has a gold ring on her finger. Her nails are neatly manicured and her hair is pulled back into a low bun. She is smiling and has a radiant expression on her face. The background is a plain light gray color. The overall mood of the photo is elegant and sophisticated. The photo should have a soft, natural light and a slight warmth to it. The woman's hair is dark brown and pulled back into a low bun, with a few loose strands framing her face.

...

PixArtSigmaPipeline 9422 7% 1342 11%Image Removed
Modelpipelinesizetimeimage example

Stable Cascade 1.0  

stable-cascade

[a89f66d459]

StableCascadeCombinedPipeline

GPU 7620 MB 6% | RAM 13.93 GB 11%2m 44.11s



Stable Diffusion 3.5 (1024x1024)  

tensorart--stable-diffusion-3.5-large-TurboX

Image Size: 512x512

[23edf37b1f]


StableDiffusion3Pipeline

GPU 16604 MB 13% | RAM 28.83 GB 23%2m 48.05s



stabilityai--stable-diffusion-3.5-large-turbo

(Authentification needed)

Image Size: 512x512

[ec07796fc0]

StableDiffusion3Pipeline

GPU 16604 MB 13% | RAM 28.51 GB 23%2m 55.18s



stabilityai--stable-diffusion-3.5-large
(Authentification needed)

Image Size: 512x512

[ceddf0a7fd]

StableDiffusion3Pipeline

GPU 16528 MB 13% | RAM 28.76 GB 23%2m 41.02s



tensorart--stable-diffusion-3.5-medium-turbo

[e89195b004]

StableDiffusion3Pipeline

GPU 9178 MB 7% | RAM 18.02 GB 14% 7m 3.79s










Stable Diffusion XL (1024x1024)  

dreamshaperXL_v21TurboDPMSDE

[4496b36d48]

StableDiffusionXLPipeline

GPU 6590 MB 5% | RAM 8.89 GB 7%1m 45.68s



TempestV0.1-Artistic

[9ca260b31e]

StableDiffusionXLPipeline

GPU 6590 MB 5% | RAM 8.93 GB 7%1m 47.59s



Segmind-Vega



StableDiffusionXLPipeline

GPU 2972 MB 2% | RAM 6.33 GB 5%54.78s



Segmind SSD-1B

StableDiffusionXLPipeline

GPU 4116 MB 3% | RAM 7.45 GB 6%1m 14.13s



juggernautXL_ragnarokBy

[dd08fa32f9]

StableDiffusionXLPipeline

 GPU 6588 MB 5% | RAM 8.89 GB 7%1m 47.37s



realvisxlV50_v50Bakedvae

[49527024b6]

StableDiffusionXLPipeline

GPU 6588 MB 5% | RAM 9.14 GB 7%1m 46.33s 



ponyDiffusionV6XL_v6TurboMerge

[7555ac941f]

StableDiffusionXLPipeline

GPU 6588 MB 5% | RAM 9.16 GB 7%1m 46.88s



prefectPonyXL_v50

[d1a2aac8e5]

StableDiffusionXLPipeline

GPU 6588 MB 5% | RAM 9.16 GB 7%1m 45.82s



realismByStableYogi_ponyV3VAE

[4796b66fd0]

StableDiffusionXLPipeline

GPU 6588 MB 5% | RAM 9.17 GB 7%1m 47.67s



ponyRealism_V23

[8ffda79382]

StableDiffusionXLPipeline

GPU 6588 MB 5% | RAM 9.15 GB 7%1m 49.29s



etri-vilab--koala-700m-llava-cap

[d7992bd7b2]

StableDiffusionXLPipeline

 GPU 2976 MB 2% | RAM 5.61 GB 4%51.43s



Stable diffusion 2.1 (512x512)  
stablestable-diffusion-2.1


StableDiffusionPipelineGPU 2576 MB 2% | RAM 4.94 GB 4%19.52s



EulerStableDiffusionPipelineGPU 2736 MB 2% | RAM 4.87 GB 4%17.60s

 

 

Steps: 50

Sampler: DDIM

StableDiffusionPipelineGPU 2740 MB 2% | RAM 4.92 GB 4% 42.43s

 

 

Stable diffusion 1.5 (512x512)  

dreamshaper_8

[879db523c3]

StableDiffusionPipelineGPU 3224 MB 3% | RAM 4.62 GB 4%23.51s



counterfeitV30_25

[a074b8864e]

StableDiffusionPipeline

GPU 2930 MB 2% | RAM 5.18 GB 4%21.06s



cyberrealistic_v80

[90389105e4]

StableDiffusionPipeline

GPU 2784 MB 2% | RAM 5.05 GB 4%21.80s



juggernaut_reborn

[338b85bc4f]

(need more steps)

StableDiffusionPipeline

GPU 2948 MB 2% | RAM 5.06 GB 4%21.86s



juggernaut_reborn

Steps: 80

StableDiffusionPipeline

GPU 2784 MB 2% | RAM 5.16 GB1m 15.75s



juggernaut_reborn

Steps: 40

Sampling DPM++ 2M SDE

StableDiffusionPipeline

GPU 2948 MB 2% | RAM 5.15 GB 4%38.21s



epicrealism_naturalSin

[bff4610d23]


StableDiffusionPipeline

GPU 2784 MB 2% | RAM 5.17 GB 4%
 21.96s



Steps: 80

StableDiffusionPipeline

GPU 2784 MB 2% | RAM 5.18 GB 4%1m 17.22s



Steps: 40

Sampling DPM++ 2M SDE

StableDiffusionPipeline

GPU 2784 MB 2% | RAM 5.17 GB 4%39.37s



SegMoE-SD-4x2-v0

[7a7d12be30]

StableDiffusionPipeline

GPU 4522 MB 4% | RAM 6.32 GB 5%36.68s



majicmixRealistic_v7

[7c819b6d13]

StableDiffusionPipeline

GPU 2784 MB 2% | RAM 5.25 GB 4%22.85s



Steps: 40

Sampling Euler a

StableDiffusionPipeline

GPU 2784 MB 2% | RAM 5.25 GB 4%39.69s



meinamix_v12Final

[a5e5a941a3]

StableDiffusionPipeline

GPU 2784 MB 2% | RAM 5.33 GB 4%24.68s



disney-pixal-cartoon

[bd1ac21dc5]

StableDiffusionPipeline

GPU 2784 MB 2% | RAM 5.25 GB 4%24.80s



Sampling DPM++ 2M SDE

StableDiffusionPipeline

GPU 2952 MB 2% | RAM 5.25 GB 4%22.12s



Steps: 40

Sampling DPM++ 2M SDE

Size: 768x768

StableDiffusionPipeline

GPU 7328 MB 6% | RAM 5.27 GB 4%4m 4.13s



Flux.1 Schnell



shuttle-3.1-aesthetic

Steps: 20

Size: 512x512

Seed: 2646842481

FluxPipeline

GPU 23084 MB 18% | RAM 34.95 GB 28%2m 56.49s



Steps: 6

Size: 512x512

Seed: 2544969645

FluxPipeline

GPU 23084 MB 18% | RAM 35.0 GB 28%1m 3.14s



Steps: 15

Size: 768x768

Seed: 2544969645

Sampling DPM++ 2M

FluxPipeline

GPU 23770 MB 19% | RAM 34.31 GB 27%3m 55.38s 



shuttle-jaguar

Steps: 6

Size: 512x512

Seed: 2390905673

FluxPipeline

GPU 23074 MB 18% | RAM 33.9 GB 27%1m 10.53s



Steps: 15

Size: 768x768

Seed: 966612124

FluxPipeline

GPU 23778 MB 19% | RAM 33.98 GB 27%3m 32.41s

 

 

Black Forest Labs FLUX.1 Schnell
 (Authentification needed)

Steps: 4

Size: 512x512

Seed: 2544969645

Sampling DPM++ 2M

FluxPipeline

GPU 23070 MB 18% | RAM 34.24 GB 27%1m 1.83s



Steps: 20

Seed: 2544969645

Size: 768x768

FluxPipeline

GPU 23770 MB 19% | RAM 34.23 GB 27%4m 52.01s



FLUX.1-dev

Steps: 20

Size: 512x512

Seed: 2544969645

FluxPipeline

GPU 23088 MB 18% | RAM 34.22 GB 27%2m 33.27s

 

 

Steps: 20

Size: 768x768

Sampler: DPM++ 2M

Seed: 2544969645

FluxPipeline

GPU 23794 MB 19% | RAM 34.23 GB 27%4m 29.58s

 

 

ostris--Flex.1-alpha

5dd0b1bc2a

Steps: 20

Size: 512x512

Seed: 2646842481

FluxPipeline

GPU 15972 MB 12% | RAM 27.59 GB 22%

2m 1.51s



Steps: 30

Size: 1024x1024

Seed: 271048284

FluxPipeline

GPU 18070 MB 14% | RAM 27.5 GB 22%

9m 32.13s 



Flex.2



ostris/Flex.2-preview

Steps: 20

Size: 512x512

Seed: 2544969645

Flex2Pipeline

GPU 16128 MB 13% | RAM 27.3 GB 22%2m 23.92s


 

 

Sampler: DPM++ 2M

Steps: 34

Seed: 2544969645

 

Flex2Pipeline

GPU 16136 MB 13% | RAM 27.17 GB 22%3m 11.60s


 

 

kandinsky (512x512)



kandinsky-3

[bf79e6c219]

Steps: 20

Size: 512x512

Seed: 519161814

Kandinsky3PipelineGPU 16662 MB 13% | RAM 25.34 GB 20%41.31s



Steps: 35

Size: 768x768

Kandinsky3PipelineGPU 16668 MB 13% | RAM 25.29 GB 20%1m 21.45s



CogView

CogView4-6B

Steps: 20

Size: 1024x1024

Seed: 3047948615

CogView4PipelineGPU 18008 MB 14% | RAM 32.6 GB 26%18m 31.15s 



Steps: 20

Size: 512x512

Seed: 3047948615

CogView4Pipeline GPU 18876 MB 15% | RAM 32.62 GB 26%3m 42.76s



CogView3-Plus-3B

Steps: 20

Size: 512x512

Seed: 3047948615

CogView3PlusPipelineGPU 9172 MB 7% | RAM 17.47 GB 14%2m 52.31s



PixArtAlpha

PixArt-Sigma-XL-2-1024-MS-MS

Size: 1024x1024

PixArtSigmaPipelineGPU 9422 MB 7% | RAM 13.42 GB 11%1m 57.11s

Image Added



Size: 1280x1280

Seed: 1977597170

PixArtSigmaPipelineGPU 11398 MB 9% | RAM 13.47 GB 11%3m 39.43s

Image Added



Sana

Sana_600M_512px

Size: 512x512

SanaPipelineGPU 5304 MB 4% | RAM 9.47 GB 8%17.30s 

Image Added

Image Added

Image Added

Sana_1600M_1024px

Size: 1024x1024

Seed: 3047948615

SanaPipelineGPU 5866 MB 5% | RAM 11.31 GB 9%1m 57.11s

Image Removed

Size: 1280x1280

Seed: 1977597170

PixArtSigmaPipelineGPU 11398 MB 9% | RAM 13.47 GB 11%3m 39.43s51.80s 

Image Added

Image Added

Image Added

Sana_1600M_4Kpx_BF16_diffusers

SanaPipelineGPU 14340 MB 11% | RAM 11.41 GB 9%



























Understanding Idea from short prompt and multilanguage test

Random prompts used in this test

...

Modelcrazy frog on the moonAsian girl with white rabbit in
New York Central Park		Sports car in faraway winter village
get towed by coca-cola truck		Президент України на
центральній площі столиці

stabilityai--stable-diffusion-3.5-large

Model Size: 24G
Image Size: 1024x1024,

Time: 17m 48.33s 



 


THUDM--CogView4-6B

Model Size:  24G

Image Size: 1024x1024,

Pipeline: CogView4Pipeline


Site https://cogview4.net/

 



 


stable-diffusion-3.5-medium-turbo

pipeline=StableDiffusion3Pipeline

Model Size: 16G
Image Size: 1024x1024,

 

Time: 13m

 

tensorart--stable-diffusion-3.5-large-TurboX

pipeline=StableDiffusion3Pipeline

Model Size: 28G
Image Size: 1024x1024,

 

Time: 17m 49.71s 


 

stabilityai--stable-cascade

Model Size:  15G

Image Size: 1024x1024,

Pipeline: StableCascadeCombinedPipeline


Time: 2m 43.67s 

Time: 2m 45.05s

Time: 2m 44.83s 

Time: 2m 44.93s 

stabilityai--stable-cascade-prior

Model Size:  31G

Image Size: 1024x1024,

Pipeline: StableCascadeCombinedPipeline



 

Time: 2m 44.86s 

Time: 2m 44.76s

Time: 2m 44.76s

Time: 2m 44.77s

dreamshaperXL_v21TurboDPMSDE

Model Size: 6.5G

Image Size: 1024x1024, 

Pipeline: StableDiffusionXLPipeline

Time: 4m 10.85             

Time: 4m 5.84s

Time: 4m 5.55s

Time: 4m 5.27s 

dreamshaperXL_v21TurboDPMSDE

Model Size: 6.5G

Image Size: 1024x1024, 

(OpenVINO)

Time: 1m 25.62s

Time: 1m 27.45s 

Time: 1m 27.33s 

Time: 1m 27.47s

ostris--Flex.1-alpha

Model Size: 6.5G

Pipeline: FluxPipeline

Image Size: 1024x1024, 

 

Time: 6m 52.95s 

Time: 6m 27.95s

Time: 6m 26.53s

Time: 6m 27.70s

TempestV0.1-Artistic

Model Size: 6.5G

Pipeline: StableDiffusionXLPipeline

Image Size: 1024x1024, 

 

Time: 1m 45.31s

Time: 1m 46.13s

Time: 1m 45.31s 

Time: 1m 47.05s

dreamshaper_8

Model Size: 2.0G

Pipeline: StableDiffusionPipeline

Image Size: 1024x1024, 

Time: 5m 53.64s

kandinsky-community--kandinsky-3

Model Size: 27G

Pipeline: Kandinsky3Pipeline
Image Size: 512x512,

 

Time: 22.38s

Time: 22.41s

Time: 22.96s

Time: 22.93s

segmind---SD-4x2-v0

Model Size: 3.7G

Pipeline: StableDiffusionPipeline

Image Size: 1024x1024, 

time=868.29 (other high load)

Time: 5m 55.77s 

Time: 6m 25.73s 

Time: 6m 35.28s 

segmind--tiny-sd

Model Size: 1G

Pipeline: StableDiffusionPipeline

Image Size: 1024x1024, 

Time: 3m 25.01s 

Time: 3m 25.15s 

Time: 3m 24.95s 

Time: 3m 26.57s 

XCLiu--instaflow_0_9B_from_sd_1_5

Model Size: 5.2G

Pipeline: InstaFlowPipeline

Image Size: 1024x1024, 


Time: 13m 47.34s

Time: 13m 48.29s

Time: 13m 54.21s

Time: 13m 54.96s

juggernautXL_ragnarokBy

Model Size: 6.7G

Pipeline: StableDiffusionXLPipeline

Image Size: 1024x1024, 

 

Time: 1m 45.56s

Time: 1m 45.57s 

Time: 1m 45.27s

Time: 1m 45.51s 

juggernaut_reborn

Model Size: 2.0G

Pipeline: StableDiffusionPipeline

Image Size: 1024x1024, 


Time: 7m 51.51s

Time: 7m 12.42s

Time: 6m 32.72s

Time: 6m 12.55s

meinamix_v12Final

Model Size: 2G

Pipeline: StableDiffusionPipeline

Image Size: 1024x1024, 

7m 5.59s

Time: 5m 50.81s

6m 18.95s

Time: 14m 30.83s  (background tasks)

ponyRealism_V23

Model Size: 6.2G

Pipeline: StableDiffusionXLPipeline

Image Size: 1024x1024, 

Time: 1m 48.85s

Time: 1m 45.83s 

Time: 1m 45.75s

Time: 1m 45.75s +neg. prompt (no nudes)

prefectPonyXL_v50

Model Size: 6.2G

Pipeline: StableDiffusionXLPipeline

Image Size: 1024x1024, 

 

Time: 1m 45.26s 

Time: 1m 45.37s 

Time: 1m 45.31s 

Time: 1m 45.46s

ponyDiffusionV6XL_v6TurboMerge

Model Size: 6.5G

Pipeline: StableDiffusionXLPipeline

Image Size: 1024x1024, 

 

Time: 1m 46.17s

Time: 1m 46.72s 

Time: 1m 46.04s

Time: 4m 14.59s

epicrealism_naturalSin

Model Size: 2G

Pipeline: StableDiffusionPipeline

Image Size: 1024x1024, 

Time: 5m 49.91s (20 step)

Time: 5m 50.01s (20 steps, CFG=6)

Time: 8m 34.48s  (30 steps, CFG=7.5)

Time: 8m 37.26s (30 steps, CFG=7.5)

counterfeitV30_25

Model Size: 4G

Image Size: 1024x1024, 

Time: 5m 50.00s 

Time: 5m 49.99s

Time: 10m 58.72s

stablediffusionapi--disney-pixal-cartoon

Model Size: 5.2G

Pipeline: StableDiffusionPipeline

Image Size: 1024x1024, 


Time: 5m 52.60s 

Time: 5m 52.44s 

Time: 5m 52.57s

5m 56.06s 

stablediffusionapi--anything-v5

Model Size: 5.2G

Pipeline: StableDiffusionPipeline

Image Size: 1024x1024, 

 

Time: 6m 8.78s

Tencent-Hunyuan--HunyuanDiT-v1.2-Diffusers

Model Size: 14G

Image Size: 1024x1024, 

Pipeline: HunyuanDiTPipeline

 Sampling method = default


PixArt-alpha--PixArt-XL-2-512x512

Model Size: 21G

Pipeline: PixArtAlphaPipeline

Size: 512x512, 

Time: 24.79s 

Time: 24.69s 

Time: 24.76s 

Time: 24.69s 

PixArt-alpha--PixArt-XL-2-512x512

Model Size: 21G

Pipeline: PixArtAlphaPipeline

Size: 1024x1024, 

 

Efficient-Large-Model–Sana_Sprint_1.6B_1024px_diffuser

Model Size: 9.1G
Image Size: 1024x1024,

Pipeline:  SanaSprintPipeline
Steps: 2

Time: 19.60s 

Time: 12.25s

Time: 11.77s

Time: 11.51s

playgroundai--playground-v2-256px-base

Model Size: 13G

Pipeline: StableDiffusionXLPipeline

Image Size: 256x256, 

 

Time: 14.15s 

Time: 14.15s 

Time: 14.07s 

Time: 14.13s


models--warp-ai–wuerstchen

Pipeline: WuerstchenCombinedPipeline

Model Size: 9.1G
Image Size: 1024x1024,


Time: 1m 39.51s

Time: 1m 38.01s

Time: 1m 38.29s

Time: 1m 37.76s 

etri-vilab--koala-700m-llava-cap

Pipeline: StableDiffusionXLPipeline

Model Size: 6.3G
Image Size: 1024x1024,



Time: 50.27s 

Time: 49.80s

Time: 50.52s 

Time: 50.52s

...


Stable Diffusion Versions

 info info from wiki https://en.wikipedia.org/wiki/Stable_Diffusion

Version numberRelease dateParametersNotes
1.1, 1.2, 1.3, 1.4August 2022
All released by CompVis. There is no "version 1.0". 1.1 gave rise to 1.2, and 1.2 gave rise to both 1.3 and 1.4.
1.5October 2022983MInitialized with the weights of 1.2, not 1.4. Released by RunwayML.
2.0November 2022
Retrained from scratch on a filtered dataset.
2.1December 2022
Initialized with the weights of 2.0.
XL 1.0July 20233.5BThe XL 1.0 base model has 3.5 billion parameters, making it around 3.5x larger than previous versions.
XL TurboNovember 2023
Distilled from XL 1.0 to run in fewer diffusion steps.
3.0February 2024 (early preview)800M to 8BA family of models.
3.5October 20242.5B to 8BA family of models with Large (8 billion parameters), Large Turbo (distilled from SD 3.5 Large), and Medium (2.5 billion parameters).


SD.Next

...

Supported Models

from https://vladmandic.github.io/sdnext-docs/Models/

PublisherModelVersionSizeDiffusion ArchitectureModel ParamsText Encoder(s)TE ParamsAuto EncoderOther
StabilityAIStable Diffusion1.52.28GBUNet0.86BCLiP ViT-L0.12BVAE
StabilityAIStable Diffusion2.12.58GBUNet0.86BCLiP ViT-H0.34BVAE
StabilityAIStable DiffusionXL6.94GBUNet2.56BCLiP ViT-L + ViT+G0.12B + 0.69BVAE
StabilityAIStable Diffusion3.0 Medium15.14GBMMDiT2.0BCLiP ViT-L + ViT+G + T5-XXL0.12B + 0.69B + 4.76B16ch VAE
StabilityAIStable Diffusion3.5 Medium15.89GBMMDiT2.25BCLiP ViT-L + ViT+G + T5-XXL0.12B + 0.69B + 4.76B16ch VAE
StabilityAIStable Diffusion3.5 Large26.98GBMMDiT8.05BCLiP ViT-L + ViT+G + T5-XXL0.12B + 0.69B + 4.76B16ch VAE
StabilityAIStable CascadeMedium11.82GBMulti-stage UNet1.56B + 3.6BCLiP ViT-G0.69B42x VQE
StabilityAIStable CascadeLite4.97GBMulti-stage UNet0.7B + 1.0BCLiP ViT-G0.69B42x VQE
Black Forest LabsFlux1 Dev/Schnell32.93GBMMDiT11.9BCLiP ViT-L + T5-XXL0.12B + 4.76B16ch VAE
OstrisFlex1 Alpha25.65GBMMDiT4.0BCLiP ViT-L + T5-XXL0.12B + 2.95B16ch VAE
NVLabsSana1.5 1.6B9.49GBMMDiT1.60BGemma22.61BDC-AE
NVLabsSana1.5 4.8B15.58GBMMDiT4.72BGemma22.61BDC-AE
NVLabsSana1.0 1600M12.63GBMMDiT1.60BGemma22.61BDC-AE
NVLabsSana1.0 600M7.51GBMMDiT0.59BGemma22.61BDC-AE
FALAuraFlow0.331.90GBMMDiT6.8BUMT512.1BVAE
AlphaVLLMLuminaNext SFT8.67GBDiT1.7BGemma2.5BVAE
AlphaVLLMLumina220.75GBDiT2.61BGemma-22.61B16ch VAE
PixArtAlphaXL 221.3GBDiT0.61BT5-XXL4.76BVAE
PixArtSigmaXL 221.3GBDiT0.61BT5-XXL4.76BVAE
SegmindSSD-1BN/A8.72GBUNet1.33BCLiP ViT-L + ViT+G0.12B + 0.69BVAE
SegmindVegaN/A6.43GBUNet0.75BCLiP ViT-L + ViT+G0.12B + 0.69BVAE
SegmindTinyN/A1.03GBUNet0.32BCLiP ViT-L0.12BVAE
KwaiKolorsN/A17.40GBUNnet2.58BChatGLM6.24BVAE
PlaygroundAIPlayground1.04.95GBUNet0.86BCLiP ViT-L0.12BVAE
PlaygroundAIPlayground2.x13.35GBUNet2.56BCLiP ViT-L + ViT+G0.12B + 0.69BVAE
TencentHunyuanDiT1.214.09GBDiT1.5BBERT + T5-XL3.52B + 1.67BVAE
Warp AIWuerstchenN/A12.16GBMulti-stage UNet1.0B + 1.05BCLiP ViT-L + ViT+G0.12B + 0.69B42x VQE
KandinskyKandinsky2.25.15GBUnet1.25BCLiP ViT-G0.69BVQ
KandinskyKandinsky3.027.72GBUnet3.05BT5-XXXL8.72BVQ
ThudmCogView3 Plus24.96GBDiT2.85BT5-XXL4.76BVAE
ThudmCogView430.39GBDiT6.37BGLM-49.40BVAE
IDKiroSDXSN/A2.05GBUNet0.32BCLiP ViT-L0.12BVAE
Open-MUSEaMUSEd2563.41GBViT0.60BCLiP ViT-L0.12BVQ
KoalaKoala700M6.58GBUNet0.78BCLiP ViT-L + ViT+G0.12B + 0.69BVAE
Thu-MLUniDiffuserv15.37GBU-ViT0.95BCLiP ViT-L + CLiP ViT-B0.12B + 0.16BVAE
SalesforceBLIP-DiffusionN/A7.23GBUNet0.86BCLiP ViT-L + BLiP-20.12B + 0.49BVAE
DeepFloydIFM12.79GBMulti-stage UNet0.37B + 0.46BT5-XXL4.76BPixel
DeepFloydIFL15.48GBMulti-stage UNet0.61B + 0.93BT5-XXL4.76BPixel
MeissonFlowMeissonicN/A3.64GBDiT1.18BCLiP ViT-H0.35BVQ
VectorSpaceLabOmniGenv115.47GBTransformer3.76BNone0VAEPhi-3
HiDream-AIHiDreamI2 Fast/Dev/Full42.71 GB + 15.69MMDiT17.10BCLiP ViT-L + ViT+G + T5-XXL + LLama-3.1-8B0.12B + 0.69B + 2.95B + 4.54B16ch VAE

Size of the model on disk

Code Block
root@server6:~# du -xsh /docker/sdnext/mnt-volume/models/Diffusers/* /docker/sdnext/mnt-volume/models/Stable-diffusion/*.safetensors |sort -n
2.0G    /docker/sdnext/mnt-volume/models/Stable-diffusion/dreamshaper_8.safetensors
2.0G    /docker/sdnext/mnt-volume/models/Stable-diffusion/epicrealism_naturalSin.safetensors
2.0G    /docker/sdnext/mnt-volume/models/Stable-diffusion/juggernaut_reborn.safetensors
2.0G    /docker/sdnext/mnt-volume/models/Stable-diffusion/majicmixRealistic_v7.safetensors
2.0G    /docker/sdnext/mnt-volume/models/Stable-diffusion/meinamix_v12Final.safetensors
3.3G    /docker/sdnext/mnt-volume/models/Diffusers/models--amused--amused-512
3.3G    /docker/sdnext/mnt-volume/models/Diffusers/models--stabilityai--stable-diffusion-x4-upscaler
3.7G    /docker/sdnext/mnt-volume/models/Diffusers/models--segmind--SegMoE-SD-4x2-v0
4.0G    /docker/sdnext/mnt-volume/models/Stable-diffusion/counterfeitV30_25.safetensors
4.0G    /docker/sdnext/mnt-volume/models/Stable-diffusion/cyberrealistic_v80.safetensors
4.8G    /docker/sdnext/mnt-volume/models/Stable-diffusion/stableDiffusion35_medium.safetensors
4.9G    /docker/sdnext/mnt-volume/models/Diffusers/models--radames--smashed-stabilityai-sd-turbo
4.9G    /docker/sdnext/mnt-volume/models/Diffusers/models--stabilityai--stable-diffusion-2-1
5.2G    /docker/sdnext/mnt-volume/models/Diffusers/models--stablediffusionapi--anything-v5
5.2G    /docker/sdnext/mnt-volume/models/Diffusers/models--stablediffusionapi--disney-pixal-cartoon
5.2G    /docker/sdnext/mnt-volume/models/Diffusers/models--XCLiu--instaflow_0_9B_from_sd_1_5
5.4G    /docker/sdnext/mnt-volume/models/Diffusers/models--warp-ai--wuerstchen
6.2G    /docker/sdnext/mnt-volume/models/Diffusers/models--segmind--Segmind-Vega
6.3G    /docker/sdnext/mnt-volume/models/Diffusers/models--etri-vilab--koala-700m-llava-cap
6.3G    /docker/sdnext/mnt-volume/models/Diffusers/models--warp-diffusion--wuerstchen-prior
6.5G    /docker/sdnext/mnt-volume/models/Stable-diffusion/dreamshaperXL_v21TurboDPMSDE.safetensors
6.5G    /docker/sdnext/mnt-volume/models/Stable-diffusion/ponyDiffusionV6XL_v6TurboMerge.safetensors
6.5G    /docker/sdnext/mnt-volume/models/Stable-diffusion/ponyRealism_V23.safetensors
6.5G    /docker/sdnext/mnt-volume/models/Stable-diffusion/prefectPonyXL_v50.safetensors
6.5G    /docker/sdnext/mnt-volume/models/Stable-diffusion/realismByStableYogi_ponyV3VAE.safetensors
6.5G    /docker/sdnext/mnt-volume/models/Stable-diffusion/TempestV0.1-Artistic.safetensors
6.7G    /docker/sdnext/mnt-volume/models/Stable-diffusion/juggernautXL_ragnarokBy.safetensors
8.0G    /docker/sdnext/mnt-volume/models/Stable-diffusion/projectZeusSD3_v10.safetensors
8.1G    /docker/sdnext/mnt-volume/models/Diffusers/models--stabilityai--stable-diffusion-3.5-large-controlnet-depth
8.2G    /docker/sdnext/mnt-volume/models/Stable-diffusion/r35on4nce_r35AnalogCstageBf16.safetensors
8.4G    /docker/sdnext/mnt-volume/models/Diffusers/models--segmind--SSD-1B
9.1G    /docker/sdnext/mnt-volume/models/Diffusers/models--Efficient-Large-Model--Sana_Sprint_1.6B_1024px_diffusers
13G     /docker/sdnext/mnt-volume/models/Diffusers/models--playgroundai--playground-v2-256px-base
13G     /docker/sdnext/mnt-volume/models/Stable-diffusion/realvisxlV50_v50Bakedvae.safetensors
14G     /docker/sdnext/mnt-volume/models/Diffusers/models--stabilityai--stable-diffusion-xl-base-1.0
14G     /docker/sdnext/mnt-volume/models/Diffusers/models--Tencent-Hunyuan--HunyuanDiT-v1.2-Diffusers
15G     /docker/sdnext/mnt-volume/models/Diffusers/models--a-k-aAiMGoD--lora-real-face-stable-3.5-large
15G     /docker/sdnext/mnt-volume/models/Diffusers/models--Shitao--OmniGen-v1
15G     /docker/sdnext/mnt-volume/models/Diffusers/models--stabilityai--stable-cascade
16G     /docker/sdnext/mnt-volume/models/Diffusers/models--tensorart--stable-diffusion-3.5-medium-turbo
16G     /docker/sdnext/mnt-volume/models/Stable-diffusion/stableDiffusion35_large.safetensors
21G     /docker/sdnext/mnt-volume/models/Diffusers/models--PixArt-alpha--PixArt-XL-2-512x512
25G     /docker/sdnext/mnt-volume/models/Diffusers/models--ostris--Flex.1-alpha
26G     /docker/sdnext/mnt-volume/models/Diffusers/models--stabilityai--stable-diffusion-3.5-large
26G     /docker/sdnext/mnt-volume/models/Diffusers/models--stabilityai--stable-diffusion-3.5-large-turbo
27G     /docker/sdnext/mnt-volume/models/Diffusers/models--kandinsky-community--kandinsky-3
28G     /docker/sdnext/mnt-volume/models/Diffusers/models--tensorart--stable-diffusion-3.5-large-TurboX
29G     /docker/sdnext/mnt-volume/models/Diffusers/models--THUDM--CogView4-6B
31G     /docker/sdnext/mnt-volume/models/Diffusers/models--fal--AuraFlow
31G     /docker/sdnext/mnt-volume/models/Diffusers/models--stabilityai--stable-cascade-prior
32G     /docker/sdnext/mnt-volume/models/Diffusers/models--black-forest-labs--FLUX.1-dev
32G     /docker/sdnext/mnt-volume/models/Diffusers/models--black-forest-labs--FLUX.1-schnell
32G     /docker/sdnext/mnt-volume/models/Diffusers/models--shuttleai--shuttle-3.1-aesthetic
32G     /docker/sdnext/mnt-volume/models/Diffusers/models--shuttleai--shuttle-jaguar