root@server6:~/ollama-cpu-docker# du -xsh /docker/sdnext/mnt-volume/models/Diffusers/* 3.3G /docker/sdnext/mnt-volume/models/Diffusers/models--amused--amused-512 9.1G /docker/sdnext/mnt-volume/models/Diffusers/models--Efficient-Large-Model--Sana_Sprint_1.6B_1024px_diffusers 27G /docker/sdnext/mnt-volume/models/Diffusers/models--kandinsky-community--kandinsky-3 25G /docker/sdnext/mnt-volume/models/Diffusers/models--ostris--Flex.1-alpha 21G /docker/sdnext/mnt-volume/models/Diffusers/models--PixArt-alpha--PixArt-XL-2-512x512 13G /docker/sdnext/mnt-volume/models/Diffusers/models--playgroundai--playground-v2-256px-base 3.7G /docker/sdnext/mnt-volume/models/Diffusers/models--segmind--SegMoE-SD-4x2-v0 1013M /docker/sdnext/mnt-volume/models/Diffusers/models--segmind--tiny-sd 5.2G /docker/sdnext/mnt-volume/models/Diffusers/models--XCLiu--instaflow_0_9B_from_sd_1_5 root@server6:~# du -xsh /docker/sdnext/mnt-volume/models/Stable-diffusion/*.safetensors 4.0G /docker/sdnext/mnt-volume/models/Stable-diffusion/counterfeitV30_25.safetensors 2.0G /docker/sdnext/mnt-volume/models/Stable-diffusion/dreamshaper_8.safetensors 6.5G /docker/sdnext/mnt-volume/models/Stable-diffusion/dreamshaperXL_v21TurboDPMSDE.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 6.7G /docker/sdnext/mnt-volume/models/Stable-diffusion/juggernautXL_ragnarokBy.safetensors 2.0G /docker/sdnext/mnt-volume/models/Stable-diffusion/meinamix_v12Final.safetensors 13G /docker/sdnext/mnt-volume/models/Stable-diffusion/ponyDiffusionV6XL_v6StartWithThisOne.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/TempestV0.1-Artistic.safetensors
Random prompts used in this test
crazy frog on the moon
Asian 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
Defaults (All SD.Next App parameters left in defaults)
- Batch count =1
- Batch size = 1
- Guidance end = 1
- Guidance scale = 6
- Steps = 20
- Sampling method = default
| Model | crazy frog on the moon | Asian 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 |
|---|---|---|---|---|
dreamshaperXL_v21TurboDPMSDE Model Size: 6.5G Image Size: 1024x1024, CFG scale: 6, Model: dreamshaperXL_v21TurboDPMSDE, Model hash: 4496b36d48, App: SD.Next, Version: 12ebadc, Operations: txt2img, Pipeline: StableDiffusionXLPipeline |
Time: 4m 10.85 |
Time: 4m 5.84s |
Time: 4m 5.55s |
Time: 4m 5.27s |
dreamshaper_8 Model Size: 2.0G Image Size: 1024x1024, |
Time: 5m 53.64s |
|
|
|
kandinsky-community--kandinsky-3 Model Size: 27G
|
Time: 22.38s |
Time: 22.41s |
Time: 22.96s |
Time: 22.93s |
segmind---SD-4x2-v0 Model Size: 3.7G Image Size: 1024x1024, |
time=868.29 (other high load) |
Time: 5m 55.77s |
Time: 6m 25.73s |
Time: 6m 35.28s |
XCLiu--instaflow_0_9B_from_sd_1_5 Model Size: 5.2G Image Size: 1024x1024, |
Time: 13m 47.34s |
Time: 13m 48.29s |
Time: 13m 54.21s |
Time: 13m 54.96s |
juggernaut_reborn Model Size: 2.0G Image Size: 1024x1024, |
Time: 7m 51.51s |
Time: 7m 12.42s |
Time: 6m 32.72s |
Time: 6m 12.55s |
meinamix_v12Final Model Size: 2G Image Size: 1024x1024, |
7m 5.59s |
Time: 5m 50.81s |
6m 18.95s |
Time: 14m 30.83s (background tasks) |
epicrealism_naturalSin Model Size: 2G 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 |
| ostris--Flex.1-alpha Model Size: 25G Image Size: 1024x1024, | - | - | - | - |
Efficient-Large-Model–Sana_Sprint_1.6B_1024px_diffuser Model Size: 9.1G | - | - | - | - |
kandinsky-community--kandinsky-3 Model Size: 27G |
| - | - | - |
PixArt-alpha--PixArt-XL-2-512x512 Model Size: 21G Size: 512x512, | - | - | - | - |
amused--amused-512 Model Size: 3.3G Image Size: 512x512,
| 'list' object has no attribute 'device' | 'list' object has no attribute 'device' | 'list' object has no attribute 'device' | 'list' object has no attribute 'device' |
playgroundai--playground-v2-256px-base Model Size: 13G Image Size: 1024x1024, Image Size: 512x512, Image Size: 256x256,
| ||||
disney-pixal-cartoon | Time: 6m 6.92s |
SD Versions info from wiki
https://en.wikipedia.org/wiki/Stable_Diffusion
| Version number | Release date | Parameters | Notes |
|---|---|---|---|
| 1.1, 1.2, 1.3, 1.4 | August 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. | |
| 1.5 | October 2022 | 983M | Initialized with the weights of 1.2, not 1.4. Released by RunwayML. |
| 2.0 | November 2022 | Retrained from scratch on a filtered dataset. | |
| 2.1 | December 2022 | Initialized with the weights of 2.0. | |
| XL 1.0 | July 2023 | 3.5B | The XL 1.0 base model has 3.5 billion parameters, making it around 3.5x larger than previous versions. |
| XL Turbo | November 2023 | Distilled from XL 1.0 to run in fewer diffusion steps. | |
| 3.0 | February 2024 (early preview) | 800M to 8B | A family of models. |
| 3.5 | October 2024 | 2.5B to 8B | A family of models with Large (8 billion parameters), Large Turbo (distilled from SD 3.5 Large), and Medium (2.5 billion parameters). |
