You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
This is a great project and I would like to share my build speed on a Mac mini with M4 16GB RAM.
mflux-generate \
--model schnell \
--steps 2 \
--seed 2 \
--quantize 8 \
--height 512 \
--width 512 \
--prompt "Tranquil pond in a bamboo forest at dawn, the sun is barely starting to peak over the horizon, panda practices Tai Chi near the edge of the pond, atmospheric perspective through the mist of morning dew, sunbeams, its movements are graceful and fluid — creating a sense of harmony and balance, the pond’s calm waters reflecting the scene, inviting a sense of meditation and connection with nature, style of Howard Terpning and Jessica Rossier"
Fetching 8 files: 100%|████████████████████████████████████████| 8/8 [00:00<00:00, 116105.30it/s]
Fetching 7 files: 100%|█████████████████████████████████████████| 7/7 [00:00<00:00, 74518.09it/s]
100%|██████████████████████████████████████████████████████████████| 2/2 [01:37<00:00, 48.54s/it]
mflux-generate \
--model schnell \
--steps 2 \
--seed 2 \
--quantize 4 \
--height 512 \
--width 512 \
--prompt "Tranquil pond in a bamboo forest at dawn, the sun is barely starting to peak over the horizon, panda practices Tai Chi near the edge of the pond, atmospheric perspective through the mist of morning dew, sunbeams, its movements are graceful and fluid — creating a sense of harmony and balance, the pond’s calm waters reflecting the scene, inviting a sense of meditation and connection with nature, style of Howard Terpning and Jessica Rossier"
Fetching 8 files: 100%|████████████████████████████████████████| 8/8 [00:00<00:00, 105186.31it/s]
Fetching 7 files: 100%|█████████████████████████████████████████| 7/7 [00:00<00:00, 42184.09it/s]
100%|██████████████████████████████████████████████████████████████| 2/2 [00:26<00:00, 13.44s/it]
This is faster if the quantized model is saved in advance.
mflux-generate --path "./schnell_4bit" \
--model schnell \
--steps 2 \
--seed 2 \
--quantize 4 \
--height 512 \
--width 512 \
--prompt "Tranquil pond in a bamboo forest at dawn, the sun is barely starting to peak over the horizon, panda practices Tai Chi near the edge of the pond, atmospheric perspective through the mist of morning dew, sunbeams, its movements are graceful and fluid — creating a sense of harmony and balance, the pond’s calm waters reflecting the scene, inviting a sense of meditation and connection with nature, style of Howard Terpning and Jessica Rossier"
100%|██████████████████████████████████████████████████████████████| 2/2 [00:15<00:00, 7.60s/it]
Because of the memory, it can not generate 1024x1024 pictures.
Hardware:
Hardware Overview:
Model Name: Mac mini
Model Identifier: Mac16,10
Chip: Apple M4
Total Number of Cores: 10 (4 performance and 6 efficiency)
Memory: 16 GB
Graphics/Displays:
Apple M4:
Chipset Model: Apple M4
Type: GPU
Bus: Built-In
Total Number of Cores: 10
Vendor: Apple (0x106b)
Metal Support: Metal 3
The text was updated successfully, but these errors were encountered:
This is a great project and I would like to share my build speed on a Mac mini with M4 16GB RAM.
This is faster if the quantized model is saved in advance.
Because of the memory, it can not generate 1024x1024 pictures.
The text was updated successfully, but these errors were encountered: