Hugging Face
Models
Datasets
Spaces
Buckets
Docs
Enterprise
Pricing
Website
Tasks
HuggingChat
Collections
Languages
Organizations
Community
Blog
Posts
Daily Papers
Hardware
Learn
Discord
Forum
GitHub
Solutions
Team & Enterprise
Hugging Face PRO
Enterprise Support
Inference Providers
Inference Endpoints
Storage Buckets
Log In
Sign Up
smile-forge
/
moss-image-onnx
Like
0
Follow
Smile Forge
2
Text-to-Image
ONNX
onnxruntime
moss-image
lora
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
Copy to bucket
main
moss-image-onnx
6.87 GB
Ctrl+K
Ctrl+K
1 contributor
History:
3 commits
AdamJones
Add a LoRA's branch in fp16 where its projection stays fp16: about a gigabyte less with a LoRA
1b6c049
verified
2 days ago
decoder
MOSS-Image-SFT for ONNX Runtime on CUDA: 8-bit denoiser, decoder and curated LoRA adapters
2 days ago
denoiser
Add a LoRA's branch in fp16 where its projection stays fp16: about a gigabyte less with a LoRA
2 days ago
loras
MOSS-Image-SFT for ONNX Runtime on CUDA: 8-bit denoiser, decoder and curated LoRA adapters
2 days ago
.gitattributes
Safe
2.2 kB
MOSS-Image-SFT for ONNX Runtime on CUDA: 8-bit denoiser, decoder and curated LoRA adapters
2 days ago
Build-MossImage.ps1
Safe
4.61 kB
MOSS-Image-SFT for ONNX Runtime on CUDA: 8-bit denoiser, decoder and curated LoRA adapters
2 days ago
Compare-MossEncoder.ps1
Safe
2.22 kB
MOSS-Image-SFT for ONNX Runtime on CUDA: 8-bit denoiser, decoder and curated LoRA adapters
2 days ago
MossImage.Pins.ps1
Safe
3.8 kB
MOSS-Image-SFT for ONNX Runtime on CUDA: 8-bit denoiser, decoder and curated LoRA adapters
2 days ago
README.md
11.9 kB
Add a LoRA's branch in fp16 where its projection stays fp16: about a gigabyte less with a LoRA
2 days ago
build_moss_image.py
38.5 kB
Add a LoRA's branch in fp16 where its projection stays fp16: about a gigabyte less with a LoRA
2 days ago
check-loras.json
1.39 kB
Add a LoRA's branch in fp16 where its projection stays fp16: about a gigabyte less with a LoRA
2 days ago
check.json
504 Bytes
Add a LoRA's branch in fp16 where its projection stays fp16: about a gigabyte less with a LoRA
2 days ago
check_moss_image.py
Safe
15.1 kB
MOSS-Image-SFT for ONNX Runtime on CUDA: 8-bit denoiser, decoder and curated LoRA adapters
2 days ago
check_moss_loras.py
Safe
7.98 kB
MOSS-Image-SFT for ONNX Runtime on CUDA: 8-bit denoiser, decoder and curated LoRA adapters
2 days ago
compare_moss_encoder.py
Safe
13.9 kB
MOSS-Image-SFT for ONNX Runtime on CUDA: 8-bit denoiser, decoder and curated LoRA adapters
2 days ago
convert_moss_loras.py
Safe
7.35 kB
MOSS-Image-SFT for ONNX Runtime on CUDA: 8-bit denoiser, decoder and curated LoRA adapters
2 days ago
loras.json
4.31 kB
Add a LoRA's branch in fp16 where its projection stays fp16: about a gigabyte less with a LoRA
2 days ago
