Text-to-Image
Diffusers
Safetensors
MOSSImagePipeline
4bit
bitsandbytes
nf4
moss-image
8-bit precision
Instructions to use eramth/MOSS-Image-SFT-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use eramth/MOSS-Image-SFT-4bit with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("eramth/MOSS-Image-SFT-4bit", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
Download model_index.json from eramth/MOSS-Image-SFT-4bit: direct link, hf CLI and curl.
- Browser
- Download file 412 Bytes
-
https://huggingface.co/eramth/MOSS-Image-SFT-4bit/resolve/main/model_index.json
- Command line
-
hf download hf://eramth/MOSS-Image-SFT-4bit/model_index.json
-
curl -L -o model_index.json https://huggingface.co/eramth/MOSS-Image-SFT-4bit/resolve/main/model_index.json
412 Bytes
| { | |
| "_class_name": "MOSSImagePipeline", | |
| "_diffusers_version": "0.38.0", | |
| "scheduler": [ | |
| "pipeline_moss_image", | |
| "MOSSImageScheduler" | |
| ], | |
| "text_encoder": [ | |
| "transformers", | |
| "Qwen3_5Model" | |
| ], | |
| "tokenizer": [ | |
| "transformers", | |
| "Qwen2Tokenizer" | |
| ], | |
| "transformer": [ | |
| "pipeline_moss_image", | |
| "MOSSImageTransformer" | |
| ], | |
| "vae": [ | |
| "diffusers", | |
| "AutoencoderKLFlux2" | |
| ] | |
| } | |