Instructions to use Rin247/MOSS-Image-SFT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Rin247/MOSS-Image-SFT with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Rin247/MOSS-Image-SFT", 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
Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
|
@@ -5,18 +5,16 @@ tags:
|
|
| 5 |
- diffusers
|
| 6 |
- mecha
|
| 7 |
- weight-only
|
| 8 |
-
- image
|
| 9 |
-
- text-to-image
|
| 10 |
library_name: diffusers
|
| 11 |
---
|
| 12 |
|
| 13 |
# MOSS-Image-SFT
|
| 14 |
|
| 15 |
-
Quantised media packages of
|
| 16 |
|
| 17 |
## MECHA Forge
|
| 18 |
|
| 19 |
-
MECHA
|
| 20 |
|
| 21 |
These media packages have been forged and optimized in the MECHA Forge.
|
| 22 |
Each one holds the Denoiser, Text Encoder, and VAE components packaged together for easier deployment.
|
|
@@ -26,6 +24,8 @@ Each one holds the Denoiser, Text Encoder, and VAE components packaged together
|
|
| 26 |
| Quant | Denoiser | Text encoder | VAE |
|
| 27 |
|---|---|---|---|
|
| 28 |
| FP4 | FP4 | FP4 | FP8 |
|
|
|
|
| 29 |
| INT4 | INT4 | INT4 | INT8 |
|
|
|
|
| 30 |
|
| 31 |
The VAE is shared between formats: FP4 reuses the FP8 file, INT4 reuses the INT8 file.
|
|
|
|
| 5 |
- diffusers
|
| 6 |
- mecha
|
| 7 |
- weight-only
|
|
|
|
|
|
|
| 8 |
library_name: diffusers
|
| 9 |
---
|
| 10 |
|
| 11 |
# MOSS-Image-SFT
|
| 12 |
|
| 13 |
+
Quantised media packages of \genmo/moss-image-sft\ (or the source model).
|
| 14 |
|
| 15 |
## MECHA Forge
|
| 16 |
|
| 17 |
+
MECHA \u2014 Model Engineering & Contextual Hearth Assembly
|
| 18 |
|
| 19 |
These media packages have been forged and optimized in the MECHA Forge.
|
| 20 |
Each one holds the Denoiser, Text Encoder, and VAE components packaged together for easier deployment.
|
|
|
|
| 24 |
| Quant | Denoiser | Text encoder | VAE |
|
| 25 |
|---|---|---|---|
|
| 26 |
| FP4 | FP4 | FP4 | FP8 |
|
| 27 |
+
| FP8 | FP8 | FP8 | FP8 |
|
| 28 |
| INT4 | INT4 | INT4 | INT8 |
|
| 29 |
+
| INT8 | INT8 | INT8 | INT8 |
|
| 30 |
|
| 31 |
The VAE is shared between formats: FP4 reuses the FP8 file, INT4 reuses the INT8 file.
|