Update README.md
Browse files
README.md
CHANGED
|
@@ -12,12 +12,11 @@ base_model_relation: merge
|
|
| 12 |
pipeline_tag: text-to-image
|
| 13 |
---
|
| 14 |
|
| 15 |
-
# **FLUX.1-Merged**
|
| 16 |
|
| 17 |
-
|
| 18 |
-
and [`black-forest-labs/FLUX.1-schnell`](https://huggingface.co/black-forest-labs/FLUX.1-schnell).
|
| 19 |
|
| 20 |
-
# **
|
| 21 |
|
| 22 |
```python
|
| 23 |
from diffusers import FluxTransformer2DModel
|
|
@@ -98,4 +97,15 @@ image = pipeline(
|
|
| 98 |
generator=torch.manual_seed(0),
|
| 99 |
).images[0]
|
| 100 |
image.save("merged_flux.png")
|
| 101 |
-
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12 |
pipeline_tag: text-to-image
|
| 13 |
---
|
| 14 |
|
| 15 |
+
# **FLUX.1-Merged (FLUX.1-dev + FLUX.1-schnell)**
|
| 16 |
|
| 17 |
+
> FLUX.1-Merged is a repository offering the merged parameters of black-forest-labs/FLUX.1-dev and black-forest-labs/FLUX.1-schnell, two powerful text-to-image transformer models. By averaging the non-guidance parameters from both models and integrating the guidance components from FLUX.1-dev, this merge aims to deliver a model that combines the strengths of both—FLUX.1-dev’s high prompt fidelity and competitive visual quality, and FLUX.1-schnell’s enhancements such as greater speed or aesthetic tuning. The final checkpoint can be used for prompt-based image generation with the Diffusers library, providing efficient and high-quality outputs for creative and research applications. Detailed instructions for merging, saving, and using the model with Diffusers are included, allowing users to generate images from text prompts with improved performance leveraging innovations from both base models.
|
|
|
|
| 18 |
|
| 19 |
+
# **Sub-Memory-efficient merging code**
|
| 20 |
|
| 21 |
```python
|
| 22 |
from diffusers import FluxTransformer2DModel
|
|
|
|
| 97 |
generator=torch.manual_seed(0),
|
| 98 |
).images[0]
|
| 99 |
image.save("merged_flux.png")
|
| 100 |
+
```
|
| 101 |
+
|
| 102 |
+
---
|
| 103 |
+
|
| 104 |
+
|
| 105 |
+
## For more information, visit the documentation.
|
| 106 |
+
|
| 107 |
+
> Flux is a suite of state-of-the-art text-to-image generation models based on diffusion transformers, developed by Black Forest Labs. The models are designed for high-quality generative image tasks, including text-to-image, inpainting, outpainting, and advanced structure or depth-controlled workflows. Flux is available through the Hugging Face diffusers library.
|
| 108 |
+
|
| 109 |
+
For detailed guides, examples, and API refer to:
|
| 110 |
+
- **[Main Flux Pipeline Documentation](https://huggingface.co/docs/diffusers/main/en/api/pipelines/flux)**
|
| 111 |
+
- **[Flux Transformer Model Documentation](https://huggingface.co/docs/diffusers/main/en/api/models/flux_transformer)**
|