Instructions to use furaidosu/enjuto-qwen-image-lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use furaidosu/enjuto-qwen-image-lora with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Qwen/Qwen-Image", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("furaidosu/enjuto-qwen-image-lora") prompt = "a man and a woman dressed in formal clothes standing in a forest surrounded by candles" image = pipe(prompt).images[0] - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
Choquinlabs commited on
Update README.md
Browse files
README.md
CHANGED
|
@@ -16,7 +16,18 @@ pipeline_tag: text-to-image
|
|
| 16 |
|
| 17 |
|
| 18 |
## Model description
|
|
|
|
| 19 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 20 |
|
| 21 |
|
| 22 |
|
|
|
|
| 16 |
|
| 17 |
|
| 18 |
## Model description
|
| 19 |
+
This model was trained using 91 synthetic images mimicking the style of Enjuto Mojamuto (by Joaquín Reyes).
|
| 20 |
|
| 21 |
+
I initially took images of Enjuto, reconstructed them in HD with qwen-image-edit, and trained a model in Wavespeed, with poor results and overfitting.
|
| 22 |
+
|
| 23 |
+
With this initial pooer model, I generated new images and manually edited them in Photoshop to generate a new set of images that were varied in colors, characters, animals, and settings.
|
| 24 |
+
|
| 25 |
+
I used this synthetic dataset to generate this new model in FAL.
|
| 26 |
+
|
| 27 |
+
More about the great artist Joaquin Reyes artwork:
|
| 28 |
+
|
| 29 |
+
* https://es.wikipedia.org/wiki/Joaqu%C3%ADn_Reyes
|
| 30 |
+
* https://www.instagram.com/enjuto_mojamuto/?hl=es
|
| 31 |
|
| 32 |
|
| 33 |
|