Create README.md

README.md

@@ -1,29 +1,46 @@
 ---
+license: other
+license_name: flux-1-dev-non-commercial-license
+license_link: https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md
+language:
+- en
 tags:
-  - text-to-image
-  - lora
-  - diffusers
-  - template:diffusion-lora
-widget:
-- text: CINFACE
-  output:
-    url: images/replicate-prediction-6r76m444g1rme0cq3gr9vf87jm.webp
-base_model: black-forest-labs/FLUX.1-dev
+- flux
+- diffusers
+- lora
+- replicate
+base_model: "black-forest-labs/FLUX.1-dev"
+pipeline_tag: text-to-image
+# widget:
+#   - text: >-
+#       prompt
+#     output:
+#       url: https://...
 instance_prompt: CINFACE
-
 ---
-# cinface-lora
+
+# Cinface-lora
 
 <Gallery />
 
+Trained on Replicate using:
 
-## Trigger words
+https://replicate.com/ostris/flux-dev-lora-trainer/train
 
+
+## Trigger words
 You should use `CINFACE` to trigger the image generation.
 
 
-## Download model
+## Use it with the [🧨 diffusers library](https://github.com/huggingface/diffusers)
+
+```py
+from diffusers import AutoPipelineForText2Image
+import torch
 
-Weights for this model are available in Safetensors format.
+pipeline = AutoPipelineForText2Image.from_pretrained('black-forest-labs/FLUX.1-dev', torch_dtype=torch.float16).to('cuda')
+pipeline.load_lora_weights('pennypacker/cinface-lora', weight_name='flux-lora.safetensors')
+image = pipeline('your prompt').images[0]
+```
 
-[Download](/pennypacker/cinface-lora/tree/main) them in the Files & versions tab.
+For more details, including weighting, merging and fusing LoRAs, check the [documentation on loading LoRAs in diffusers](https://huggingface.co/docs/diffusers/main/en/using-diffusers/loading_adapters)