Upload README.md with huggingface_hub

README.md

@@ -1,73 +1,57 @@
 ---
 base_model: krea/Krea-2-Raw
-library_name: diffusers
-license: apache-2.0
-instance_prompt: dark fantasy ink style
-widget: []
 tags:
 - text-to-image
-- diffusers-training
 - diffusers
 - lora
 - krea2
-- krea2-diffusers
 - template:sd-lora
+license: apache-2.0
+instance_prompt: "dark fantasy ink style"
+widget:
+- text: "A colossal skeletal dragon coiled around a crumbling gothic spire under a blood-red moon, dark fantasy ink style"
+  output:
+    url: sample_0.png
+- text: "A hooded plague doctor walking through a fog-drenched cobblestone alleyway lit by a single flickering lantern, dark fantasy ink style"
+  output:
+    url: sample_1.png
+- text: "An ornate, decaying throne room overgrown with black thorny vines and shimmering ghostly embers, dark fantasy ink style"
+  output:
+    url: sample_2.png
 ---
 
-<!-- This model card has been generated automatically according to the information the training script had access to. You
-should probably proofread and complete it, then remove this comment. -->
-
-
-# Krea 2 DreamBooth LoRA - AllwaysFurious/classicdnd
+# Krea 2 LoRA — AllwaysFurious/classicdnd
 
 <Gallery />
 
-## Model description
+A DreamBooth-LoRA for **Krea 2**, trained on **Krea 2 RAW** and shown on **Krea 2 Turbo**. The samples below were generated with this LoRA on Turbo (8 steps).
 
-These are AllwaysFurious/classicdnd DreamBooth LoRA weights, trained on krea/Krea-2-Raw.
+## Trigger
 
-The weights were trained using [DreamBooth](https://dreambooth.github.io/) with the [Krea 2 diffusers trainer](https://github.com/huggingface/diffusers/blob/main/examples/dreambooth/README_krea2.md).
+Use the phrase `dark fantasy ink style` to invoke the concept.
 
-Krea 2 ships as two checkpoints: **RAW** (the non-distilled base you fine-tune on) and **Turbo** (an 8-step distilled checkpoint for fast, high-quality inference). Train your LoRA on RAW and run it on Turbo — LoRAs trained on RAW express strongly on Turbo.
+## Samples
 
-## Trigger words
+![sample](./sample_0.png)
 
-You should use `dark fantasy ink style` to trigger the image generation.
+> *"A colossal skeletal dragon coiled around a crumbling gothic spire under a blood-red moon, dark fantasy ink style"*
 
-## Download model
+![sample](./sample_1.png)
 
-[Download the *.safetensors LoRA](AllwaysFurious/classicdnd/tree/main) in the Files & versions tab.
+> *"A hooded plague doctor walking through a fog-drenched cobblestone alleyway lit by a single flickering lantern, dark fantasy ink style"*
 
-## Use it with the [🧨 diffusers library](https://github.com/huggingface/diffusers)
+![sample](./sample_2.png)
 
-```py
->>> import torch
->>> from diffusers import Krea2Pipeline
-
->>> # Load the LoRA onto Krea 2 Turbo (the distilled inference model)
->>> pipe = Krea2Pipeline.from_pretrained("krea/Krea-2-Turbo", torch_dtype=torch.bfloat16).to("cuda")
->>> pipe.load_lora_weights("AllwaysFurious/classicdnd")
-
->>> # Turbo recipe: 8 steps, no classifier-free guidance
->>> image = pipe("dark fantasy ink style", num_inference_steps=8, guidance_scale=0.0).images[0]
->>> image.save("output.png")
-```
+> *"An ornate, decaying throne room overgrown with black thorny vines and shimmering ghostly embers, dark fantasy ink style"*
 
-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)
+## Use it with diffusers
 
+```py
+import torch
+from diffusers import Krea2Pipeline
 
-## Intended uses & limitations
-
-#### How to use
-
-```python
-# TODO: add an example code snippet for running this diffusion pipeline
+pipe = Krea2Pipeline.from_pretrained("krea/Krea-2-Turbo", torch_dtype=torch.bfloat16).to("cuda")
+pipe.load_lora_weights("AllwaysFurious/classicdnd")
+image = pipe("A colossal skeletal dragon coiled around a crumbling gothic spire under a blood-red moon, dark fantasy ink style", num_inference_steps=8, guidance_scale=0.0).images[0]
+image.save("output.png")
 ```
-
-#### Limitations and bias
-
-[TODO: provide examples of latent issues and potential remediations]
-
-## Training details
-
-[TODO: describe the data used to train the model]