Upload README.md with huggingface_hub

README.md

@@ -1,75 +1,106 @@
 ---
-base_model:
-- krea/Krea-2-Turbo
-- krea/Krea-2-Raw
-library_name: diffusers
-license: apache-2.0
-instance_prompt: Beth1
-widget: []
+base_model: krea/Krea-2-Raw
 tags:
 - text-to-image
-- diffusers-training
 - diffusers
 - lora
 - krea2
-- krea2-diffusers
 - template:sd-lora
+license: apache-2.0
+instance_prompt: "Beth1"
+widget:
+- text: "A cinematic portrait of Beth1 as a cyberpunk hacker in a neon-drenched Tokyo alleyway, surrounded by holographic displays."
+  output:
+    url: sample_0.png
+- text: "Beth1 dressed as a regal Victorian queen, sitting on an ornate gold throne in a grand marble ballroom."
+  output:
+    url: sample_1.png
+- text: "A high-action shot of Beth1 as an astronaut floating in zero gravity inside a futuristic space station overlooking Saturn."
+  output:
+    url: sample_2.png
+- text: "Beth1 as a whimsical forest sprite with iridescent wings, perched on a giant glowing mushroom in a mystical woodland."
+  output:
+    url: sample_3.png
+- text: "A gritty, black-and-white noir scene featuring Beth1 as a 1940s detective standing under a streetlamp in the rain."
+  output:
+    url: sample_4.png
+- text: "Beth1 as a professional deep-sea diver exploring a bioluminescent coral reef with colorful alien fish."
+  output:
+    url: sample_5.png
+- text: "A vibrant oil painting of Beth1 as a Renaissance scholar in a dusty library filled with ancient scrolls."
+  output:
+    url: sample_6.png
+- text: "Beth1 as a post-apocalyptic scavenger wearing rusted armor, standing atop a ruined skyscraper in a desert wasteland."
+  output:
+    url: sample_7.png
+- text: "A cozy, sun-drenched scene of Beth1 baking bread in a rustic French country kitchen with flour in the air."
+  output:
+    url: sample_8.png
+- text: "Beth1 as a powerful sorceress casting a swirling vortex of cosmic energy amidst a field of floating crystals."
+  output:
+    url: sample_9.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 LoRA — Lonuhbow/beth
 
+<Gallery />
 
-# Krea 2 DreamBooth LoRA - Lonuhbow/beth
+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).
 
-<Gallery />
+## Trigger
 
-## Model description
+Use the token `Beth1` to invoke the concept.
 
-These are Lonuhbow/beth DreamBooth LoRA weights, trained on krea/Krea-2-Raw.
+## Samples
 
-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).
+![sample](./sample_0.png)
 
-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.
+> *"A cinematic portrait of Beth1 as a cyberpunk hacker in a neon-drenched Tokyo alleyway, surrounded by holographic displays."*
 
-## Trigger words
+![sample](./sample_1.png)
 
-You should use `Beth1` to trigger the image generation.
+> *"Beth1 dressed as a regal Victorian queen, sitting on an ornate gold throne in a grand marble ballroom."*
 
-## Download model
+![sample](./sample_2.png)
 
-[Download the *.safetensors LoRA](Lonuhbow/beth/tree/main) in the Files & versions tab.
+> *"A high-action shot of Beth1 as an astronaut floating in zero gravity inside a futuristic space station overlooking Saturn."*
 
-## Use it with the [🧨 diffusers library](https://github.com/huggingface/diffusers)
+![sample](./sample_3.png)
 
-```py
->>> import torch
->>> from diffusers import Krea2Pipeline
+> *"Beth1 as a whimsical forest sprite with iridescent wings, perched on a giant glowing mushroom in a mystical woodland."*
 
->>> # 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("Lonuhbow/beth")
+![sample](./sample_4.png)
 
->>> # Turbo recipe: 8 steps, no classifier-free guidance
->>> image = pipe("Beth1", num_inference_steps=8, guidance_scale=0.0).images[0]
->>> image.save("output.png")
-```
+> *"A gritty, black-and-white noir scene featuring Beth1 as a 1940s detective standing under a streetlamp in the rain."*
 
-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)
+![sample](./sample_5.png)
 
+> *"Beth1 as a professional deep-sea diver exploring a bioluminescent coral reef with colorful alien fish."*
 
-## Intended uses & limitations
+![sample](./sample_6.png)
 
-#### How to use
+> *"A vibrant oil painting of Beth1 as a Renaissance scholar in a dusty library filled with ancient scrolls."*
 
-```python
-# TODO: add an example code snippet for running this diffusion pipeline
-```
+![sample](./sample_7.png)
 
-#### Limitations and bias
+> *"Beth1 as a post-apocalyptic scavenger wearing rusted armor, standing atop a ruined skyscraper in a desert wasteland."*
 
-[TODO: provide examples of latent issues and potential remediations]
+![sample](./sample_8.png)
 
-## Training details
+> *"A cozy, sun-drenched scene of Beth1 baking bread in a rustic French country kitchen with flour in the air."*
 
-[TODO: describe the data used to train the model]
+![sample](./sample_9.png)
+
+> *"Beth1 as a powerful sorceress casting a swirling vortex of cosmic energy amidst a field of floating crystals."*
+
+## Use it with diffusers
+
+```py
+import torch
+from diffusers import Krea2Pipeline
+
+pipe = Krea2Pipeline.from_pretrained("krea/Krea-2-Turbo", torch_dtype=torch.bfloat16).to("cuda")
+pipe.load_lora_weights("Lonuhbow/beth")
+image = pipe("A cinematic portrait of Beth1 as a cyberpunk hacker in a neon-drenched Tokyo alleyway, surrounded by holographic displays.", num_inference_steps=8, guidance_scale=0.0).images[0]
+image.save("output.png")
+```