Instructions to use oliverbrown/ark-dinosaur-lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use oliverbrown/ark-dinosaur-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("stable-diffusion-v1-5/stable-diffusion-v1-5", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("oliverbrown/ark-dinosaur-lora") prompt = "arkdino, dinosaur, megalodon, gigantic prehistoric shark with powerful jaws, torpedo-shaped body, triangular dorsal fin, and crescent tail fin, 1 head, 2 pectoral fins, 1 dorsal fin, 1 tail fin, side profile, scientific field sketch, ark dossier, annotated notes, middle page crease " image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
ark-dinosaur-lora

- Prompt
- arkdino, dinosaur, megalodon, gigantic prehistoric shark with powerful jaws, torpedo-shaped body, triangular dorsal fin, and crescent tail fin, 1 head, 2 pectoral fins, 1 dorsal fin, 1 tail fin, side profile, scientific field sketch, ark dossier, annotated notes, middle page crease

- Prompt
- arkdino, dinosaur, argentavis, massive prehistoric bird with broad wings, sharp hooked beak, and strong talons, 1 head, 2 wings, 2 legs, 1 tail, feathered body, wings spread, side profile, scientific field sketch, ark dossier, annotated notes, middle page crease

- Prompt
- arkdino, dinosaur, tyrannosaurus rex, giant bipedal predator with massive jaws, muscular body, and long tail, 1 head, 2 short arms, 2 strong legs, 1 tail, side profile, scientific field sketch, ark dossier, annotated notes, middle page crease
Model description
First LoRa I have made using SD1.5 as the base model (my GPU does not have a lot of VRAM). This lora is used to generate ARK: Survival Evolved dossier style images, not ARK dinosaurs from the game itself. Workflow was tested in ComfyUI, more details about fine-tuning to come and more updates hopefully.
Link to Repo: https://github.com/oliverbrown1/ark-dossier-lora
Trigger words
You should use arkdino to trigger the image generation.
Download model
Download them in the Files & versions tab.
- Downloads last month
- 33
Model tree for oliverbrown/ark-dinosaur-lora
Base model
stable-diffusion-v1-5/stable-diffusion-v1-5