Instructions to use crotai/incate with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use crotai/incate with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-xl-base-1.0", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("crotai/incate") prompt = "Ultra-detailed macro wildlife photography of a green chameleon facing the camera, centered symmetrical composition, extreme close-up, sharp focus on eyes and facial scales, intricate skin texture with visible micro scales, natural green and teal color variations, subtle orange accents around eyes, realistic reptile skin detail, vibrant natural colors, soft diffused daylight, shallow depth of field, creamy blurred green leaf background, cinematic bokeh, high dynamic range, professional DSLR photography, 100mm macro lens, f/2.8, photorealistic, ultra high resolution, crisp clarity, natural lighting, no artificial glow" image = pipe(prompt).images[0] - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
| tags: | |
| - text-to-image | |
| - lora | |
| - diffusers | |
| - template:diffusion-lora | |
| widget: | |
| - output: | |
| url: images/unnamed.jpg | |
| text: >- | |
| Ultra-detailed macro wildlife photography of a green chameleon facing the | |
| camera, centered symmetrical composition, extreme close-up, sharp focus on | |
| eyes and facial scales, intricate skin texture with visible micro scales, | |
| natural green and teal color variations, subtle orange accents around eyes, | |
| realistic reptile skin detail, vibrant natural colors, soft diffused | |
| daylight, shallow depth of field, creamy blurred green leaf background, | |
| cinematic bokeh, high dynamic range, professional DSLR photography, 100mm | |
| macro lens, f/2.8, photorealistic, ultra high resolution, crisp clarity, | |
| natural lighting, no artificial glow | |
| parameters: | |
| negative_prompt: >- | |
| low quality, blurry, soft focus, oversharpened, low resolution, pixelated, | |
| jpeg artifacts, cartoon, anime, illustration, painting, cgi, 3d render, | |
| unreal engine, plastic skin, wax texture, fake scales, distorted anatomy, | |
| extra eyes, mutated face, deformed mouth, cross-eyed, flat lighting, harsh | |
| flash, overexposed, underexposed, color banding, oversaturated, | |
| monochrome, unnatural colors, motion blur, noise, grainy, watermark, logo, | |
| text | |
| base_model: stabilityai/stable-diffusion-xl-base-1.0 | |
| instance_prompt: null | |
| license: mit | |
| # incate | |
| <Gallery /> | |
| ## Model description | |
| This model was trained on a dataset of over 1,013 images with similar sizes. It is a LoRA model trained using PEFT, so please use it appropriately. | |
| ## Download model | |
| [Download](/crotai/incate/tree/main) them in the Files & versions tab. | |