|
--- |
|
tags: |
|
- text-to-image |
|
- stable-diffusion |
|
- kviai |
|
- midjourney |
|
- lora |
|
- dalle-3 |
|
- dalle |
|
- deepvision |
|
- diffusers |
|
widget: |
|
- text: reimagine the ZX Spectrum Game MANIC MINER as a 3D modern style game |
|
output: |
|
url: https://www.instantaiprompt.com/wp-content/uploads/2023/12/manic-miner.jpg |
|
- text: >- |
|
cute Harry Potter, pixar animated movie style, dramatic lighting, standing |
|
outside Hogwarts. |
|
output: |
|
url: >- |
|
https://www.instantaiprompt.com/wp-content/uploads/2023/12/harry-potter-ai-hp.jpg |
|
- text: >- |
|
close up of a Quokka, national geographic style photography, stunning image, |
|
golden hour |
|
output: |
|
url: https://www.instantaiprompt.com/wp-content/uploads/2023/12/ai-quokka.jpg |
|
base_model: runwayml/stable-diffusion-v1-5 |
|
instance_prompt: <lora:Dall-e_3_0.3-v2-000003> |
|
license: openrail |
|
language: |
|
- en |
|
- fr |
|
- ru |
|
pipeline_tag: text-to-image |
|
library_name: diffusers |
|
--- |
|
# DALL-E 3 XL |
|
|
|
<Gallery /> |
|
|
|
## Model description |
|
|
|
This is a test model like Dall-E 3. |
|
|
|
Estimated generateion time is ~ 60 seconds on gpu |
|
|
|
By KVI Kontent |
|
|
|
## Usage |
|
|
|
You can try out model using Huggingface Interface API, and here is how: |
|
```Python |
|
import requests |
|
import io |
|
from PIL import * |
|
|
|
API_URL = "https://api-inference.huggingface.co/models/Kvikontent/kviimager2.0" |
|
headers = {"Authorization": "Bearer huggingface_api_token"} |
|
|
|
def query(payload): |
|
response = requests.post(API_URL, headers=headers, json=payload) |
|
return response.content |
|
|
|
image_bytes = query({ |
|
"inputs": "Astronaut riding a horse", |
|
}) |
|
|
|
image = Image.open(io.BytesIO(image_bytes)) |
|
image.save("generated_image.jpg") |
|
``` |
|
or using Diffusers library (requires pytorch and transformers too): |
|
```Python |
|
from diffusers import DiffusionPipeline |
|
import io |
|
from PIL import * |
|
|
|
pipeline = DiffusionPipeline.from_pretrained("stablediffusionapi/juggernaut-xl-v5") |
|
pipeline.load_lora_weights("Kvikontent/kviimager2.0") |
|
|
|
prompt = "Astronaut riding a horse" |
|
|
|
image_bytes = pipeline(prompt) |
|
image = Image.open(io.BytesIO(image_bytes)) |
|
image.save("generated_image.jpg") |
|
``` |
|
|
|
## Credits |
|
|
|
* Author - Vasiliy Katsyka |
|
* Company - [KVIAI](https://hf.co/kviai) |
|
* Licence - Openrail |
|
|
|
## Official demo |
|
|
|
You can use official demo on Spaces: [try](https://huggingface.co/spaces/kvikontent/kviimager2.0). |
