Spaces:
Sleeping
Sleeping
| # from dotenv import load_dotenv | |
| # load_dotenv() | |
| import io | |
| import os | |
| import warnings | |
| from PIL import Image | |
| from stability_sdk import client | |
| import stability_sdk.interfaces.gooseai.generation.generation_pb2 as generation | |
| import gradio as gr | |
| # STABILITY_KEY = os.getenv('STABILITY_KEY') | |
| # STABILITY_HOST = os.getenv('STABILITY_HOST') | |
| STABILITY_KEY = os.environ.get("STABILITY_KEY") | |
| STABILITY_HOST = os.environ.get('STABILITY_HOST') | |
| # Set up our connection to the API. | |
| stability_api = client.StabilityInference( | |
| key=STABILITY_KEY, # API Key reference. | |
| verbose=True, # Print debug messages. | |
| engine="stable-diffusion-v1-5", # Set the engine to use for generation. For SD 2.0 use "stable-diffusion-v2-0". | |
| # Available engines: stable-diffusion-v1 stable-diffusion-v1-5 stable-diffusion-512-v2-0 stable-diffusion-768-v2-0 stable-inpainting-v1-0 stable-inpainting-512-v2-0 | |
| ) | |
| prompt = "clear portrait of a superhero concept from avengers, supercool!!, background hyper detailed, character concept, full body, dynamic pose, intricate, highly detailed, digital painting, artstation, concept art, smooth, sharp focus, illustration, beautiful face" | |
| def img2img(prompt, img): | |
| #@title <a name="Step 5"><font color="#FFFFFF">5. Set up an initial image based on our previous generation, and use a prompt to convert it into a crayon drawing.</font></a> | |
| # init_img = Image.open(base64_string).convert("RGB") | |
| # img = init_img.resize((768, 512)) | |
| img = img.resize((768, 512)) | |
| # Set up our initial generation parameters. | |
| answers = stability_api.generate( | |
| prompt=prompt, | |
| init_image=img, # Assign our previously generated img as our Initial Image for transformation. | |
| start_schedule=0.6, # Set the strength of our prompt in relation to our initial image. | |
| seed=123467458, # If attempting to transform an image that was previously generated with our API, | |
| # initial images benefit from having their own distinct seed rather than using the seed of the original image generation. | |
| steps=30, # Amount of inference steps performed on image generation. Defaults to 30. | |
| cfg_scale=8.0, # Influences how strongly your generation is guided to match your prompt. | |
| # Setting this value higher increases the strength in which it tries to match your prompt. | |
| # Defaults to 7.0 if not specified. | |
| width=512, # Generation width, defaults to 512 if not included. | |
| height=512, # Generation height, defaults to 512 if not included. | |
| samples=1 | |
| # sampler=generation.SAMPLER_K_DPMPP_2M # Choose which sampler we want to denoise our generation with. | |
| # Defaults to k_dpmpp_2m if not specified. Clip Guidance only supports ancestral samplers. | |
| # (Available Samplers: ddim, plms, k_euler, k_euler_ancestral, k_heun, k_dpm_2, k_dpm_2_ancestral, k_dpmpp_2s_ancestral, k_lms, k_dpmpp_2m) | |
| ) | |
| # Set up our warning to print to the console if the adult content classifier is tripped. | |
| # If adult content classifier is not tripped, display generated image. | |
| for resp in answers: | |
| for artifact in resp.artifacts: | |
| if artifact.finish_reason == generation.FILTER: | |
| warnings.warn( | |
| "Your request activated the API's safety filters and could not be processed." | |
| "Please modify the prompt and try again.") | |
| if artifact.type == generation.ARTIFACT_IMAGE: | |
| img2 = Image.open(io.BytesIO(artifact.binary)) # Set our resulting initial image generation as 'img2' to avoid overwriting our previous 'img' generation. | |
| # display(img2) | |
| return img2 | |
| gr.Interface(fn=img2img, inputs=[gr.Text(value=prompt), gr.Image(type='pil')], | |
| outputs=gr.Image(type='pil')).launch(debug=True) | |
| # def greet(name): | |
| # return "Hello " + name + "!!" | |
| # iface = gr.Interface(fn=greet, inputs="text", outputs="text") | |
| # iface.launch() |