Spaces:
Runtime error
Runtime error
File size: 2,619 Bytes
79ded7b 69c3e7a 79ded7b 6b361a8 79ded7b |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 |
import gradio as gr
import requests
from PIL import Image
from pathlib import Path
from io import BytesIO
# Diffusers
import diffusers
from diffusers import (
FlaxControlNetModel,
FlaxStableDiffusionControlNetPipeline
)
from diffusers.utils import load_image
# Pytorch
import torch
# Numpy
import numpy as np
# Jax
import jax
import jax.numpy as jnp
from jax import pmap
# Flax
import flax
from flax.jax_utils import replicate
from flax.training.common_utils import shard
def create_key(seed=0):
return jax.random.PRNGKey(seed)
def image_grid(imgs, rows, cols):
w, h = imgs[0].size
grid = Image.new("RGB", size=(cols * w, rows * h))
for i, img in enumerate(imgs):
grid.paste(img, box=(i % cols * w, i // cols * h))
return grid
# load control net and stable diffusion v1-5
controlnet, controlnet_params = FlaxControlNetModel.from_pretrained(
"jax-diffuser-event/learner/trained_model_v0.1", from_flax=True, dtype=jnp.float32
)
pipe, params = FlaxStableDiffusionControlNetPipeline.from_pretrained(
"runwayml/stable-diffusion-v1-5",
controlnet=controlnet,
from_pt=True,
dtype=jnp.float32,
safety_checker=None,
)
# inference function takes prompt, negative prompt and image
def infer(prompts, negative_prompts, image):
params["controlnet"] = controlnet_params
num_samples = 1 # jax.device_count()
rng = create_key(0)
rng = jax.random.split(rng, jax.device_count())
battlemap_image = load_image(image)
prompt_ids = pipe.prepare_text_inputs([prompts] * num_samples)
negative_prompt_ids = pipe.prepare_text_inputs([negative_prompts] * num_samples)
processed_image = pipe.prepare_image_inputs([battlemap_image] * num_samples)
p_params = replicate(params)
prompt_ids = shard(prompt_ids)
negative_prompt_ids = shard(negative_prompt_ids)
processed_image = shard(processed_image)
output = pipe(
prompt_ids=prompt_ids,
image=processed_image,
params=p_params,
# params = params,
prng_seed=rng,
num_inference_steps=50,
neg_prompt_ids=negative_prompt_ids,
jit=True,
).images
output_image = pipe.numpy_to_pil(
np.asarray(output.reshape((num_samples,) + output.shape[-3:]))
)
return output_image
title = "ControlNet on Battlemaps"
description = "This is a demo on ControlNet based on Bettlemaps."
# you need to pass inputs and outputs according to inference function
gr.Interface(
fn=infer,
inputs=["text", "text", "image"],
outputs="gallery",
title=title,
description=description,
).launch()
|