diff options
38 files changed, 959 insertions, 405 deletions
@@ -88,7 +88,7 @@ A browser interface based on Gradio library for Stable Diffusion. - [Alt-Diffusion](https://arxiv.org/abs/2211.06679) support - see [wiki](https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Features#alt-diffusion) for instructions
- Now without any bad letters!
- Load checkpoints in safetensors format
-- Eased resolution restriction: generated image's domension must be a multiple of 8 rather than 64
+- Eased resolution restriction: generated image's dimension must be a multiple of 8 rather than 64
- Now with a license!
- Reorder elements in the UI from settings screen
@@ -169,5 +169,6 @@ Licenses for borrowed code can be found in `Settings -> Licenses` screen, and al - UniPC sampler - Wenliang Zhao - https://github.com/wl-zhao/UniPC
- TAESD - Ollin Boer Bohan - https://github.com/madebyollin/taesd
- LyCORIS - KohakuBlueleaf
+- Restart sampling - lambertae - https://github.com/Newbeeer/diffusion_restart_sampling
- Initial Gradio script - posted on 4chan by an Anonymous user. Thank you Anonymous user.
- (You)
diff --git a/javascript/hints.js b/javascript/hints.js index 4167cb28..6de9372e 100644 --- a/javascript/hints.js +++ b/javascript/hints.js @@ -190,3 +190,14 @@ onUiUpdate(function(mutationRecords) { tooltipCheckTimer = setTimeout(processTooltipCheckNodes, 1000); } }); + +onUiLoaded(function() { + for (var comp of window.gradio_config.components) { + if (comp.props.webui_tooltip && comp.props.elem_id) { + var elem = gradioApp().getElementById(comp.props.elem_id); + if (elem) { + elem.title = comp.props.webui_tooltip; + } + } + } +}); diff --git a/javascript/ui.js b/javascript/ui.js index d70a681b..abf23a78 100644 --- a/javascript/ui.js +++ b/javascript/ui.js @@ -152,7 +152,11 @@ function submit() { showSubmitButtons('txt2img', false); var id = randomId(); - localStorage.setItem("txt2img_task_id", id); + try { + localStorage.setItem("txt2img_task_id", id); + } catch (e) { + console.warn(`Failed to save txt2img task id to localStorage: ${e}`); + } requestProgress(id, gradioApp().getElementById('txt2img_gallery_container'), gradioApp().getElementById('txt2img_gallery'), function() { showSubmitButtons('txt2img', true); @@ -171,7 +175,11 @@ function submit_img2img() { showSubmitButtons('img2img', false); var id = randomId(); - localStorage.setItem("img2img_task_id", id); + try { + localStorage.setItem("img2img_task_id", id); + } catch (e) { + console.warn(`Failed to save img2img task id to localStorage: ${e}`); + } requestProgress(id, gradioApp().getElementById('img2img_gallery_container'), gradioApp().getElementById('img2img_gallery'), function() { showSubmitButtons('img2img', true); @@ -191,8 +199,6 @@ function restoreProgressTxt2img() { showRestoreProgressButton("txt2img", false); var id = localStorage.getItem("txt2img_task_id"); - id = localStorage.getItem("txt2img_task_id"); - if (id) { requestProgress(id, gradioApp().getElementById('txt2img_gallery_container'), gradioApp().getElementById('txt2img_gallery'), function() { showSubmitButtons('txt2img', true); diff --git a/modules/api/api.py b/modules/api/api.py index 606db179..908c4514 100644 --- a/modules/api/api.py +++ b/modules/api/api.py @@ -15,7 +15,7 @@ from fastapi.encoders import jsonable_encoder from secrets import compare_digest import modules.shared as shared -from modules import sd_samplers, deepbooru, sd_hijack, images, scripts, ui, postprocessing, errors, restart +from modules import sd_samplers, deepbooru, sd_hijack, images, scripts, ui, postprocessing, errors, restart, shared_items from modules.api import models from modules.shared import opts from modules.processing import StableDiffusionProcessingTxt2Img, StableDiffusionProcessingImg2Img, process_images @@ -197,6 +197,7 @@ class Api: self.add_api_route("/sdapi/v1/prompt-styles", self.get_prompt_styles, methods=["GET"], response_model=List[models.PromptStyleItem]) self.add_api_route("/sdapi/v1/embeddings", self.get_embeddings, methods=["GET"], response_model=models.EmbeddingsResponse) self.add_api_route("/sdapi/v1/refresh-checkpoints", self.refresh_checkpoints, methods=["POST"]) + self.add_api_route("/sdapi/v1/refresh-vae", self.refresh_vae, methods=["POST"]) self.add_api_route("/sdapi/v1/create/embedding", self.create_embedding, methods=["POST"], response_model=models.CreateResponse) self.add_api_route("/sdapi/v1/create/hypernetwork", self.create_hypernetwork, methods=["POST"], response_model=models.CreateResponse) self.add_api_route("/sdapi/v1/preprocess", self.preprocess, methods=["POST"], response_model=models.PreprocessResponse) @@ -343,6 +344,7 @@ class Api: processed = process_images(p) finally: shared.state.end() + shared.total_tqdm.clear() b64images = list(map(encode_pil_to_base64, processed.images)) if send_images else [] @@ -402,6 +404,7 @@ class Api: processed = process_images(p) finally: shared.state.end() + shared.total_tqdm.clear() b64images = list(map(encode_pil_to_base64, processed.images)) if send_images else [] @@ -608,6 +611,10 @@ class Api: with self.queue_lock: shared.refresh_checkpoints() + def refresh_vae(self): + with self.queue_lock: + shared_items.refresh_vae_list() + def create_embedding(self, args: dict): try: shared.state.begin(job="create_embedding") diff --git a/modules/call_queue.py b/modules/call_queue.py index 61aa240f..f2eb17d6 100644 --- a/modules/call_queue.py +++ b/modules/call_queue.py @@ -3,7 +3,7 @@ import html import threading
import time
-from modules import shared, progress, errors
+from modules import shared, progress, errors, devices
queue_lock = threading.Lock()
@@ -75,6 +75,8 @@ def wrap_gradio_call(func, extra_outputs=None, add_stats=False): error_message = f'{type(e).__name__}: {e}'
res = extra_outputs_array + [f"<div class='error'>{html.escape(error_message)}</div>"]
+ devices.torch_gc()
+
shared.state.skipped = False
shared.state.interrupted = False
shared.state.job_count = 0
diff --git a/modules/cmd_args.py b/modules/cmd_args.py index 1262f1a4..64f21e01 100644 --- a/modules/cmd_args.py +++ b/modules/cmd_args.py @@ -67,6 +67,7 @@ parser.add_argument("--opt-sdp-no-mem-attention", action='store_true', help="pre parser.add_argument("--disable-opt-split-attention", action='store_true', help="prefer no cross-attention layer optimization for automatic choice of optimization")
parser.add_argument("--disable-nan-check", action='store_true', help="do not check if produced images/latent spaces have nans; useful for running without a checkpoint in CI")
parser.add_argument("--use-cpu", nargs='+', help="use CPU as torch device for specified modules", default=[], type=str.lower)
+parser.add_argument("--disable-model-loading-ram-optimization", action='store_true', help="disable an optimization that reduces RAM use when loading a model")
parser.add_argument("--listen", action='store_true', help="launch gradio with 0.0.0.0 as server name, allowing to respond to network requests")
parser.add_argument("--port", type=int, help="launch gradio with given server port, you need root/admin rights for ports < 1024, defaults to 7860 if available", default=None)
parser.add_argument("--show-negative-prompt", action='store_true', help="does not do anything", default=False)
diff --git a/modules/devices.py b/modules/devices.py index 57e51da3..00a00b18 100644 --- a/modules/devices.py +++ b/modules/devices.py @@ -3,7 +3,7 @@ import contextlib from functools import lru_cache import torch -from modules import errors +from modules import errors, rng_philox if sys.platform == "darwin": from modules import mac_specific @@ -71,14 +71,17 @@ def enable_tf32(): torch.backends.cudnn.allow_tf32 = True - errors.run(enable_tf32, "Enabling TF32") -cpu = torch.device("cpu") -device = device_interrogate = device_gfpgan = device_esrgan = device_codeformer = None -dtype = torch.float16 -dtype_vae = torch.float16 -dtype_unet = torch.float16 +cpu: torch.device = torch.device("cpu") +device: torch.device = None +device_interrogate: torch.device = None +device_gfpgan: torch.device = None +device_esrgan: torch.device = None +device_codeformer: torch.device = None +dtype: torch.dtype = torch.float16 +dtype_vae: torch.dtype = torch.float16 +dtype_unet: torch.dtype = torch.float16 unet_needs_upcast = False @@ -90,23 +93,87 @@ def cond_cast_float(input): return input.float() if unet_needs_upcast else input +nv_rng = None + + def randn(seed, shape): + """Generate a tensor with random numbers from a normal distribution using seed. + + Uses the seed parameter to set the global torch seed; to generate more with that seed, use randn_like/randn_without_seed.""" + from modules.shared import opts - torch.manual_seed(seed) + manual_seed(seed) + + if opts.randn_source == "NV": + return torch.asarray(nv_rng.randn(shape), device=device) + if opts.randn_source == "CPU" or device.type == 'mps': return torch.randn(shape, device=cpu).to(device) + return torch.randn(shape, device=device) +def randn_local(seed, shape): + """Generate a tensor with random numbers from a normal distribution using seed. + + Does not change the global random number generator. You can only generate the seed's first tensor using this function.""" + + from modules.shared import opts + + if opts.randn_source == "NV": + rng = rng_philox.Generator(seed) + return torch.asarray(rng.randn(shape), device=device) + + local_device = cpu if opts.randn_source == "CPU" or device.type == 'mps' else device + local_generator = torch.Generator(local_device).manual_seed(int(seed)) + return torch.randn(shape, device=local_device, generator=local_generator).to(device) + + +def randn_like(x): + """Generate a tensor with random numbers from a normal distribution using the previously initialized genrator. + + Use either randn() or manual_seed() to initialize the generator.""" + + from modules.shared import opts + + if opts.randn_source == "NV": + return torch.asarray(nv_rng.randn(x.shape), device=x.device, dtype=x.dtype) + + if opts.randn_source == "CPU" or x.device.type == 'mps': + return torch.randn_like(x, device=cpu).to(x.device) + + return torch.randn_like(x) + + def randn_without_seed(shape): + """Generate a tensor with random numbers from a normal distribution using the previously initialized genrator. + + Use either randn() or manual_seed() to initialize the generator.""" + from modules.shared import opts + if opts.randn_source == "NV": + return torch.asarray(nv_rng.randn(shape), device=device) + if opts.randn_source == "CPU" or device.type == 'mps': return torch.randn(shape, device=cpu).to(device) + return torch.randn(shape, device=device) +def manual_seed(seed): + """Set up a global random number generator using the specified seed.""" + from modules.shared import opts + + if opts.randn_source == "NV": + global nv_rng + nv_rng = rng_philox.Generator(seed) + return + + torch.manual_seed(seed) + + def autocast(disable=False): from modules import shared diff --git a/modules/errors.py b/modules/errors.py index 5271a9fe..dffabe45 100644 --- a/modules/errors.py +++ b/modules/errors.py @@ -14,7 +14,8 @@ def record_exception(): if exception_records and exception_records[-1] == e:
return
- exception_records.append((e, tb))
+ from modules import sysinfo
+ exception_records.append(sysinfo.format_exception(e, tb))
if len(exception_records) > 5:
exception_records.pop(0)
diff --git a/modules/extras.py b/modules/extras.py index e9c0263e..2a310ae3 100644 --- a/modules/extras.py +++ b/modules/extras.py @@ -7,7 +7,7 @@ import json import torch
import tqdm
-from modules import shared, images, sd_models, sd_vae, sd_models_config
+from modules import shared, images, sd_models, sd_vae, sd_models_config, errors
from modules.ui_common import plaintext_to_html
import gradio as gr
import safetensors.torch
@@ -72,7 +72,20 @@ def to_half(tensor, enable): return tensor
-def run_modelmerger(id_task, primary_model_name, secondary_model_name, tertiary_model_name, interp_method, multiplier, save_as_half, custom_name, checkpoint_format, config_source, bake_in_vae, discard_weights, save_metadata):
+def read_metadata(primary_model_name, secondary_model_name, tertiary_model_name):
+ metadata = {}
+
+ for checkpoint_name in [primary_model_name, secondary_model_name, tertiary_model_name]:
+ checkpoint_info = sd_models.checkpoints_list.get(checkpoint_name, None)
+ if checkpoint_info is None:
+ continue
+
+ metadata.update(checkpoint_info.metadata)
+
+ return json.dumps(metadata, indent=4, ensure_ascii=False)
+
+
+def run_modelmerger(id_task, primary_model_name, secondary_model_name, tertiary_model_name, interp_method, multiplier, save_as_half, custom_name, checkpoint_format, config_source, bake_in_vae, discard_weights, save_metadata, add_merge_recipe, copy_metadata_fields, metadata_json):
shared.state.begin(job="model-merge")
def fail(message):
@@ -241,11 +254,25 @@ def run_modelmerger(id_task, primary_model_name, secondary_model_name, tertiary_ shared.state.textinfo = "Saving"
print(f"Saving to {output_modelname}...")
- metadata = None
+ metadata = {}
+
+ if save_metadata and copy_metadata_fields:
+ if primary_model_info:
+ metadata.update(primary_model_info.metadata)
+ if secondary_model_info:
+ metadata.update(secondary_model_info.metadata)
+ if tertiary_model_info:
+ metadata.update(tertiary_model_info.metadata)
if save_metadata:
- metadata = {"format": "pt"}
+ try:
+ metadata.update(json.loads(metadata_json))
+ except Exception as e:
+ errors.display(e, "readin metadata from json")
+
+ metadata["format"] = "pt"
+ if save_metadata and add_merge_recipe:
merge_recipe = {
"type": "webui", # indicate this model was merged with webui's built-in merger
"primary_model_hash": primary_model_info.sha256,
@@ -261,7 +288,6 @@ def run_modelmerger(id_task, primary_model_name, secondary_model_name, tertiary_ "is_inpainting": result_is_inpainting_model,
"is_instruct_pix2pix": result_is_instruct_pix2pix_model
}
- metadata["sd_merge_recipe"] = json.dumps(merge_recipe)
sd_merge_models = {}
@@ -281,11 +307,12 @@ def run_modelmerger(id_task, primary_model_name, secondary_model_name, tertiary_ if tertiary_model_info:
add_model_metadata(tertiary_model_info)
+ metadata["sd_merge_recipe"] = json.dumps(merge_recipe)
metadata["sd_merge_models"] = json.dumps(sd_merge_models)
_, extension = os.path.splitext(output_modelname)
if extension.lower() == ".safetensors":
- safetensors.torch.save_file(theta_0, output_modelname, metadata=metadata)
+ safetensors.torch.save_file(theta_0, output_modelname, metadata=metadata if len(metadata)>0 else None)
else:
torch.save(theta_0, output_modelname)
diff --git a/modules/img2img.py b/modules/img2img.py index a811e7a4..68e415ef 100644 --- a/modules/img2img.py +++ b/modules/img2img.py @@ -10,7 +10,6 @@ from modules import sd_samplers, images as imgutil from modules.generation_parameters_copypaste import create_override_settings_dict, parse_generation_parameters
from modules.processing import Processed, StableDiffusionProcessingImg2Img, process_images
from modules.shared import opts, state
-from modules.images import save_image
import modules.shared as shared
import modules.processing as processing
from modules.ui import plaintext_to_html
@@ -18,9 +17,10 @@ import modules.scripts def process_batch(p, input_dir, output_dir, inpaint_mask_dir, args, to_scale=False, scale_by=1.0, use_png_info=False, png_info_props=None, png_info_dir=None):
+ output_dir = output_dir.strip()
processing.fix_seed(p)
- images = list(shared.walk_files(input_dir, allowed_extensions=(".png", ".jpg", ".jpeg", ".webp")))
+ images = list(shared.walk_files(input_dir, allowed_extensions=(".png", ".jpg", ".jpeg", ".webp", ".tif", ".tiff")))
is_inpaint_batch = False
if inpaint_mask_dir:
@@ -32,11 +32,6 @@ def process_batch(p, input_dir, output_dir, inpaint_mask_dir, args, to_scale=Fal print(f"Will process {len(images)} images, creating {p.n_iter * p.batch_size} new images for each.")
- save_normally = output_dir == ''
-
- p.do_not_save_grid = True
- p.do_not_save_samples = not save_normally
-
state.job_count = len(images) * p.n_iter
# extract "default" params to use in case getting png info fails
@@ -111,21 +106,14 @@ def process_batch(p, input_dir, output_dir, inpaint_mask_dir, args, to_scale=Fal proc = modules.scripts.scripts_img2img.run(p, *args)
if proc is None:
- proc = process_images(p)
-
- for n, processed_image in enumerate(proc.images):
- filename = image_path.stem
- infotext = proc.infotext(p, n)
- relpath = os.path.dirname(os.path.relpath(image, input_dir))
-
- if n > 0:
- filename += f"-{n}"
-
- if not save_normally:
- os.makedirs(os.path.join(output_dir, relpath), exist_ok=True)
- if processed_image.mode == 'RGBA':
- processed_image = processed_image.convert("RGB")
- save_image(processed_image, os.path.join(output_dir, relpath), None, extension=opts.samples_format, info=infotext, forced_filename=filename, save_to_dirs=False)
+ if output_dir:
+ p.outpath_samples = output_dir
+ p.override_settings['save_to_dirs'] = False
+ if p.n_iter > 1 or p.batch_size > 1:
+ p.override_settings['samples_filename_pattern'] = f'{image_path.stem}-[generation_number]'
+ else:
+ p.override_settings['samples_filename_pattern'] = f'{image_path.stem}'
+ process_images(p)
def img2img(id_task: str, mode: int, prompt: str, negative_prompt: str, prompt_styles, init_img, sketch, init_img_with_mask, inpaint_color_sketch, inpaint_color_sketch_orig, init_img_inpaint, init_mask_inpaint, steps: int, sampler_index: int, mask_blur: int, mask_alpha: float, inpainting_fill: int, restore_faces: bool, tiling: bool, n_iter: int, batch_size: int, cfg_scale: float, image_cfg_scale: float, denoising_strength: float, seed: int, subseed: int, subseed_strength: float, seed_resize_from_h: int, seed_resize_from_w: int, seed_enable_extras: bool, selected_scale_tab: int, height: int, width: int, scale_by: float, resize_mode: int, inpaint_full_res: bool, inpaint_full_res_padding: int, inpainting_mask_invert: int, img2img_batch_input_dir: str, img2img_batch_output_dir: str, img2img_batch_inpaint_mask_dir: str, override_settings_texts, img2img_batch_use_png_info: bool, img2img_batch_png_info_props: list, img2img_batch_png_info_dir: str, request: gr.Request, *args):
diff --git a/modules/processing.py b/modules/processing.py index b0992ee1..8f34c8b4 100644 --- a/modules/processing.py +++ b/modules/processing.py @@ -492,7 +492,7 @@ def create_random_tensors(shape, seeds, subseeds=None, subseed_strength=0.0, see noise_shape = shape if seed_resize_from_h <= 0 or seed_resize_from_w <= 0 else (shape[0], seed_resize_from_h//8, seed_resize_from_w//8)
subnoise = None
- if subseeds is not None:
+ if subseeds is not None and subseed_strength != 0:
subseed = 0 if i >= len(subseeds) else subseeds[i]
subnoise = devices.randn(subseed, noise_shape)
@@ -524,7 +524,7 @@ def create_random_tensors(shape, seeds, subseeds=None, subseed_strength=0.0, see cnt = p.sampler.number_of_needed_noises(p)
if eta_noise_seed_delta > 0:
- torch.manual_seed(seed + eta_noise_seed_delta)
+ devices.manual_seed(seed + eta_noise_seed_delta)
for j in range(cnt):
sampler_noises[j].append(devices.randn_without_seed(tuple(noise_shape)))
@@ -636,7 +636,7 @@ def create_infotext(p, all_prompts, all_seeds, all_subseeds, comments=None, iter "Token merging ratio": None if token_merging_ratio == 0 else token_merging_ratio,
"Token merging ratio hr": None if not enable_hr or token_merging_ratio_hr == 0 else token_merging_ratio_hr,
"Init image hash": getattr(p, 'init_img_hash', None),
- "RNG": opts.randn_source if opts.randn_source != "GPU" else None,
+ "RNG": opts.randn_source if opts.randn_source != "GPU" and opts.randn_source != "NV" else None,
"NGMS": None if p.s_min_uncond == 0 else p.s_min_uncond,
**p.extra_generation_params,
"Version": program_version() if opts.add_version_to_infotext else None,
@@ -1348,6 +1348,7 @@ class StableDiffusionProcessingImg2Img(StableDiffusionProcessing): image = image.to(shared.device, dtype=devices.dtype_vae)
self.init_latent = self.sd_model.get_first_stage_encoding(self.sd_model.encode_first_stage(image))
+ devices.torch_gc()
if self.resize_mode == 3:
self.init_latent = torch.nn.functional.interpolate(self.init_latent, size=(self.height // opt_f, self.width // opt_f), mode="bilinear")
diff --git a/modules/prompt_parser.py b/modules/prompt_parser.py index 203ae1ac..8169a459 100644 --- a/modules/prompt_parser.py +++ b/modules/prompt_parser.py @@ -19,7 +19,7 @@ prompt: (emphasized | scheduled | alternate | plain | WHITESPACE)* !emphasized: "(" prompt ")"
| "(" prompt ":" prompt ")"
| "[" prompt "]"
-scheduled: "[" [prompt ":"] prompt ":" [WHITESPACE] NUMBER "]"
+scheduled: "[" [prompt ":"] prompt ":" [WHITESPACE] NUMBER [WHITESPACE] "]"
alternate: "[" prompt ("|" prompt)+ "]"
WHITESPACE: /\s+/
plain: /([^\\\[\]():|]|\\.)+/
@@ -60,11 +60,11 @@ def get_learned_conditioning_prompt_schedules(prompts, steps): class CollectSteps(lark.Visitor):
def scheduled(self, tree):
- tree.children[-1] = float(tree.children[-1])
- if tree.children[-1] < 1:
- tree.children[-1] *= steps
- tree.children[-1] = min(steps, int(tree.children[-1]))
- res.append(tree.children[-1])
+ tree.children[-2] = float(tree.children[-2])
+ if tree.children[-2] < 1:
+ tree.children[-2] *= steps
+ tree.children[-2] = min(steps, int(tree.children[-2]))
+ res.append(tree.children[-2])
def alternate(self, tree):
res.extend(range(1, steps+1))
@@ -75,7 +75,7 @@ def get_learned_conditioning_prompt_schedules(prompts, steps): def at_step(step, tree):
class AtStep(lark.Transformer):
def scheduled(self, args):
- before, after, _, when = args
+ before, after, _, when, _ = args
yield before or () if step <= when else after
def alternate(self, args):
yield next(args[(step - 1)%len(args)])
@@ -333,7 +333,7 @@ re_attention = re.compile(r""" \\|
\(|
\[|
-:([+-]?[.\d]+)\)|
+:\s*([+-]?[.\d]+)\s*\)|
\)|
]|
[^\\()\[\]:]+|
diff --git a/modules/rng_philox.py b/modules/rng_philox.py new file mode 100644 index 00000000..5532cf9d --- /dev/null +++ b/modules/rng_philox.py @@ -0,0 +1,102 @@ +"""RNG imitiating torch cuda randn on CPU. You are welcome.
+
+Usage:
+
+```
+g = Generator(seed=0)
+print(g.randn(shape=(3, 4)))
+```
+
+Expected output:
+```
+[[-0.92466259 -0.42534415 -2.6438457 0.14518388]
+ [-0.12086647 -0.57972564 -0.62285122 -0.32838709]
+ [-1.07454231 -0.36314407 -1.67105067 2.26550497]]
+```
+"""
+
+import numpy as np
+
+philox_m = [0xD2511F53, 0xCD9E8D57]
+philox_w = [0x9E3779B9, 0xBB67AE85]
+
+two_pow32_inv = np.array([2.3283064e-10], dtype=np.float32)
+two_pow32_inv_2pi = np.array([2.3283064e-10 * 6.2831855], dtype=np.float32)
+
+
+def uint32(x):
+ """Converts (N,) np.uint64 array into (2, N) np.unit32 array."""
+ return x.view(np.uint32).reshape(-1, 2).transpose(1, 0)
+
+
+def philox4_round(counter, key):
+ """A single round of the Philox 4x32 random number generator."""
+
+ v1 = uint32(counter[0].astype(np.uint64) * philox_m[0])
+ v2 = uint32(counter[2].astype(np.uint64) * philox_m[1])
+
+ counter[0] = v2[1] ^ counter[1] ^ key[0]
+ counter[1] = v2[0]
+ counter[2] = v1[1] ^ counter[3] ^ key[1]
+ counter[3] = v1[0]
+
+
+def philox4_32(counter, key, rounds=10):
+ """Generates 32-bit random numbers using the Philox 4x32 random number generator.
+
+ Parameters:
+ counter (numpy.ndarray): A 4xN array of 32-bit integers representing the counter values (offset into generation).
+ key (numpy.ndarray): A 2xN array of 32-bit integers representing the key values (seed).
+ rounds (int): The number of rounds to perform.
+
+ Returns:
+ numpy.ndarray: A 4xN array of 32-bit integers containing the generated random numbers.
+ """
+
+ for _ in range(rounds - 1):
+ philox4_round(counter, key)
+
+ key[0] = key[0] + philox_w[0]
+ key[1] = key[1] + philox_w[1]
+
+ philox4_round(counter, key)
+ return counter
+
+
+def box_muller(x, y):
+ """Returns just the first out of two numbers generated by Box–Muller transform algorithm."""
+ u = x * two_pow32_inv + two_pow32_inv / 2
+ v = y * two_pow32_inv_2pi + two_pow32_inv_2pi / 2
|