split samplers into one more files for k-diffusion

modules/sd_samplers.py

-from collections import deque
-import torch
-import inspect
-import k_diffusion.sampling
-import ldm.models.diffusion.ddim
-import ldm.models.diffusion.plms
-from modules import prompt_parser, devices, sd_samplers_common, sd_samplers_compvis
-
-from modules.shared import opts, state
-import modules.shared as shared
-from modules.script_callbacks import CFGDenoiserParams, cfg_denoiser_callback
+from modules import sd_samplers_compvis, sd_samplers_kdiffusion, shared
 
 # imports for functions that previously were here and are used by other modules
 from modules.sd_samplers_common import samples_to_image_grid, sample_to_image
 
-
-samplers_k_diffusion = [
-    ('Euler a', 'sample_euler_ancestral', ['k_euler_a', 'k_euler_ancestral'], {}),
-    ('Euler', 'sample_euler', ['k_euler'], {}),
-    ('LMS', 'sample_lms', ['k_lms'], {}),
-    ('Heun', 'sample_heun', ['k_heun'], {}),
-    ('DPM2', 'sample_dpm_2', ['k_dpm_2'], {'discard_next_to_last_sigma': True}),
-    ('DPM2 a', 'sample_dpm_2_ancestral', ['k_dpm_2_a'], {'discard_next_to_last_sigma': True}),
-    ('DPM++ 2S a', 'sample_dpmpp_2s_ancestral', ['k_dpmpp_2s_a'], {}),
-    ('DPM++ 2M', 'sample_dpmpp_2m', ['k_dpmpp_2m'], {}),
-    ('DPM++ SDE', 'sample_dpmpp_sde', ['k_dpmpp_sde'], {}),
-    ('DPM fast', 'sample_dpm_fast', ['k_dpm_fast'], {}),
-    ('DPM adaptive', 'sample_dpm_adaptive', ['k_dpm_ad'], {}),
-    ('LMS Karras', 'sample_lms', ['k_lms_ka'], {'scheduler': 'karras'}),
-    ('DPM2 Karras', 'sample_dpm_2', ['k_dpm_2_ka'], {'scheduler': 'karras', 'discard_next_to_last_sigma': True}),
-    ('DPM2 a Karras', 'sample_dpm_2_ancestral', ['k_dpm_2_a_ka'], {'scheduler': 'karras', 'discard_next_to_last_sigma': True}),
-    ('DPM++ 2S a Karras', 'sample_dpmpp_2s_ancestral', ['k_dpmpp_2s_a_ka'], {'scheduler': 'karras'}),
-    ('DPM++ 2M Karras', 'sample_dpmpp_2m', ['k_dpmpp_2m_ka'], {'scheduler': 'karras'}),
-    ('DPM++ SDE Karras', 'sample_dpmpp_sde', ['k_dpmpp_sde_ka'], {'scheduler': 'karras'}),
-]
-
-samplers_data_k_diffusion = [
-    sd_samplers_common.SamplerData(label, lambda model, funcname=funcname: KDiffusionSampler(funcname, model), aliases, options)
-    for label, funcname, aliases, options in samplers_k_diffusion
-    if hasattr(k_diffusion.sampling, funcname)
-]
-
 all_samplers = [
-    *samplers_data_k_diffusion,
-    sd_samplers_common.SamplerData('DDIM', lambda model: sd_samplers_compvis.VanillaStableDiffusionSampler(ldm.models.diffusion.ddim.DDIMSampler, model), [], {}),
-    sd_samplers_common.SamplerData('PLMS', lambda model: sd_samplers_compvis.VanillaStableDiffusionSampler(ldm.models.diffusion.plms.PLMSSampler, model), [], {}),
+    *sd_samplers_kdiffusion.samplers_data_k_diffusion,
+    *sd_samplers_compvis.samplers_data_compvis,
 ]
 all_samplers_map = {x.name: x for x in all_samplers}
 
@@ -69,8 +31,8 @@ def create_sampler(name, model):
 def set_samplers():
     global samplers, samplers_for_img2img
 
-    hidden = set(opts.hide_samplers)
-    hidden_img2img = set(opts.hide_samplers + ['PLMS'])
+    hidden = set(shared.opts.hide_samplers)
+    hidden_img2img = set(shared.opts.hide_samplers + ['PLMS'])
 
     samplers = [x for x in all_samplers if x.name not in hidden]
     samplers_for_img2img = [x for x in all_samplers if x.name not in hidden_img2img]
@@ -83,257 +45,3 @@ def set_samplers():
 
 
 set_samplers()
-
-sampler_extra_params = {
-    'sample_euler': ['s_churn', 's_tmin', 's_tmax', 's_noise'],
-    'sample_heun': ['s_churn', 's_tmin', 's_tmax', 's_noise'],
-    'sample_dpm_2': ['s_churn', 's_tmin', 's_tmax', 's_noise'],
-}
-
-
-class CFGDenoiser(torch.nn.Module):
-    def __init__(self, model):
-        super().__init__()
-        self.inner_model = model
-        self.mask = None
-        self.nmask = None
-        self.init_latent = None
-        self.step = 0
-
-    def combine_denoised(self, x_out, conds_list, uncond, cond_scale):
-        denoised_uncond = x_out[-uncond.shape[0]:]
-        denoised = torch.clone(denoised_uncond)
-
-        for i, conds in enumerate(conds_list):
-            for cond_index, weight in conds:
-                denoised[i] += (x_out[cond_index] - denoised_uncond[i]) * (weight * cond_scale)
-
-        return denoised
-
-    def forward(self, x, sigma, uncond, cond, cond_scale, image_cond):
-        if state.interrupted or state.skipped:
-            raise sd_samplers_common.InterruptedException
-
-        conds_list, tensor = prompt_parser.reconstruct_multicond_batch(cond, self.step)
-        uncond = prompt_parser.reconstruct_cond_batch(uncond, self.step)
-
-        batch_size = len(conds_list)
-        repeats = [len(conds_list[i]) for i in range(batch_size)]
-
-        x_in = torch.cat([torch.stack([x[i] for _ in range(n)]) for i, n in enumerate(repeats)] + [x])
-        image_cond_in = torch.cat([torch.stack([image_cond[i] for _ in range(n)]) for i, n in enumerate(repeats)] + [image_cond])
-        sigma_in = torch.cat([torch.stack([sigma[i] for _ in range(n)]) for i, n in enumerate(repeats)] + [sigma])
-
-        denoiser_params = CFGDenoiserParams(x_in, image_cond_in, sigma_in, state.sampling_step, state.sampling_steps)
-        cfg_denoiser_callback(denoiser_params)
-        x_in = denoiser_params.x
-        image_cond_in = denoiser_params.image_cond
-        sigma_in = denoiser_params.sigma
-
-        if tensor.shape[1] == uncond.shape[1]:
-            cond_in = torch.cat([tensor, uncond])
-
-            if shared.batch_cond_uncond:
-                x_out = self.inner_model(x_in, sigma_in, cond={"c_crossattn": [cond_in], "c_concat": [image_cond_in]})
-            else:
-                x_out = torch.zeros_like(x_in)
-                for batch_offset in range(0, x_out.shape[0], batch_size):
-                    a = batch_offset
-                    b = a + batch_size
-                    x_out[a:b] = self.inner_model(x_in[a:b], sigma_in[a:b], cond={"c_crossattn": [cond_in[a:b]], "c_concat": [image_cond_in[a:b]]})
-        else:
-            x_out = torch.zeros_like(x_in)
-            batch_size = batch_size*2 if shared.batch_cond_uncond else batch_size
-            for batch_offset in range(0, tensor.shape[0], batch_size):
-                a = batch_offset
-                b = min(a + batch_size, tensor.shape[0])
-                x_out[a:b] = self.inner_model(x_in[a:b], sigma_in[a:b], cond={"c_crossattn": [tensor[a:b]], "c_concat": [image_cond_in[a:b]]})
-
-            x_out[-uncond.shape[0]:] = self.inner_model(x_in[-uncond.shape[0]:], sigma_in[-uncond.shape[0]:], cond={"c_crossattn": [uncond], "c_concat": [image_cond_in[-uncond.shape[0]:]]})
-
-        devices.test_for_nans(x_out, "unet")
-
-        if opts.live_preview_content == "Prompt":
-            sd_samplers_common.store_latent(x_out[0:uncond.shape[0]])
-        elif opts.live_preview_content == "Negative prompt":
-            sd_samplers_common.store_latent(x_out[-uncond.shape[0]:])
-
-        denoised = self.combine_denoised(x_out, conds_list, uncond, cond_scale)
-
-        if self.mask is not None:
-            denoised = self.init_latent * self.mask + self.nmask * denoised
-
-        self.step += 1
-
-        return denoised
-
-
-class TorchHijack:
-    def __init__(self, sampler_noises):
-        # Using a deque to efficiently receive the sampler_noises in the same order as the previous index-based
-        # implementation.
-        self.sampler_noises = deque(sampler_noises)
-
-    def __getattr__(self, item):
-        if item == 'randn_like':
-            return self.randn_like
-
-        if hasattr(torch, item):
-            return getattr(torch, item)
-
-        raise AttributeError("'{}' object has no attribute '{}'".format(type(self).__name__, item))
-
-    def randn_like(self, x):
-        if self.sampler_noises:
-            noise = self.sampler_noises.popleft()
-            if noise.shape == x.shape:
-                return noise
-
-        if x.device.type == 'mps':
-            return torch.randn_like(x, device=devices.cpu).to(x.device)
-        else:
-            return torch.randn_like(x)
-
-
-class KDiffusionSampler:
-    def __init__(self, funcname, sd_model):
-        denoiser = k_diffusion.external.CompVisVDenoiser if sd_model.parameterization == "v" else k_diffusion.external.CompVisDenoiser
-
-        self.model_wrap = denoiser(sd_model, quantize=shared.opts.enable_quantization)
-        self.funcname = funcname
-        self.func = getattr(k_diffusion.sampling, self.funcname)
-        self.extra_params = sampler_extra_params.get(funcname, [])
-        self.model_wrap_cfg = CFGDenoiser(self.model_wrap)
-        self.sampler_noises = None
-        self.stop_at = None
-        self.eta = None
-        self.default_eta = 1.0
-        self.config = None
-        self.last_latent = None
-
-        self.conditioning_key = sd_model.model.conditioning_key
-
-    def callback_state(self, d):
-        step = d['i']
-        latent = d["denoised"]
-        if opts.live_preview_content == "Combined":
-            sd_samplers_common.store_latent(latent)
-        self.last_latent = latent
-
-        if self.stop_at is not None and step > self.stop_at:
-            raise sd_samplers_common.InterruptedException
-
-        state.sampling_step = step
-        shared.total_tqdm.update()
-
-    def launch_sampling(self, steps, func):
-        state.sampling_steps = steps
-        state.sampling_step = 0
-
-        try:
-            return func()
-        except sd_samplers_common.InterruptedException:
-            return self.last_latent
-
-    def number_of_needed_noises(self, p):
-        return p.steps
-
-    def initialize(self, p):
-        self.model_wrap_cfg.mask = p.mask if hasattr(p, 'mask') else None
-        self.model_wrap_cfg.nmask = p.nmask if hasattr(p, 'nmask') else None
-        self.model_wrap_cfg.step = 0
-        self.eta = p.eta or opts.eta_ancestral
-
-        k_diffusion.sampling.torch = TorchHijack(self.sampler_noises if self.sampler_noises is not None else [])
-
-        extra_params_kwargs = {}
-        for param_name in self.extra_params:
-            if hasattr(p, param_name) and param_name in inspect.signature(self.func).parameters:
-                extra_params_kwargs[param_name] = getattr(p, param_name)
-
-        if 'eta' in inspect.signature(self.func).parameters:
-            extra_params_kwargs['eta'] = self.eta
-
-        return extra_params_kwargs
-
-    def get_sigmas(self, p, steps):
-        discard_next_to_last_sigma = self.config is not None and self.config.options.get('discard_next_to_last_sigma', False)
-        if opts.always_discard_next_to_last_sigma and not discard_next_to_last_sigma:
-            discard_next_to_last_sigma = True
-            p.extra_generation_params["Discard penultimate sigma"] = True
-
-        steps += 1 if discard_next_to_last_sigma else 0
-
-        if p.sampler_noise_scheduler_override:
-            sigmas = p.sampler_noise_scheduler_override(steps)
-        elif self.config is not None and self.config.options.get('scheduler', None) == 'karras':
-            sigma_min, sigma_max = (0.1, 10) if opts.use_old_karras_scheduler_sigmas else (self.model_wrap.sigmas[0].item(), self.model_wrap.sigmas[-1].item())
-
-            sigmas = k_diffusion.sampling.get_sigmas_karras(n=steps, sigma_min=sigma_min, sigma_max=sigma_max, device=shared.device)
-        else:
-            sigmas = self.model_wrap.get_sigmas(steps)
-
-        if discard_next_to_last_sigma:
-            sigmas = torch.cat([sigmas[:-2], sigmas[-1:]])
-
-        return sigmas
-
-    def sample_img2img(self, p, x, noise, conditioning, unconditional_conditioning, steps=None, image_conditioning=None):
-        steps, t_enc = sd_samplers_common.setup_img2img_steps(p, steps)
-
-        sigmas = self.get_sigmas(p, steps)
-
-        sigma_sched = sigmas[steps - t_enc - 1:]
-        xi = x + noise * sigma_sched[0]
-        
-        extra_params_kwargs = self.initialize(p)
-        if 'sigma_min' in inspect.signature(self.func).parameters:
-            ## last sigma is zero which isn't allowed by DPM Fast & Adaptive so taking value before last
-            extra_params_kwargs['sigma_min'] = sigma_sched[-2]
-        if 'sigma_max' in inspect.signature(self.func).parameters:
-            extra_params_kwargs['sigma_max'] = sigma_sched[0]
-        if 'n' in inspect.signature(self.func).parameters:
-            extra_params_kwargs['n'] = len(sigma_sched) - 1
-        if 'sigma_sched' in inspect.signature(self.func).parameters:
-            extra_params_kwargs['sigma_sched'] = sigma_sched
-        if 'sigmas' in inspect.signature(self.func).parameters:
-            extra_params_kwargs['sigmas'] = sigma_sched
-
-        self.model_wrap_cfg.init_latent = x
-        self.last_latent = x
-
-        samples = self.launch_sampling(t_enc + 1, lambda: self.func(self.model_wrap_cfg, xi, extra_args={
-            'cond': conditioning, 
-            'image_cond': image_conditioning, 
-            'uncond': unconditional_conditioning, 
-            'cond_scale': p.cfg_scale
-        }, disable=False, callback=self.callback_state, **extra_params_kwargs))
-
-        return samples
-
-    def sample(self, p, x, conditioning, unconditional_conditioning, steps=None, image_conditioning = None):
-        steps = steps or p.steps
-
-        sigmas = self.get_sigmas(p, steps)
-
-        x = x * sigmas[0]
-
-        extra_params_kwargs = self.initialize(p)
-        if 'sigma_min' in inspect.signature(self.func).parameters:
-            extra_params_kwargs['sigma_min'] = self.model_wrap.sigmas[0].item()
-            extra_params_kwargs['sigma_max'] = self.model_wrap.sigmas[-1].item()
-            if 'n' in inspect.signature(self.func).parameters:
-                extra_params_kwargs['n'] = steps
-        else:
-            extra_params_kwargs['sigmas'] = sigmas
-
-        self.last_latent = x
-        samples = self.launch_sampling(steps, lambda: self.func(self.model_wrap_cfg, x, extra_args={
-            'cond': conditioning, 
-            'image_cond': image_conditioning, 
-            'uncond': unconditional_conditioning, 
-            'cond_scale': p.cfg_scale
-        }, disable=False, callback=self.callback_state, **extra_params_kwargs))
-
-        return samples
-

modules/sd_samplers_common.py

-from collections import namedtuple, deque
+from collections import namedtuple
 import numpy as np
 import torch
 from PIL import Image
@@ -64,6 +64,7 @@ class InterruptedException(BaseException):
 
 
 # MPS fix for randn in torchsde
+# XXX move this to separate file for MPS
 def torchsde_randn(size, dtype, device, seed):
     if device.type == 'mps':
         generator = torch.Generator(devices.cpu).manual_seed(int(seed))

modules/sd_samplers_compvis.py

 import math
+import ldm.models.diffusion.ddim
+import ldm.models.diffusion.plms
 
 import numpy as np
 import torch
@@ -7,6 +9,12 @@ from modules.shared import state
 from modules import sd_samplers_common, prompt_parser, shared
 
 
+samplers_data_compvis = [
+    sd_samplers_common.SamplerData('DDIM', lambda model: VanillaStableDiffusionSampler(ldm.models.diffusion.ddim.DDIMSampler, model), [], {}),
+    sd_samplers_common.SamplerData('PLMS', lambda model: VanillaStableDiffusionSampler(ldm.models.diffusion.plms.PLMSSampler, model), [], {}),
+]
+
+
 class VanillaStableDiffusionSampler:
     def __init__(self, constructor, sd_model):
         self.sampler = constructor(sd_model)

modules/sd_samplers_kdiffusion.py

@@ -2,18 +2,12 @@ from collections import deque
 import torch
 import inspect
 import k_diffusion.sampling
-import ldm.models.diffusion.ddim
-import ldm.models.diffusion.plms
 from modules import prompt_parser, devices, sd_samplers_common, sd_samplers_compvis
 
 from modules.shared import opts, state
 import modules.shared as shared
 from modules.script_callbacks import CFGDenoiserParams, cfg_denoiser_callback
 
-# imports for functions that previously were here and are used by other modules
-from modules.sd_samplers_common import samples_to_image_grid, sample_to_image
-
-
 samplers_k_diffusion = [
     ('Euler a', 'sample_euler_ancestral', ['k_euler_a', 'k_euler_ancestral'], {}),
     ('Euler', 'sample_euler', ['k_euler'], {}),
@@ -40,50 +34,6 @@ samplers_data_k_diffusion = [
     if hasattr(k_diffusion.sampling, funcname)
 ]
 
-all_samplers = [
-    *samplers_data_k_diffusion,
-    sd_samplers_common.SamplerData('DDIM', lambda model: sd_samplers_compvis.VanillaStableDiffusionSampler(ldm.models.diffusion.ddim.DDIMSampler, model), [], {}),
-    sd_samplers_common.SamplerData('PLMS', lambda model: sd_samplers_compvis.VanillaStableDiffusionSampler(ldm.models.diffusion.plms.PLMSSampler, model), [], {}),
-]
-all_samplers_map = {x.name: x for x in all_samplers}
-
-samplers = []
-samplers_for_img2img = []
-samplers_map = {}
-
-
-def create_sampler(name, model):
-    if name is not None:
-        config = all_samplers_map.get(name, None)
-    else:
-        config = all_samplers[0]
-
-    assert config is not None, f'bad sampler name: {name}'
-
-    sampler = config.constructor(model)
-    sampler.config = config
-
-    return sampler
-
-
-def set_samplers():
-    global samplers, samplers_for_img2img
-
-    hidden = set(opts.hide_samplers)
-    hidden_img2img = set(opts.hide_samplers + ['PLMS'])
-
-    samplers = [x for x in all_samplers if x.name not in hidden]
-    samplers_for_img2img = [x for x in all_samplers if x.name not in hidden_img2img]
-
-    samplers_map.clear()
-    for sampler in all_samplers:
-        samplers_map[sampler.name.lower()] = sampler.name
-        for alias in sampler.aliases:
-            samplers_map[alias.lower()] = sampler.name
-
-
-set_samplers()
-
 sampler_extra_params = {
     'sample_euler': ['s_churn', 's_tmin', 's_tmax', 's_noise'],
     'sample_heun': ['s_churn', 's_tmin', 's_tmax', 's_noise'],
@@ -92,6 +42,13 @@ sampler_extra_params = {
 
 
 class CFGDenoiser(torch.nn.Module):
+    """
+    Classifier free guidance denoiser. A wrapper for stable diffusion model (specifically for unet)
+    that can take a noisy picture and produce a noise-free picture using two guidances (prompts)
+    instead of one. Originally, the second prompt is just an empty string, but we use non-empty
+    negative prompt.
+    """
+
     def __init__(self, model):
         super().__init__()
         self.inner_model = model