From 94a659ee1f9061d97a431f0de2afee63c93e2cdd Mon Sep 17 00:00:00 2001 From: Vladimir Mandic Date: Thu, 2 Jan 2025 11:00:10 -0500 Subject: [PATCH] fix xyz with detailer, sd35 img2img Signed-off-by: Vladimir Mandic --- CHANGELOG.md | 7 +++++-- modules/postprocess/yolo.py | 24 +++++++++++------------- modules/processing.py | 2 +- modules/processing_args.py | 3 +++ modules/processing_class.py | 2 +- modules/sd_models.py | 2 +- modules/sd_samplers_diffusers.py | 5 +++++ scripts/xyz_grid_on.py | 2 ++ 8 files changed, 29 insertions(+), 18 deletions(-) diff --git a/CHANGELOG.md b/CHANGELOG.md index 7ecde280c..8a24d8ff5 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -1,6 +1,6 @@ # Change Log for SD.Next -## Update for 2025-01-01 +## Update for 2025-01-02 - [Allegro Video](https://huggingface.co/rhymes-ai/Allegro) - optimizations: full offload and quantization support @@ -18,8 +18,11 @@ - **Fixes**: - explict clear caches on model load - lock adetailer commit: `#a89c01d` - - xyzgrid fix progress calculation + - xyzgrid progress calculation + - xyzgrid detailer - vae tiling use default value if not set + - sd35 img2img + - samplers test for scale noise before using ## Update for 2024-12-31 diff --git a/modules/postprocess/yolo.py b/modules/postprocess/yolo.py index 3ee2406d1..4011147ec 100644 --- a/modules/postprocess/yolo.py +++ b/modules/postprocess/yolo.py @@ -1,5 +1,6 @@ from typing import TYPE_CHECKING import os +from copy import copy import numpy as np import gradio as gr from PIL import Image, ImageDraw @@ -259,23 +260,23 @@ def restore(self, np_image, p: processing.StableDiffusionProcessing = None): report = [{'label': i.label, 'score': i.score, 'size': f'{i.width}x{i.height}' } for i in items] shared.log.info(f'Detailer: model="{name}" items={report} args={items[0].args} denoise={p.denoising_strength} blur={p.mask_blur} width={p.width} height={p.height} padding={p.inpaint_full_res_padding}') - shared.log.debug(f'Detailer: prompt="{prompt}" negative="{negative}"') + # shared.log.debug(f'Detailer: prompt="{prompt}" negative="{negative}"') models_used.append(name) mask_all = [] p.state = '' prev_state = shared.state.job + pc = copy(p) for item in items: if item.mask is None: continue - p.init_images = [image] - p.image_mask = [item.mask] - # mask_all.append(item.mask) - p.recursion = True + pc.init_images = [image] + pc.image_mask = [item.mask] + pc.overlay_images = [] + pc.recursion = True shared.state.job = 'Detailer' - pp = processing.process_images_inner(p) - del p.recursion - p.overlay_images = None # skip applying overlay twice + pp = processing.process_images_inner(pc) + del pc.recursion if pp is not None and pp.images is not None and len(pp.images) > 0: image = pp.images[0] # update image to be reused for next item if len(pp.images) > 1: @@ -298,13 +299,10 @@ def restore(self, np_image, p: processing.StableDiffusionProcessing = None): if len(mask_all) > 0 and shared.opts.include_mask: from modules.control.util import blend p.image_mask = blend([np.array(m) for m in mask_all]) - # combined = blend([np_image, p.image_mask]) - # combined = Image.fromarray(combined) - # combined.save('/tmp/item.png') p.image_mask = Image.fromarray(p.image_mask) - if len(models_used) > 0: - shared.log.debug(f'Detailer processed: models={models_used}') + # if len(models_used) > 0: + # shared.log.debug(f'Detailer processed: models={models_used}') return np_image def ui(self, tab: str): diff --git a/modules/processing.py b/modules/processing.py index c85938268..23fde5dee 100644 --- a/modules/processing.py +++ b/modules/processing.py @@ -463,7 +463,7 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed: ipadapter.unapply(shared.sd_model, unload=getattr(p, 'ip_adapter_unload', False)) if shared.opts.include_mask: - if shared.opts.mask_apply_overlay and p.overlay_images is not None and len(p.overlay_images): + if shared.opts.mask_apply_overlay and p.overlay_images is not None and len(p.overlay_images) > 0: p.image_mask = create_binary_mask(p.overlay_images[0]) p.image_mask = ImageOps.invert(p.image_mask) output_images.append(p.image_mask) diff --git a/modules/processing_args.py b/modules/processing_args.py index f39537538..360928de7 100644 --- a/modules/processing_args.py +++ b/modules/processing_args.py @@ -307,6 +307,9 @@ def set_pipeline_args(p, model, prompts:list, negative_prompts:list, prompts_2:t if isinstance(args['image'], torch.Tensor) or isinstance(args['image'], np.ndarray): args['width'] = 8 * args['image'].shape[-1] args['height'] = 8 * args['image'].shape[-2] + elif isinstance(args['image'][0], torch.Tensor) or isinstance(args['image'][0], np.ndarray): + args['width'] = 8 * args['image'][0].shape[-1] + args['height'] = 8 * args['image'][0].shape[-2] else: args['width'] = 8 * math.ceil(args['image'][0].width / 8) args['height'] = 8 * math.ceil(args['image'][0].height / 8) diff --git a/modules/processing_class.py b/modules/processing_class.py index 96761d262..5960fea76 100644 --- a/modules/processing_class.py +++ b/modules/processing_class.py @@ -502,7 +502,7 @@ def init(self, all_prompts=None, all_seeds=None, all_subseeds=None): image = images.resize_image(self.resize_mode, image, self.width, self.height, upscaler_name=self.resize_name, context=self.resize_context) self.width = image.width self.height = image.height - if self.image_mask is not None and shared.opts.mask_apply_overlay and not hasattr(self, 'xyz'): + if self.image_mask is not None and shared.opts.mask_apply_overlay: image_masked = Image.new('RGBa', (image.width, image.height)) image_to_paste = image.convert("RGBA").convert("RGBa") image_to_mask = ImageOps.invert(self.mask_for_overlay.convert('L')) if self.mask_for_overlay is not None else None diff --git a/modules/sd_models.py b/modules/sd_models.py index c401ae6b7..51d25edfa 100644 --- a/modules/sd_models.py +++ b/modules/sd_models.py @@ -1288,7 +1288,7 @@ def set_diffuser_pipe(pipe, new_pipe_type): new_pipe.image_encoder = image_encoder if feature_extractor is not None: new_pipe.feature_extractor = feature_extractor - if new_pipe.__class__.__name__ == 'FluxPipeline': + if new_pipe.__class__.__name__ in ['FluxPipeline', 'StableDiffusion3Pipeline']: new_pipe.register_modules(image_encoder = image_encoder) new_pipe.register_modules(feature_extractor = feature_extractor) new_pipe.is_sdxl = getattr(pipe, 'is_sdxl', False) # a1111 compatibility item diff --git a/modules/sd_samplers_diffusers.py b/modules/sd_samplers_diffusers.py index 06459d8a8..6e5f37cd7 100644 --- a/modules/sd_samplers_diffusers.py +++ b/modules/sd_samplers_diffusers.py @@ -271,11 +271,16 @@ def __init__(self, name, constructor, model, **kwargs): sampler = constructor(**self.config) accept_sigmas = "sigmas" in set(inspect.signature(sampler.set_timesteps).parameters.keys()) accepts_timesteps = "timesteps" in set(inspect.signature(sampler.set_timesteps).parameters.keys()) + accept_scale_noise = hasattr(sampler, "scale_noise") debug(f'Sampler: sampler="{name}" sigmas={accept_sigmas} timesteps={accepts_timesteps}') if ('Flux' in model.__class__.__name__) and (not accept_sigmas): shared.log.warning(f'Sampler: sampler="{name}" does not accept sigmas') self.sampler = None return + if ('StableDiffusion3' in model.__class__.__name__) and (not accept_scale_noise): + shared.log.warning(f'Sampler: sampler="{name}" does not implement scale noise') + self.sampler = None + return self.sampler = sampler if name == 'DC Solver': if not hasattr(self.sampler, 'dc_ratios'): diff --git a/scripts/xyz_grid_on.py b/scripts/xyz_grid_on.py index ba23356da..0abd0fa1c 100644 --- a/scripts/xyz_grid_on.py +++ b/scripts/xyz_grid_on.py @@ -325,12 +325,14 @@ def cell(x, y, z, ix, iy, iz): x_opt.apply(pc, x, xs) y_opt.apply(pc, y, ys) z_opt.apply(pc, z, zs) + try: processed = processing.process_images(pc) except Exception as e: shared.log.error(f"XYZ grid: Failed to process image: {e}") errors.display(e, 'XYZ grid') processed = None + if ix == 0 and iy == 0: # create subgrid info text pc.extra_generation_params = copy(pc.extra_generation_params) pc.extra_generation_params['Script'] = self.title()