quick taesd vae decode

CHANGELOG.md

@@ -6,6 +6,9 @@
   - **pipeline autodetect**
     if pipeline is set to autodetect (default for new installs), app will try to autodetect pipeline based on selected model  
     this should reduce user errors such as loading sd-xl model when sd pipeline is selected  
+  - **quick vae decode** as alternative to full vae decode which is very resource intensive  
+    quick decode is based on `taesd` and produces lower quality, but its great for tests or grids as it runs much faster and uses far less vram  
+    disabled by default, selectable in *txt2img/img2img -> advanced -> full quality*  
   - **prompt attention** for sd and sd-xl  
     native `compel` implementation and standrd -> compel translation  
     thanks @ai-casanova  

modules/img2img.py

@@ -74,13 +74,13 @@ def process_batch(p, input_files, input_dir, output_dir, inpaint_mask_dir, args)
         shared.log.debug(f'Processed: {len(image_files)} Memory: {memory_stats()} batch')
 
 
-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, latent_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, diffusers_guidance_rescale: float, refiner_start: float, clip_skip: int, denoising_strength: float, seed: int, subseed: int, subseed_strength: float, seed_resize_from_h: int, seed_resize_from_w: int, 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_files: list, img2img_batch_input_dir: str, img2img_batch_output_dir: str, img2img_batch_inpaint_mask_dir: str, override_settings_texts, *args): # pylint: disable=unused-argument
+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, latent_index: int, mask_blur: int, mask_alpha: float, inpainting_fill: int, full_quality: bool, restore_faces: bool, tiling: bool, n_iter: int, batch_size: int, cfg_scale: float, image_cfg_scale: float, diffusers_guidance_rescale: float, refiner_start: float, clip_skip: int, denoising_strength: float, seed: int, subseed: int, subseed_strength: float, seed_resize_from_h: int, seed_resize_from_w: int, 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_files: list, img2img_batch_input_dir: str, img2img_batch_output_dir: str, img2img_batch_inpaint_mask_dir: str, override_settings_texts, *args): # pylint: disable=unused-argument
 
     if shared.sd_model is None:
         shared.log.warning('Model not loaded')
         return [], '', '', 'Error: model not loaded'
 
-    shared.log.debug(f'img2img: id_task={id_task}|mode={mode}|prompt={prompt}|negative_prompt={negative_prompt}|prompt_styles={prompt_styles}|init_img={init_img}|sketch={sketch}|init_img_with_mask={init_img_with_mask}|inpaint_color_sketch={inpaint_color_sketch}|inpaint_color_sketch_orig={inpaint_color_sketch_orig}|init_img_inpaint={init_img_inpaint}|init_mask_inpaint={init_mask_inpaint}|steps={steps}|sampler_index={sampler_index}|latent_index={latent_index}|mask_blur={mask_blur}|mask_alpha={mask_alpha}|inpainting_fill={inpainting_fill}|restore_faces={restore_faces}|tiling={tiling}|n_iter={n_iter}|batch_size={batch_size}|cfg_scale={cfg_scale}|image_cfg_scale={image_cfg_scale}|clip_skip={clip_skip}|denoising_strength={denoising_strength}|seed={seed}|subseed{subseed}|subseed_strength={subseed_strength}|seed_resize_from_h={seed_resize_from_h}|seed_resize_from_w={seed_resize_from_w}|selected_scale_tab={selected_scale_tab}|height={height}|width={width}|scale_by={scale_by}|resize_mode={resize_mode}|inpaint_full_res={inpaint_full_res}|inpaint_full_res_padding={inpaint_full_res_padding}|inpainting_mask_invert={inpainting_mask_invert}|img2img_batch_files={img2img_batch_files}|img2img_batch_input_dir={img2img_batch_input_dir}|img2img_batch_output_dir={img2img_batch_output_dir}|img2img_batch_inpaint_mask_dir={img2img_batch_inpaint_mask_dir}|override_settings_texts={override_settings_texts}|args={args}')
+    shared.log.debug(f'img2img: id_task={id_task}|mode={mode}|prompt={prompt}|negative_prompt={negative_prompt}|prompt_styles={prompt_styles}|init_img={init_img}|sketch={sketch}|init_img_with_mask={init_img_with_mask}|inpaint_color_sketch={inpaint_color_sketch}|inpaint_color_sketch_orig={inpaint_color_sketch_orig}|init_img_inpaint={init_img_inpaint}|init_mask_inpaint={init_mask_inpaint}|steps={steps}|sampler_index={sampler_index}|latent_index={latent_index}|mask_blur={mask_blur}|mask_alpha={mask_alpha}|inpainting_fill={inpainting_fill}|full_quality={full_quality}|restore_faces={restore_faces}|tiling={tiling}|n_iter={n_iter}|batch_size={batch_size}|cfg_scale={cfg_scale}|image_cfg_scale={image_cfg_scale}|clip_skip={clip_skip}|denoising_strength={denoising_strength}|seed={seed}|subseed{subseed}|subseed_strength={subseed_strength}|seed_resize_from_h={seed_resize_from_h}|seed_resize_from_w={seed_resize_from_w}|selected_scale_tab={selected_scale_tab}|height={height}|width={width}|scale_by={scale_by}|resize_mode={resize_mode}|inpaint_full_res={inpaint_full_res}|inpaint_full_res_padding={inpaint_full_res_padding}|inpainting_mask_invert={inpainting_mask_invert}|img2img_batch_files={img2img_batch_files}|img2img_batch_input_dir={img2img_batch_input_dir}|img2img_batch_output_dir={img2img_batch_output_dir}|img2img_batch_inpaint_mask_dir={img2img_batch_inpaint_mask_dir}|override_settings_texts={override_settings_texts}|args={args}')
 
     if init_img is None:
         shared.log.debug('Init image not set')
@@ -158,6 +158,7 @@ def img2img(id_task: str, mode: int, prompt: str, negative_prompt: str, prompt_s
         clip_skip=clip_skip,
         width=width,
         height=height,
+        full_quality=full_quality,
         restore_faces=restore_faces,
         tiling=tiling,
         init_images=[image],

modules/processing.py

@@ -86,7 +86,7 @@ class StableDiffusionProcessing:
     """
     The first set of paramaters: sd_models -> do_not_reload_embeddings represent the minimum required to create a StableDiffusionProcessing
     """
-    def __init__(self, sd_model=None, outpath_samples=None, outpath_grids=None, prompt: str = "", styles: List[str] = None, seed: int = -1, subseed: int = -1, subseed_strength: float = 0, seed_resize_from_h: int = -1, seed_resize_from_w: int = -1, seed_enable_extras: bool = True, sampler_name: str = None, latent_sampler: str = None, batch_size: int = 1, n_iter: int = 1, steps: int = 50, cfg_scale: float = 7.0, image_cfg_scale: float = None, clip_skip: int = 1, width: int = 512, height: int = 512, restore_faces: bool = False, tiling: bool = False, do_not_save_samples: bool = False, do_not_save_grid: bool = False, extra_generation_params: Dict[Any, Any] = None, overlay_images: Any = None, negative_prompt: str = None, eta: float = None, do_not_reload_embeddings: bool = False, denoising_strength: float = 0, diffusers_guidance_rescale: float = 0.7, ddim_discretize: str = None, s_min_uncond: float = 0.0, s_churn: float = 0.0, s_tmax: float = None, s_tmin: float = 0.0, s_noise: float = 1.0, override_settings: Dict[str, Any] = None, override_settings_restore_afterwards: bool = True, sampler_index: int = None, script_args: list = None): # pylint: disable=unused-argument
+    def __init__(self, sd_model=None, outpath_samples=None, outpath_grids=None, prompt: str = "", styles: List[str] = None, seed: int = -1, subseed: int = -1, subseed_strength: float = 0, seed_resize_from_h: int = -1, seed_resize_from_w: int = -1, seed_enable_extras: bool = True, sampler_name: str = None, latent_sampler: str = None, batch_size: int = 1, n_iter: int = 1, steps: int = 50, cfg_scale: float = 7.0, image_cfg_scale: float = None, clip_skip: int = 1, width: int = 512, height: int = 512, full_quality: bool = True, restore_faces: bool = False, tiling: bool = False, do_not_save_samples: bool = False, do_not_save_grid: bool = False, extra_generation_params: Dict[Any, Any] = None, overlay_images: Any = None, negative_prompt: str = None, eta: float = None, do_not_reload_embeddings: bool = False, denoising_strength: float = 0, diffusers_guidance_rescale: float = 0.7, ddim_discretize: str = None, s_min_uncond: float = 0.0, s_churn: float = 0.0, s_tmax: float = None, s_tmin: float = 0.0, s_noise: float = 1.0, override_settings: Dict[str, Any] = None, override_settings_restore_afterwards: bool = True, sampler_index: int = None, script_args: list = None): # pylint: disable=unused-argument
 
         self.outpath_samples: str = outpath_samples
         self.outpath_grids: str = outpath_grids
@@ -110,6 +110,7 @@ class StableDiffusionProcessing:
         self.diffusers_guidance_rescale = diffusers_guidance_rescale
         self.width: int = width
         self.height: int = height
+        self.full_quality: bool = full_quality
         self.restore_faces: bool = restore_faces
         self.tiling: bool = tiling
         self.do_not_save_samples: bool = do_not_save_samples
@@ -450,6 +451,10 @@ def create_infotext(p: StableDiffusionProcessing, all_prompts, all_seeds, all_su
 
     if all_negative_prompts is None:
         all_negative_prompts = p.all_negative_prompts
+    if p.full_quality:
+        vae = None if not shared.opts.add_model_name_to_info or sd_vae.loaded_vae_file is None else os.path.splitext(os.path.basename(sd_vae.loaded_vae_file))[0]
+    else:
+        vae = 'TAESD'
 
     generation_params = {
         "Steps": p.steps,
@@ -461,7 +466,7 @@ def create_infotext(p: StableDiffusionProcessing, all_prompts, all_seeds, all_su
         "Model": None if not shared.opts.add_model_name_to_info or not shared.sd_model.sd_checkpoint_info.model_name else shared.sd_model.sd_checkpoint_info.model_name.replace(',', '').replace(':', ''),
         "Model hash": getattr(p, 'sd_model_hash', None if not shared.opts.add_model_hash_to_info or not shared.sd_model.sd_model_hash else shared.sd_model.sd_model_hash),
         "Refiner": None if not shared.opts.add_model_name_to_info or not shared.sd_refiner or not shared.sd_refiner.sd_checkpoint_info.model_name else shared.sd_refiner.sd_checkpoint_info.model_name.replace(',', '').replace(':', ''),
-        "VAE": None if not shared.opts.add_model_name_to_info or sd_vae.loaded_vae_file is None else os.path.splitext(os.path.basename(sd_vae.loaded_vae_file))[0],
+        "VAE": vae,
         # subseed
         "Variation seed": None if p.subseed_strength == 0 else all_subseeds[index],
         "Variation seed strength": None if p.subseed_strength == 0 else p.subseed_strength,

modules/processing_diffusers.py

@@ -49,8 +49,8 @@ def process_diffusers(p: StableDiffusionProcessing, seeds, prompts, negative_pro
         decoded = torch.zeros((len(latents), 3, p.height, p.width), dtype=devices.dtype_vae, device=devices.device)
         for i in range(len(output.images)):
             decoded[i] = (sd_vae_taesd.decode(latents[i]) * 2.0) - 1.0
-        images = model.image_processor.postprocess(decoded, output_type=output_type)
-        return images
+        imgs = model.image_processor.postprocess(decoded, output_type=output_type)
+        return imgs
 
 
     def set_pipeline_args(model, prompt: str, negative_prompt: str, prompt_2: typing.Optional[str] =None, negative_prompt_2: typing.Optional[str] = None, is_refiner: bool = False, **kwargs):
@@ -177,10 +177,7 @@ def process_diffusers(p: StableDiffusionProcessing, seeds, prompts, negative_pro
         return results
 
     if shared.sd_refiner is None or not p.enable_hr:
-        if shared.opts.diffusers_taesd_vae_output:
-            output.images = taesd_vae_decode(output.images, shared.sd_model)
-        else:
-            output.images = vae_decode(output.images, shared.sd_model)
+        output.images = vae_decode(output.images, shared.sd_model) if p.full_quality else taesd_vae_decode(output.images, shared.sd_model)
 
     if lora_state['active']:
         unload_diffusers_lora()

modules/shared.py

@@ -396,7 +396,6 @@ options_templates.update(options_section(('cuda', "Compute Settings"), {
 
 options_templates.update(options_section(('diffusers', "Diffusers Settings"), {
     "diffusers_allow_safetensors": OptionInfo(True, 'Diffusers allow loading from safetensors files'),
-    "diffusers_taesd_vae_output": OptionInfo(False, 'Use TAESD VAE for quick image outputs'),
     "diffusers_pipeline": OptionInfo(pipelines[0], 'Diffusers pipeline', gr.Dropdown, lambda: {"choices": pipelines}),
     "diffusers_move_base": OptionInfo(False, "Move base model to CPU when using refiner"),
     "diffusers_move_refiner": OptionInfo(True, "Move refiner model to CPU when not in use"),

modules/txt2img.py

@@ -5,9 +5,9 @@ from modules.ui import plaintext_to_html
 from modules.memstats import memory_stats
 
 
-def txt2img(id_task: str, prompt: str, negative_prompt: str, prompt_styles, steps: int, sampler_index: int, latent_index: int, restore_faces: bool, tiling: bool, n_iter: int, batch_size: int, cfg_scale: float, image_cfg_scale: float, diffusers_guidance_rescale: float, clip_skip: int, seed: int, subseed: int, subseed_strength: float, seed_resize_from_h: int, seed_resize_from_w: int, height: int, width: int, enable_hr: bool, denoising_strength: float, hr_scale: float, hr_upscaler: str, hr_second_pass_steps: int, hr_resize_x: int, hr_resize_y: int, refiner_start: int, refiner_prompt: str, refiner_negative: str, override_settings_texts, *args): # pylint: disable=unused-argument
+def txt2img(id_task: str, prompt: str, negative_prompt: str, prompt_styles, steps: int, sampler_index: int, latent_index: int, full_quality: bool, restore_faces: bool, tiling: bool, n_iter: int, batch_size: int, cfg_scale: float, image_cfg_scale: float, diffusers_guidance_rescale: float, clip_skip: int, seed: int, subseed: int, subseed_strength: float, seed_resize_from_h: int, seed_resize_from_w: int, height: int, width: int, enable_hr: bool, denoising_strength: float, hr_scale: float, hr_upscaler: str, hr_second_pass_steps: int, hr_resize_x: int, hr_resize_y: int, refiner_start: int, refiner_prompt: str, refiner_negative: str, override_settings_texts, *args): # pylint: disable=unused-argument
 
-    shared.log.debug(f'txt2img: id_task={id_task}|prompt={prompt}|negative_prompt={negative_prompt}|prompt_styles={prompt_styles}|steps={steps}|sampler_index={sampler_index}|latent_index={latent_index}|restore_faces={restore_faces}|tiling={tiling}|n_iter={n_iter}|batch_size={batch_size}|cfg_scale={cfg_scale}|clip_skip={clip_skip}|seed={seed}|subseed={subseed}|subseed_strength={subseed_strength}|seed_resize_from_h={seed_resize_from_h}|seed_resize_from_w={seed_resize_from_w}||height={height}|width={width}|enable_hr={enable_hr}|denoising_strength={denoising_strength}|hr_scale={hr_scale}|hr_upscaler={hr_upscaler}|hr_second_pass_steps={hr_second_pass_steps}|hr_resize_x={hr_resize_x}|hr_resize_y={hr_resize_y}|image_cfg_scale={image_cfg_scale}|diffusers_guidance_rescale={diffusers_guidance_rescale}|refiner_start={refiner_start}||refiner_prompt={refiner_prompt}|refiner_negative={refiner_negative}|override_settings_texts={override_settings_texts}|args={args}')
+    shared.log.debug(f'txt2img: id_task={id_task}|prompt={prompt}|negative_prompt={negative_prompt}|prompt_styles={prompt_styles}|steps={steps}|sampler_index={sampler_index}|latent_index={latent_index}|full_quality={full_quality}|restore_faces={restore_faces}|tiling={tiling}|n_iter={n_iter}|batch_size={batch_size}|cfg_scale={cfg_scale}|clip_skip={clip_skip}|seed={seed}|subseed={subseed}|subseed_strength={subseed_strength}|seed_resize_from_h={seed_resize_from_h}|seed_resize_from_w={seed_resize_from_w}||height={height}|width={width}|enable_hr={enable_hr}|denoising_strength={denoising_strength}|hr_scale={hr_scale}|hr_upscaler={hr_upscaler}|hr_second_pass_steps={hr_second_pass_steps}|hr_resize_x={hr_resize_x}|hr_resize_y={hr_resize_y}|image_cfg_scale={image_cfg_scale}|diffusers_guidance_rescale={diffusers_guidance_rescale}|refiner_start={refiner_start}||refiner_prompt={refiner_prompt}|refiner_negative={refiner_negative}|override_settings_texts={override_settings_texts}|args={args}')
 
     if shared.sd_model is None:
         shared.log.warning('Model not loaded')
@@ -43,6 +43,7 @@ def txt2img(id_task: str, prompt: str, negative_prompt: str, prompt_styles, step
         clip_skip=clip_skip,
         width=width,
         height=height,
+        full_quality=full_quality,
         restore_faces=restore_faces,
         tiling=tiling,
         enable_hr=enable_hr,

modules/ui.py

@@ -379,6 +379,7 @@ def create_ui(startup_timer = None):
                         cfg_scale = gr.Slider(minimum=1.0, maximum=30.0, step=0.1, label='CFG Scale', value=6.0, elem_id="txt2img_cfg_scale")
                         clip_skip = gr.Slider(label='CLIP skip', value=1, minimum=1, maximum=14, step=1, elem_id='txt2img_clip_skip', interactive=True)
                     with FormRow(elem_classes="checkboxes-row", variant="compact"):
+                        full_quality = gr.Checkbox(label='Full quality', value=True, elem_id="txt2img_full_quality")
                         restore_faces = gr.Checkbox(label='Face restore', value=False, visible=len(modules.shared.face_restorers) > 1, elem_id="txt2img_restore_faces")
                         tiling = gr.Checkbox(label='Tiling', value=False, elem_id="txt2img_tiling")
 
@@ -435,7 +436,7 @@ def create_ui(startup_timer = None):
                     txt2img_prompt_styles,
                     steps,
                     sampler_index, latent_index,
-                    restore_faces, tiling,
+                    full_quality, restore_faces, tiling,
                     batch_count, batch_size,
                     cfg_scale, image_cfg_scale,
                     diffusers_guidance_rescale,
@@ -484,6 +485,7 @@ def create_ui(startup_timer = None):
                 (latent_index, "Latent sampler"),
                 (denoising_strength, "Denoising strength"),
                 (refiner_start, "Refiner start"),
+                (full_quality, "Full quality"),
                 (restore_faces, "Face restoration"),
                 (batch_size, "Batch size"),
                 (batch_count, "Batch count"),
@@ -669,6 +671,7 @@ def create_ui(startup_timer = None):
                         clip_skip = gr.Slider(label='CLIP skip', value=1, minimum=1, maximum=4, step=1, elem_id='img2img_clip_skip', interactive=True)
                         diffusers_guidance_rescale = gr.Slider(minimum=0.0, maximum=1.0, step=0.05, label='Guidance Rescale', value=0.7, elem_id="txt2img_image_cfg_rescale")
                     with FormRow(elem_classes="img2img_checkboxes_row", variant="compact"):
+                        full_quality = gr.Checkbox(label='Full quality', value=True, elem_id="img2img_full_quality")
                         restore_faces = gr.Checkbox(label='Restore faces', value=False, visible=len(modules.shared.face_restorers) > 1, elem_id="img2img_restore_faces")
                         tiling = gr.Checkbox(label='Tiling', value=False, elem_id="img2img_tiling")
 
@@ -733,7 +736,7 @@ def create_ui(startup_timer = None):
                     sampler_index, latent_index,
                     mask_blur, mask_alpha,
                     inpainting_fill,
-                    restore_faces, tiling,
+                    full_quality, restore_faces, tiling,
                     batch_count, batch_size,
                     cfg_scale, image_cfg_scale,
                     diffusers_guidance_rescale,