diff --git a/modules/processing.py b/modules/processing.py index 85d354232..f01a6907f 100644 --- a/modules/processing.py +++ b/modules/processing.py @@ -344,7 +344,7 @@ class StableDiffusionProcessing: def setup_conds(self): prompts = prompt_parser.SdConditioning(self.prompts, width=self.width, height=self.height) - negative_prompts = prompt_parser.SdConditioning(self.negative_prompts, width=self.width, height=self.height) + negative_prompts = prompt_parser.SdConditioning(self.negative_prompts, width=self.width, height=self.height, is_negative_prompt=True) sampler_config = sd_samplers.find_sampler_config(self.sampler_name) self.step_multiplier = 2 if sampler_config and sampler_config.options.get("second_order", False) else 1 diff --git a/modules/prompt_parser.py b/modules/prompt_parser.py index 33810669f..b29d079d5 100644 --- a/modules/prompt_parser.py +++ b/modules/prompt_parser.py @@ -116,11 +116,17 @@ class SdConditioning(list): A list with prompts for stable diffusion's conditioner model. Can also specify width and height of created image - SDXL needs it. """ - def __init__(self, prompts, width=None, height=None): + def __init__(self, prompts, is_negative_prompt=False, width=None, height=None, copy_from=None): super().__init__() self.extend(prompts) - self.width = width or getattr(prompts, 'width', None) - self.height = height or getattr(prompts, 'height', None) + + if copy_from is None: + copy_from = prompts + + self.is_negative_prompt = is_negative_prompt or getattr(copy_from, 'is_negative_prompt', False) + self.width = width or getattr(copy_from, 'width', None) + self.height = height or getattr(copy_from, 'height', None) + def get_learned_conditioning(model, prompts: SdConditioning | list[str], steps): @@ -153,7 +159,7 @@ def get_learned_conditioning(model, prompts: SdConditioning | list[str], steps): res.append(cached) continue - texts = [x[1] for x in prompt_schedule] + texts = SdConditioning([x[1] for x in prompt_schedule], copy_from=prompts) conds = model.get_learned_conditioning(texts) cond_schedule = [] diff --git a/modules/sd_hijack.py b/modules/sd_hijack.py index 266811f95..647cdfbed 100644 --- a/modules/sd_hijack.py +++ b/modules/sd_hijack.py @@ -190,7 +190,7 @@ class StableDiffusionModelHijack: if typename == 'FrozenCLIPEmbedder': model_embeddings = m.cond_stage_model.transformer.text_model.embeddings model_embeddings.token_embedding = EmbeddingsWithFixes(model_embeddings.token_embedding, self) - m.cond_stage_model = sd_hijack_clip.FrozenCLIPEmbedderWithCustomWords(embedder, self) + m.cond_stage_model = sd_hijack_clip.FrozenCLIPEmbedderForSDXLWithCustomWords(embedder, self) conditioner.embedders[i] = m.cond_stage_model if typename == 'FrozenOpenCLIPEmbedder2': embedder.model.token_embedding = EmbeddingsWithFixes(embedder.model.token_embedding, self) diff --git a/modules/sd_hijack_clip.py b/modules/sd_hijack_clip.py index 6c17a81d2..b3771909f 100644 --- a/modules/sd_hijack_clip.py +++ b/modules/sd_hijack_clip.py @@ -323,3 +323,18 @@ class FrozenCLIPEmbedderWithCustomWords(FrozenCLIPEmbedderWithCustomWordsBase): embedded = embedding_layer.token_embedding.wrapped(ids.to(embedding_layer.token_embedding.wrapped.weight.device)).squeeze(0) return embedded + + +class FrozenCLIPEmbedderForSDXLWithCustomWords(FrozenCLIPEmbedderWithCustomWords): + def __init__(self, wrapped, hijack): + super().__init__(wrapped, hijack) + + def encode_with_transformers(self, tokens): + outputs = self.wrapped.transformer(input_ids=tokens, output_hidden_states=self.wrapped.layer == "hidden") + + if self.wrapped.layer == "last": + z = outputs.last_hidden_state + else: + z = outputs.hidden_states[self.wrapped.layer_idx] + + return z diff --git a/modules/sd_models_config.py b/modules/sd_models_config.py index 2e92479a1..04c09ab00 100644 --- a/modules/sd_models_config.py +++ b/modules/sd_models_config.py @@ -12,7 +12,6 @@ sd_xl_repo_configs_path = os.path.join(paths.paths['Stable Diffusion XL'], "conf config_default = shared.sd_default_config config_sd2 = os.path.join(sd_repo_configs_path, "v2-inference.yaml") config_sd2v = os.path.join(sd_repo_configs_path, "v2-inference-v.yaml") -config_sd2v = os.path.join(sd_xl_repo_configs_path, "sd_2_1_768.yaml") config_sd2_inpainting = os.path.join(sd_repo_configs_path, "v2-inpainting-inference.yaml") config_sdxl = os.path.join(sd_xl_repo_configs_path, "sd_xl_base.yaml") config_depth_model = os.path.join(sd_repo_configs_path, "v2-midas-inference.yaml") diff --git a/modules/sd_models_xl.py b/modules/sd_models_xl.py index 1dd4459fe..b799ff46f 100644 --- a/modules/sd_models_xl.py +++ b/modules/sd_models_xl.py @@ -22,7 +22,8 @@ def get_learned_conditioning(self: sgm.models.diffusion.DiffusionEngine, batch: "target_size_as_tuple": torch.tensor([height, width]).repeat(len(batch), 1).to(devices.device, devices.dtype), } - c = self.conditioner(sdxl_conds) + force_zero_negative_prompt = getattr(batch, 'is_negative_prompt', False) and all(x == '' for x in batch) + c = self.conditioner(sdxl_conds, force_zero_embeddings=['txt'] if force_zero_negative_prompt else []) return c