diffsynth 2.0.14__tar.gz → 2.0.15__tar.gz

{diffsynth-2.0.14 → diffsynth-2.0.15}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: diffsynth
-Version: 2.0.14
+Version: 2.0.15
 Summary: Enjoy the magic of Diffusion models!
 Author: ModelScope Team
 License: Apache-2.0

{diffsynth-2.0.14 → diffsynth-2.0.15}/diffsynth/configs/model_configs.py

@@ -917,6 +917,14 @@ stable_diffusion_xl_series = [
         "state_dict_converter": "diffsynth.utils.state_dict_converters.stable_diffusion_vae.SDVAEStateDictConverter",
         "extra_kwargs": {"scaling_factor": 0.13025, "sample_size": 1024, "force_upcast": True},
     },
+    {
+        # Example: ModelConfig(model_id="stabilityai/stable-diffusion-xl-base-1.0", origin_file_pattern="sd_xl_base_1.0.safetensors")
+        "model_hash": "4cf64a799d04260df438c6f33c9a047e",
+        "model_name": "stable_diffusion_xl_unet",
+        "model_class": "diffsynth.models.stable_diffusion_xl_unet.SDXLUNet2DConditionModel",
+        "extra_kwargs": {"attention_head_dim": [5, 10, 20], "transformer_layers_per_block": [1, 2, 10], "use_linear_projection": True, "addition_embed_type": "text_time", "addition_time_embed_dim": 256, "projection_class_embeddings_input_dim": 2816},
+        "state_dict_converter": "diffsynth.utils.state_dict_converters.sdxl.SDXLUNetStateDictConverter_Original2Diffusers",
+    }
 ]
 
 stable_diffusion_series = [

{diffsynth-2.0.14 → diffsynth-2.0.15}/diffsynth/diffusion/ddim_scheduler.py

@@ -87,8 +87,9 @@ class DDIMScheduler():
     
     
     def add_noise(self, original_samples, noise, timestep):
-        sqrt_alpha_prod = math.sqrt(self.alphas_cumprod[int(timestep.flatten().tolist()[0])])
-        sqrt_one_minus_alpha_prod = math.sqrt(1 - self.alphas_cumprod[int(timestep.flatten().tolist()[0])])
+        timestep_id = max(min(int(timestep.flatten().tolist()[0]), len(self.alphas_cumprod)-1), 0)
+        sqrt_alpha_prod = math.sqrt(self.alphas_cumprod[timestep_id])
+        sqrt_one_minus_alpha_prod = math.sqrt(1 - self.alphas_cumprod[timestep_id])
         noisy_samples = sqrt_alpha_prod * original_samples + sqrt_one_minus_alpha_prod * noise
         return noisy_samples
     
@@ -97,8 +98,9 @@ class DDIMScheduler():
         if self.prediction_type == "epsilon":
             return noise
         else:
-            sqrt_alpha_prod = math.sqrt(self.alphas_cumprod[int(timestep.flatten().tolist()[0])])
-            sqrt_one_minus_alpha_prod = math.sqrt(1 - self.alphas_cumprod[int(timestep.flatten().tolist()[0])])
+            timestep_id = max(min(int(timestep.flatten().tolist()[0]), len(self.alphas_cumprod)-1), 0)
+            sqrt_alpha_prod = math.sqrt(self.alphas_cumprod[timestep_id])
+            sqrt_one_minus_alpha_prod = math.sqrt(1 - self.alphas_cumprod[timestep_id])
             target = sqrt_alpha_prod * noise - sqrt_one_minus_alpha_prod * sample
             return target
         

{diffsynth-2.0.14 → diffsynth-2.0.15}/diffsynth/pipelines/stable_diffusion_xl.py

@@ -13,6 +13,7 @@ from ..models.stable_diffusion_text_encoder import SDTextEncoder
 from ..models.stable_diffusion_xl_unet import SDXLUNet2DConditionModel
 from ..models.stable_diffusion_xl_text_encoder import SDXLTextEncoder2
 from ..models.stable_diffusion_vae import StableDiffusionVAE
+from ..utils.lora.sdxl import SdxlLoRALoader
 
 
 def rescale_noise_cfg(noise_cfg, noise_pred_text, guidance_rescale=0.0):
@@ -53,6 +54,7 @@ class StableDiffusionXLPipeline(BasePipeline):
         ]
         self.model_fn = model_fn_stable_diffusion_xl
         self.compilable_models = ["unet"]
+        self.lora_loader = SdxlLoRALoader
 
     @staticmethod
     def from_pretrained(