22

app.py

@@ -8,10 +8,10 @@ from diffsynth.pipelines.qwen_image import (
 from safetensors.torch import save_file
 import torch
 from PIL import Image
-# from utils import repo_utils, image_utils, prompt_utils
+from utils import repo_utils, image_utils, prompt_utils
 
 
-# repo_utils.clone_repo_if_not_exists("https://github.com/apple/ml-starflow.git", "app/models")
+# repo_utils.clone_repo_if_not_exists("git clone https://huggingface.co/DiffSynth-Studio/General-Image-Encoders", "app/repos")
 # repo_utils.clone_repo_if_not_exists("https://huggingface.co/apple/starflow", "app/models")
 
 DTYPE = torch.bfloat16
@@ -33,9 +33,24 @@ pipe = QwenImagePipeline.from_pretrained(
     torch_dtype=torch.bfloat16,
     device="cuda",
     model_configs=[
-        ModelConfig(model_id="DiffSynth-Studio/General-Image-Encoders", origin_file_pattern="SigLIP2-G384/model.safetensors", **vram_config_disk_offload),
-        ModelConfig(model_id="DiffSynth-Studio/General-Image-Encoders", origin_file_pattern="DINOv3-7B/model.safetensors", **vram_config_disk_offload),
-        ModelConfig(model_id="DiffSynth-Studio/Qwen-Image-i2L", origin_file_pattern="Qwen-Image-i2L-Style.safetensors", **vram_config_disk_offload),
+        ModelConfig(
+            download_source="huggingface", 
+            model_id="DiffSynth-Studio/General-Image-Encoders", 
+            origin_file_pattern="SigLIP2-G384/model.safetensors", 
+            **vram_config_disk_offload
+        ),
+        ModelConfig(
+            download_source="huggingface", 
+            model_id="DiffSynth-Studio/General-Image-Encoders", 
+            origin_file_pattern="DINOv3-7B/model.safetensors", 
+            **vram_config_disk_offload
+        ),
+        ModelConfig(
+            download_source="huggingface", 
+            model_id="DiffSynth-Studio/Qwen-Image-i2L", 
+            origin_file_pattern="Qwen-Image-i2L-Style.safetensors", 
+            **vram_config_disk_offload
+        ),
     ],
     processor_config=ModelConfig(model_id="Qwen/Qwen-Image-Edit", origin_file_pattern="processor/"),
     vram_limit=torch.cuda.mem_get_info("cuda")[1] / (1024 ** 3) - 0.5,
@@ -144,7 +159,14 @@ with gr.Blocks() as demo:
             gr.HTML(read_file("static/header.html"))
         with gr.Row():
             with gr.Column():
-
+                gallery = gr.Gallery(
+                    label="Generated images", 
+                    show_label=False, 
+                    elem_id="gallery", 
+                    columns=2, 
+                    object_fit="cover", 
+                    height=300)
+                
                 prompt = gr.Textbox(
                     label="Prompt",
                     show_label=False,

requirements.txt

@@ -5,3 +5,4 @@ accelerate
 spaces
 git+https://github.com/huggingface/diffusers.git
 git+https://github.com/modelscope/DiffSynth-Studio.git
+python-ulid