Upgrade to Qwen-Image-Edit-2511 with Phr00t v18 transformer

- Update base model from 2509 to 2511
- Use extracted Phr00t v18 NSFW transformer (Sneak-Moose/Qwen-Rapid-AIO-v18-NSFW-diffusers)
- Comment out next-scene LoRA for initial testing (trained on 2509)
- Update UI description and CLAUDE.md documentation

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

CLAUDE.md

@@ -4,12 +4,12 @@ This file provides guidance to Claude Code (claude.ai/code) when working with co
 
 ## Project Overview
 
-This is a Gradio Space that implements "Next Scene" cinematic image generation using Qwen-Image-Edit-2509 with LoRA fine-tuning. The application generates visually progressive image sequences with natural cinematic transitions from frame to frame, optimized for fast 4-step inference.
+This is a Gradio Space that implements "Next Scene" cinematic image generation using Qwen-Image-Edit-2511 with LoRA fine-tuning. The application generates visually progressive image sequences with natural cinematic transitions from frame to frame, optimized for fast 4-step inference.
 
 **Key Model Components:**
-- Base model: `Qwen/Qwen-Image-Edit-2509` (image editing diffusion model)
-- Accelerated transformer: `linoyts/Qwen-Image-Edit-Rapid-AIO` (4-step optimized variant)
-- LoRA adapter: `lovis93/next-scene-qwen-image-lora-2509` (cinematic progression fine-tune)
+- Base model: `Qwen/Qwen-Image-Edit-2511` (image editing diffusion model)
+- Accelerated transformer: `Sneak-Moose/Qwen-Rapid-AIO-v18-NSFW-diffusers` (extracted from Phr00t's v18, 4-step optimized)
+- LoRA adapter: `lovis93/next-scene-qwen-image-lora-2509` (cinematic progression fine-tune, trained on 2509)
 
 ## Running the Application
 

app.py

@@ -93,19 +93,29 @@ def use_history_as_input(evt: gr.SelectData):
 dtype = torch.bfloat16
 device = "cuda" if torch.cuda.is_available() else "cpu"
 
-pipe = QwenImageEditPlusPipeline.from_pretrained("Qwen/Qwen-Image-Edit-2509", 
-                                                transformer= QwenImageTransformer2DModel.from_pretrained("linoyts/Qwen-Image-Edit-Rapid-AIO", 
-                                                                                                         subfolder='transformer',
-                                                                                                         torch_dtype=dtype,
-                                                                                                         device_map='cuda'),torch_dtype=dtype).to(device)
-
-pipe.load_lora_weights(
-        "lovis93/next-scene-qwen-image-lora-2509", 
-        weight_name="next-scene_lora-v2-3000.safetensors", adapter_name="next-scene"
-    )
-pipe.set_adapters(["next-scene"], adapter_weights=[1.])
-pipe.fuse_lora(adapter_names=["next-scene"], lora_scale=1.)
-pipe.unload_lora_weights()
+# Load Qwen-Image-Edit-2511 with Phr00t's v18 accelerated transformer (4-step inference)
+pipe = QwenImageEditPlusPipeline.from_pretrained(
+    "Qwen/Qwen-Image-Edit-2511",
+    transformer=QwenImageTransformer2DModel.from_pretrained(
+        "Sneak-Moose/Qwen-Rapid-AIO-v18-NSFW-diffusers",
+        subfolder='transformer',
+        torch_dtype=dtype,
+        device_map='cuda'
+    ),
+    torch_dtype=dtype
+).to(device)
+
+# Load next-scene LoRA for cinematic progression
+# Note: This LoRA was trained on 2509, may need testing with 2511/v18
+# TODO: Re-enable after testing base 2511/v18 works correctly
+# pipe.load_lora_weights(
+#     "lovis93/next-scene-qwen-image-lora-2509",
+#     weight_name="next-scene_lora-v2-3000.safetensors",
+#     adapter_name="next-scene"
+# )
+# pipe.set_adapters(["next-scene"], adapter_weights=[1.])
+# pipe.fuse_lora(adapter_names=["next-scene"], lora_scale=1.)
+# pipe.unload_lora_weights()
 
 
 # Apply the same optimizations from the first version
@@ -234,7 +244,7 @@ with gr.Blocks(css=css) as demo:
         </div>
         """)
         gr.Markdown("""
-        This demo uses [Qwen-Image-Edit-2509](https://huggingface.co/Qwen/Qwen-Image-Edit-2509) with [lovis93/next-scene-qwen-image-lora](https://huggingface.co/lovis93/next-scene-qwen-image-lora-2509) for cinematic image sequences with natural visual progression from frame to frame 🎥 and [linoyts/Qwen-Image-Edit-Rapid-AIO](https://huggingface.co/linoyts/Qwen-Image-Edit-Rapid-AIO) + [AoT compilation & FA3](https://huggingface.co/blog/zerogpu-aoti) for accelerated 4-step inference.
+        This demo uses [Qwen-Image-Edit-2511](https://huggingface.co/Qwen/Qwen-Image-Edit-2511) with [Phr00t's Rapid-AIO v18](https://huggingface.co/Phr00t/Qwen-Image-Edit-Rapid-AIO) transformer + [lovis93/next-scene-qwen-image-lora](https://huggingface.co/lovis93/next-scene-qwen-image-lora-2509) for cinematic image sequences with natural visual progression 🎥 and [AoT compilation & FA3](https://huggingface.co/blog/zerogpu-aoti) for accelerated 4-step inference.
 
         Upload an image and enter your prompt to generate the next scene. The model will use your prompt exactly as provided.
         """)