Upload 2 files

Basic gradio app

app.py

@@ -1,154 +1,74 @@
-import gradio as gr
-import numpy as np
-import random
-
-# import spaces #[uncomment to use ZeroGPU]
-from diffusers import DiffusionPipeline
-import torch
-
-device = "cuda" if torch.cuda.is_available() else "cpu"
-model_repo_id = "stabilityai/sdxl-turbo"  # Replace to the model you would like to use
-
-if torch.cuda.is_available():
-    torch_dtype = torch.float16
-else:
-    torch_dtype = torch.float32
-
-pipe = DiffusionPipeline.from_pretrained(model_repo_id, torch_dtype=torch_dtype)
-pipe = pipe.to(device)
-
-MAX_SEED = np.iinfo(np.int32).max
-MAX_IMAGE_SIZE = 1024
-
-
-# @spaces.GPU #[uncomment to use ZeroGPU]
-def infer(
-    prompt,
-    negative_prompt,
-    seed,
-    randomize_seed,
-    width,
-    height,
-    guidance_scale,
-    num_inference_steps,
-    progress=gr.Progress(track_tqdm=True),
-):
-    if randomize_seed:
-        seed = random.randint(0, MAX_SEED)
-
-    generator = torch.Generator().manual_seed(seed)
-
-    image = pipe(
-        prompt=prompt,
-        negative_prompt=negative_prompt,
-        guidance_scale=guidance_scale,
-        num_inference_steps=num_inference_steps,
-        width=width,
-        height=height,
-        generator=generator,
-    ).images[0]
-
-    return image, seed
-
-
-examples = [
-    "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k",
-    "An astronaut riding a green horse",
-    "A delicious ceviche cheesecake slice",
-]
-
-css = """
-#col-container {
-    margin: 0 auto;
-    max-width: 640px;
-}
-"""
-
-with gr.Blocks(css=css) as demo:
-    with gr.Column(elem_id="col-container"):
-        gr.Markdown(" # Text-to-Image Gradio Template")
-
-        with gr.Row():
-            prompt = gr.Text(
-                label="Prompt",
-                show_label=False,
-                max_lines=1,
-                placeholder="Enter your prompt",
-                container=False,
-            )
-
-            run_button = gr.Button("Run", scale=0, variant="primary")
-
-        result = gr.Image(label="Result", show_label=False)
-
-        with gr.Accordion("Advanced Settings", open=False):
-            negative_prompt = gr.Text(
-                label="Negative prompt",
-                max_lines=1,
-                placeholder="Enter a negative prompt",
-                visible=False,
-            )
-
-            seed = gr.Slider(
-                label="Seed",
-                minimum=0,
-                maximum=MAX_SEED,
-                step=1,
-                value=0,
-            )
-
-            randomize_seed = gr.Checkbox(label="Randomize seed", value=True)
-
-            with gr.Row():
-                width = gr.Slider(
-                    label="Width",
-                    minimum=256,
-                    maximum=MAX_IMAGE_SIZE,
-                    step=32,
-                    value=1024,  # Replace with defaults that work for your model
-                )
-
-                height = gr.Slider(
-                    label="Height",
-                    minimum=256,
-                    maximum=MAX_IMAGE_SIZE,
-                    step=32,
-                    value=1024,  # Replace with defaults that work for your model
-                )
-
-            with gr.Row():
-                guidance_scale = gr.Slider(
-                    label="Guidance scale",
-                    minimum=0.0,
-                    maximum=10.0,
-                    step=0.1,
-                    value=0.0,  # Replace with defaults that work for your model
-                )
-
-                num_inference_steps = gr.Slider(
-                    label="Number of inference steps",
-                    minimum=1,
-                    maximum=50,
-                    step=1,
-                    value=2,  # Replace with defaults that work for your model
-                )
-
-        gr.Examples(examples=examples, inputs=[prompt])
-    gr.on(
-        triggers=[run_button.click, prompt.submit],
-        fn=infer,
-        inputs=[
-            prompt,
-            negative_prompt,
-            seed,
-            randomize_seed,
-            width,
-            height,
-            guidance_scale,
-            num_inference_steps,
-        ],
-        outputs=[result, seed],
-    )
-
-if __name__ == "__main__":
-    demo.launch()
+import torch
+import gradio as gr
+import spaces
+
+from huggingface_hub import hf_hub_download
+from safetensors.torch import load_file
+
+from diffusers import ZImagePipeline, ZImageTransformer2DModel  # Z-Image specific
+
+BASE_ID = "Tongyi-MAI/Z-Image-Turbo"
+CUSTOM_REPO = "MutantSparrow/Ray"
+CUSTOM_FILE = "Z-IMAGE-TURBO/Rayzist.v1.0.safetensors"
+
+pipe = None
+
+def load_pipe():
+    global pipe
+    if pipe is not None:
+        return pipe
+
+    # Load base components like the official demo
+    transformer = ZImageTransformer2DModel.from_pretrained(
+        BASE_ID,
+        subfolder="transformer",
+        torch_dtype=torch.bfloat16,
+    )
+
+    pipe = ZImagePipeline.from_pretrained(
+        BASE_ID,
+        transformer=transformer,
+        torch_dtype=torch.bfloat16,
+    ).to("cuda")
+
+    # Now load your custom denoiser weights into the transformer
+    ckpt_path = hf_hub_download(CUSTOM_REPO, CUSTOM_FILE)
+    state = load_file(ckpt_path)
+
+    missing, unexpected = pipe.transformer.load_state_dict(state, strict=False)
+    print("Loaded custom weights.")
+    print("Missing keys:", len(missing))
+    print("Unexpected keys:", len(unexpected))
+
+    pipe.set_progress_bar_config(disable=True)
+    return pipe
+
+@spaces.GPU
+def generate(prompt, steps=9, height=1024, width=1024, seed=0):
+    p = load_pipe()
+    g = torch.Generator("cuda").manual_seed(int(seed))
+
+    img = p(
+        prompt=prompt,
+        height=int(height),
+        width=int(width),
+        num_inference_steps=int(steps),
+        guidance_scale=0.0,  # turbo-style in the official demo
+        generator=g,
+    ).images[0]
+    return img
+
+with gr.Blocks() as demo:
+    gr.Markdown("RAYZIST! A Z-Image Turbo Finetune")
+    prompt = gr.Textbox(label="Prompt", lines=5)
+    steps  = gr.Slider(1, 12, value=8, step=1, label="Steps")
+    width  = gr.Dropdown([512, 768, 1024, 1280], value=1024, label="Width")
+    height = gr.Dropdown([512, 768, 1024, 1280], value=1024, label="Height")
+    seed   = gr.Number(value=0, label="Seed")
+    out    = gr.Image(label="Result")
+
+    btn = gr.Button("GO >")
+    btn.click(generate, [prompt, steps, height, width, seed], out)
+
+demo.queue()
+demo.launch()

requirements.txt

@@ -1,6 +1,7 @@
-accelerate
-diffusers
-invisible_watermark
-torch
-transformers
-xformers
+gradio
+torch
+diffusers
+transformers
+accelerate
+safetensors
+huggingface_hub