change to flux

app.py

@@ -1,312 +1,122 @@
 import gradio as gr
+import numpy as np
+import random
 import spaces
-from gradio_litmodel3d import LitModel3D
-
-import os
-import shutil
-os.environ['SPCONV_ALGO'] = 'native'
-from typing import *
 import torch
-import numpy as np
-import imageio
-from easydict import EasyDict as edict
-from PIL import Image
-from trellis.pipelines import TrellisImageTo3DPipeline
-from trellis.representations import Gaussian, MeshExtractResult
-from trellis.utils import render_utils, postprocessing_utils
-
-
-MAX_SEED = np.iinfo(np.int32).max
-TMP_DIR = os.path.join(os.path.dirname(os.path.abspath(__file__)), 'tmp')
-# os.makedirs(TMP_DIR, exist_ok=True)
-
-
-# def start_session(req: gr.Request):
-#     gr.Warning('start start session')
-#     user_dir = os.path.join(TMP_DIR, str(req.session_hash))
-#     os.makedirs(user_dir, exist_ok=True)
-#     gr.Warning('end start session')
-    
-    
-# def end_session(req: gr.Request):
-#     user_dir = os.path.join(TMP_DIR, str(req.session_hash))
-#     shutil.rmtree(user_dir)
-
-
-# def preprocess_image(image: Image.Image) -> Image.Image:
-#     """
-#     Preprocess the input image.
-
-#     Args:
-#         image (Image.Image): The input image.
-
-#     Returns:
-#         Image.Image: The preprocessed image.
-#     """
-#     processed_image = pipeline.preprocess_image(image)
-#     return processed_image
-
-
-# def pack_state(gs: Gaussian, mesh: MeshExtractResult) -> dict:
-#     return {
-#         'gaussian': {
-#             **gs.init_params,
-#             '_xyz': gs._xyz.cpu().numpy(),
-#             '_features_dc': gs._features_dc.cpu().numpy(),
-#             '_scaling': gs._scaling.cpu().numpy(),
-#             '_rotation': gs._rotation.cpu().numpy(),
-#             '_opacity': gs._opacity.cpu().numpy(),
-#         },
-#         'mesh': {
-#             'vertices': mesh.vertices.cpu().numpy(),
-#             'faces': mesh.faces.cpu().numpy(),
-#         },
-#     }
-    
-    
-# def unpack_state(state: dict) -> Tuple[Gaussian, edict, str]:
-#     gs = Gaussian(
-#         aabb=state['gaussian']['aabb'],
-#         sh_degree=state['gaussian']['sh_degree'],
-#         mininum_kernel_size=state['gaussian']['mininum_kernel_size'],
-#         scaling_bias=state['gaussian']['scaling_bias'],
-#         opacity_bias=state['gaussian']['opacity_bias'],
-#         scaling_activation=state['gaussian']['scaling_activation'],
-#     )
-#     gs._xyz = torch.tensor(state['gaussian']['_xyz'], device='cuda')
-#     gs._features_dc = torch.tensor(state['gaussian']['_features_dc'], device='cuda')
-#     gs._scaling = torch.tensor(state['gaussian']['_scaling'], device='cuda')
-#     gs._rotation = torch.tensor(state['gaussian']['_rotation'], device='cuda')
-#     gs._opacity = torch.tensor(state['gaussian']['_opacity'], device='cuda')
-    
-#     mesh = edict(
-#         vertices=torch.tensor(state['mesh']['vertices'], device='cuda'),
-#         faces=torch.tensor(state['mesh']['faces'], device='cuda'),
-#     )
-    
-#     return gs, mesh
-
-
-# def get_seed(randomize_seed: bool, seed: int) -> int:
-#     """
-#     Get the random seed.
-#     """
-#     return np.random.randint(0, MAX_SEED) if randomize_seed else seed
-
-
-# @spaces.GPU
-# def image_to_3d(
-#     image: Image.Image,
-#     seed: int,
-#     ss_guidance_strength: float,
-#     ss_sampling_steps: int,
-#     slat_guidance_strength: float,
-#     slat_sampling_steps: int,
-#     req: gr.Request,
-# ) -> Tuple[dict, str]:
-#     """
-#     Convert an image to a 3D model.
-
-#     Args:
-#         image (Image.Image): The input image.
-#         seed (int): The random seed.
-#         ss_guidance_strength (float): The guidance strength for sparse structure generation.
-#         ss_sampling_steps (int): The number of sampling steps for sparse structure generation.
-#         slat_guidance_strength (float): The guidance strength for structured latent generation.
-#         slat_sampling_steps (int): The number of sampling steps for structured latent generation.
-
-#     Returns:
-#         dict: The information of the generated 3D model.
-#         str: The path to the video of the 3D model.
-#     """
-#     user_dir = os.path.join(TMP_DIR, str(req.session_hash))
-#     outputs = pipeline.run(
-#         image,
-#         seed=seed,
-#         formats=["gaussian", "mesh"],
-#         preprocess_image=False,
-#         sparse_structure_sampler_params={
-#             "steps": ss_sampling_steps,
-#             "cfg_strength": ss_guidance_strength,
-#         },
-#         slat_sampler_params={
-#             "steps": slat_sampling_steps,
-#             "cfg_strength": slat_guidance_strength,
-#         },
-#     )
-#     video = render_utils.render_video(outputs['gaussian'][0], num_frames=120)['color']
-#     video_geo = render_utils.render_video(outputs['mesh'][0], num_frames=120)['normal']
-#     video = [np.concatenate([video[i], video_geo[i]], axis=1) for i in range(len(video))]
-#     video_path = os.path.join(user_dir, 'sample.mp4')
-#     imageio.mimsave(video_path, video, fps=15)
-#     state = pack_state(outputs['gaussian'][0], outputs['mesh'][0])
-#     torch.cuda.empty_cache()
-#     return state, video_path
+from diffusers import DiffusionPipeline
 
+dtype = torch.bfloat16
+device = "cuda" if torch.cuda.is_available() else "cpu"
 
-# @spaces.GPU(duration=90)
-# def extract_glb(
-#     state: dict,
-#     mesh_simplify: float,
-#     texture_size: int,
-#     req: gr.Request,
-# ) -> Tuple[str, str]:
-#     """
-#     Extract a GLB file from the 3D model.
+pipe = DiffusionPipeline.from_pretrained("black-forest-labs/FLUX.1-schnell", torch_dtype=dtype).to(device)
 
-#     Args:
-#         state (dict): The state of the generated 3D model.
-#         mesh_simplify (float): The mesh simplification factor.
-#         texture_size (int): The texture resolution.
-
-#     Returns:
-#         str: The path to the extracted GLB file.
-#     """
-#     user_dir = os.path.join(TMP_DIR, str(req.session_hash))
-#     gs, mesh = unpack_state(state)
-#     glb = postprocessing_utils.to_glb(gs, mesh, simplify=mesh_simplify, texture_size=texture_size, verbose=False)
-#     glb_path = os.path.join(user_dir, 'sample.glb')
-#     glb.export(glb_path)
-#     torch.cuda.empty_cache()
-#     return glb_path, glb_path
-
-
-# @spaces.GPU
-# def extract_gaussian(state: dict, req: gr.Request) -> Tuple[str, str]:
-#     """
-#     Extract a Gaussian file from the 3D model.
-
-#     Args:
-#         state (dict): The state of the generated 3D model.
-
-#     Returns:
-#         str: The path to the extracted Gaussian file.
-#     """
-#     user_dir = os.path.join(TMP_DIR, str(req.session_hash))
-#     gs, _ = unpack_state(state)
-#     gaussian_path = os.path.join(user_dir, 'sample.ply')
-#     gs.save_ply(gaussian_path)
-#     torch.cuda.empty_cache()
-#     return gaussian_path, gaussian_path
-
-
-# def split_image(image: Image.Image) -> List[Image.Image]:
-#     """
-#     Split an image into multiple views.
-#     """
-#     image = np.array(image)
-#     alpha = image[..., 3]
-#     alpha = np.any(alpha>0, axis=0)
-#     start_pos = np.where(~alpha[:-1] & alpha[1:])[0].tolist()
-#     end_pos = np.where(alpha[:-1] & ~alpha[1:])[0].tolist()
-#     images = []
-#     for s, e in zip(start_pos, end_pos):
-#         images.append(Image.fromarray(image[:, s:e+1]))
-#     return [preprocess_image(image) for image in images]
-
-
-with gr.Blocks(delete_cache=(600, 600)) as demo:
-    gr.Markdown("""
-    ## Text to 3D Asset with Mistral + Flux + Trellis 
-    * Upload an image and click "Generate" to create a 3D asset
-    """)
+MAX_SEED = np.iinfo(np.int32).max
+MAX_IMAGE_SIZE = 2048
+
+@spaces.GPU()
+def infer(prompt, seed=42, randomize_seed=False, width=1024, height=1024, num_inference_steps=4, 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, 
+            width = width,
+            height = height,
+            num_inference_steps = num_inference_steps, 
+            generator = generator,
+            guidance_scale=0.0
+    ).images[0] 
+    return image, seed
+ 
+examples = [
+    "a tiny astronaut hatching from an egg on the moon",
+    "a cat holding a sign that says hello world",
+    "an anime illustration of a wiener schnitzel",
+]
+
+css="""
+#col-container {
+    margin: 0 auto;
+    max-width: 520px;
+}
+"""
+
+with gr.Blocks(css=css) as demo:
     
-    with gr.Row():
-        with gr.Column():
-            image_prompt = gr.Image(label="Image Prompt", format="png", image_mode="RGBA", type="pil", height=300)
+    with gr.Column(elem_id="col-container"):
+        gr.Markdown(f"""# FLUX.1 [schnell]
+12B param rectified flow transformer distilled from [FLUX.1 [pro]](https://blackforestlabs.ai/) for 4 step generation
+[[blog](https://blackforestlabs.ai/announcing-black-forest-labs/)] [[model](https://huggingface.co/black-forest-labs/FLUX.1-schnell)]
+        """)
+        
+        with gr.Row():
             
-            with gr.Accordion(label="Generation Settings", open=False):
-                seed = gr.Slider(0, MAX_SEED, label="Seed", value=0, step=1)
-                randomize_seed = gr.Checkbox(label="Randomize Seed", value=True)
-                gr.Markdown("Stage 1: Sparse Structure Generation")
-                with gr.Row():
-                    ss_guidance_strength = gr.Slider(0.0, 10.0, label="Guidance Strength", value=7.5, step=0.1)
-                    ss_sampling_steps = gr.Slider(1, 50, label="Sampling Steps", value=12, step=1)
-                gr.Markdown("Stage 2: Structured Latent Generation")
-                with gr.Row():
-                    slat_guidance_strength = gr.Slider(0.0, 10.0, label="Guidance Strength", value=3.0, step=0.1)
-                    slat_sampling_steps = gr.Slider(1, 50, label="Sampling Steps", value=12, step=1)
-
-            generate_btn = gr.Button("Generate")
+            prompt = gr.Text(
+                label="Prompt",
+                show_label=False,
+                max_lines=1,
+                placeholder="Enter your prompt",
+                container=False,
+            )
+            
+            run_button = gr.Button("Run", scale=0)
+        
+        result = gr.Image(label="Result", show_label=False)
+        
+        with gr.Accordion("Advanced Settings", open=False):
+            
+            seed = gr.Slider(
+                label="Seed",
+                minimum=0,
+                maximum=MAX_SEED,
+                step=1,
+                value=0,
+            )
             
-            with gr.Accordion(label="GLB Extraction Settings", open=False):
-                mesh_simplify = gr.Slider(0.9, 0.98, label="Simplify", value=0.95, step=0.01)
-                texture_size = gr.Slider(512, 2048, label="Texture Size", value=1024, step=512)
+            randomize_seed = gr.Checkbox(label="Randomize seed", value=True)
             
             with gr.Row():
-                extract_glb_btn = gr.Button("Extract GLB", interactive=False)
-                extract_gs_btn = gr.Button("Extract Gaussian", interactive=False)
-
-        with gr.Column():
-            video_output = gr.Video(label="Generated 3D Asset", autoplay=True, loop=True, height=300)
-            model_output = LitModel3D(label="Extracted GLB/Gaussian", exposure=10.0, height=300)
+                
+                width = gr.Slider(
+                    label="Width",
+                    minimum=256,
+                    maximum=MAX_IMAGE_SIZE,
+                    step=32,
+                    value=1024,
+                )
+                
+                height = gr.Slider(
+                    label="Height",
+                    minimum=256,
+                    maximum=MAX_IMAGE_SIZE,
+                    step=32,
+                    value=1024,
+                )
             
             with gr.Row():
-                download_glb = gr.DownloadButton(label="Download GLB", interactive=False)
-                download_gs = gr.DownloadButton(label="Download Gaussian", interactive=False)  
-    
-    # output_buf = gr.State()
-
-
-    # Handlers
-    # demo.load(start_session)
-    # demo.unload(end_session)
-    
-    
-    # image_prompt.upload(
-    #     preprocess_image,
-    #     inputs=[image_prompt],
-    #     outputs=[image_prompt],
-    # )
-
-    # generate_btn.click(
-    #     get_seed,
-    #     inputs=[randomize_seed, seed],
-    #     outputs=[seed],
-    # ).then(
-    #     image_to_3d,
-    #     inputs=[image_prompt, seed, ss_guidance_strength, ss_sampling_steps, slat_guidance_strength, slat_sampling_steps],
-    #     outputs=[output_buf, video_output],
-    # ).then(
-    #     lambda: tuple([gr.Button(interactive=True), gr.Button(interactive=True)]),
-    #     outputs=[extract_glb_btn, extract_gs_btn],
-    # )
-
-    # video_output.clear(
-    #     lambda: tuple([gr.Button(interactive=False), gr.Button(interactive=False)]),
-    #     outputs=[extract_glb_btn, extract_gs_btn],
-    # )
-
-    # extract_glb_btn.click(
-    #     extract_glb,
-    #     inputs=[output_buf, mesh_simplify, texture_size],
-    #     outputs=[model_output, download_glb],
-    # ).then(
-    #     lambda: gr.Button(interactive=True),
-    #     outputs=[download_glb],
-    # )
-    
-    # extract_gs_btn.click(
-    #     extract_gaussian,
-    #     inputs=[output_buf],
-    #     outputs=[model_output, download_gs],
-    # ).then(
-    #     lambda: gr.Button(interactive=True),
-    #     outputs=[download_gs],
-    # )
-
-    # model_output.clear(
-    #     lambda: gr.Button(interactive=False),
-    #     outputs=[download_glb],
-    # )
-    
-
-# Launch the Gradio app
-if __name__ == "__main__":
-    pipeline = TrellisImageTo3DPipeline.from_pretrained("JeffreyXiang/TRELLIS-image-large")
-    pipeline.cuda()
-    # try:
-    #     pipeline.preprocess_image(Image.fromarray(np.zeros((512, 512, 3), dtype=np.uint8)))    # Preload rembg
-    # except:
-    #     pass
-    demo.launch()
+                
+  
+                num_inference_steps = gr.Slider(
+                    label="Number of inference steps",
+                    minimum=1,
+                    maximum=50,
+                    step=1,
+                    value=4,
+                )
+        
+        gr.Examples(
+            examples = examples,
+            fn = infer,
+            inputs = [prompt],
+            outputs = [result, seed],
+            cache_examples="lazy"
+        )
+
+    gr.on(
+        triggers=[run_button.click, prompt.submit],
+        fn = infer,
+        inputs = [prompt, seed, randomize_seed, width, height, num_inference_steps],
+        outputs = [result, seed]
+    )
+
+demo.launch()

requirements.txt

@@ -23,4 +23,8 @@ transformers==4.46.3
 gradio_litmodel3d==0.0.1
 https://github.com/Dao-AILab/flash-attention/releases/download/v2.7.0.post2/flash_attn-2.7.0.post2+cu12torch2.4cxx11abiFALSE-cp310-cp310-linux_x86_64.whl
 https://huggingface.co/spaces/JeffreyXiang/TRELLIS/resolve/main/wheels/diff_gaussian_rasterization-0.0.0-cp310-cp310-linux_x86_64.whl?download=true
-https://huggingface.co/spaces/JeffreyXiang/TRELLIS/resolve/main/wheels/nvdiffrast-0.3.3-cp310-cp310-linux_x86_64.whl?download=true
+https://huggingface.co/spaces/JeffreyXiang/TRELLIS/resolve/main/wheels/nvdiffrast-0.3.3-cp310-cp310-linux_x86_64.whl?download=true
+accelerate
+git+https://github.com/huggingface/diffusers.git
+invisible_watermark
+sentencepiece