- CogVideoX-2B Huggingface Space🤗
+ CogVideoX-5B Huggingface Space🤗
@@ -176,21 +233,22 @@ with gr.Blocks() as demo:
with gr.Row():
with gr.Column():
prompt = gr.Textbox(label="Prompt (Less than 200 Words)", placeholder="Enter your prompt here", lines=5)
+
with gr.Row():
gr.Markdown(
- "✨Upon pressing the enhanced prompt button, we will use [GLM-4 Model](https://github.com/THUDM/GLM-4) to polish the prompt and overwrite the original one."
- )
+ "✨Upon pressing the enhanced prompt button, we will use [GLM-4 Model](https://github.com/THUDM/GLM-4) to polish the prompt and overwrite the original one.")
enhance_button = gr.Button("✨ Enhance Prompt(Optional)")
with gr.Column():
- gr.Markdown(
- "**Optional Parameters** (default values are recommended)
"
- "Turn Inference Steps larger if you want more detailed video, but it will be slower.
"
- "50 steps are recommended for most cases. will cause 120 seconds for inference.
"
- )
+ gr.Markdown("**Optional Parameters** (default values are recommended)
"
+ "Increasing the number of inference steps will produce more detailed videos, but it will slow down the process.
"
+ "50 steps are recommended for most cases.
"
+ "For the 5B model, 50 steps will take approximately 350 seconds.")
with gr.Row():
num_inference_steps = gr.Number(label="Inference Steps", value=50)
guidance_scale = gr.Number(label="Guidance Scale", value=6.0)
+ with gr.Row():
+ up_scale_model_ckpt = gr.Text(label="UP_SCALE_MODEL_CKPT", value="")
generate_button = gr.Button("🎬 Generate Video")
with gr.Column():
@@ -200,59 +258,88 @@ with gr.Blocks() as demo:
download_gif_button = gr.File(label="📥 Download GIF", visible=False)
gr.Markdown("""
-
-
- | Prompt |
- Video URL |
- Inference Steps |
- Guidance Scale |
-
-
- | A detailed wooden toy ship with intricately carved masts and sails is seen gliding smoothly over a plush, blue carpet that mimics the waves of the sea. The ship's hull is painted a rich brown, with tiny windows. The carpet, soft and textured, provides a perfect backdrop, resembling an oceanic expanse. Surrounding the ship are various other toys and children's items, hinting at a playful environment. The scene captures the innocence and imagination of childhood, with the toy ship's journey symbolizing endless adventures in a whimsical, indoor setting. |
- Video 1 |
- 50 |
- 6 |
-
-
- | The camera follows behind a white vintage SUV with a black roof rack as it speeds up a steep dirt road surrounded by pine trees on a steep mountain slope, dust kicks up from it’s tires, the sunlight shines on the SUV as it speeds along the dirt road, casting a warm glow over the scene. The dirt road curves gently into the distance, with no other cars or vehicles in sight. The trees on either side of the road are redwoods, with patches of greenery scattered throughout. The car is seen from the rear following the curve with ease, making it seem as if it is on a rugged drive through the rugged terrain. The dirt road itself is surrounded by steep hills and mountains, with a clear blue sky above with wispy clouds. |
- Video 2 |
- 50 |
- 6 |
-
-
- | A street artist, clad in a worn-out denim jacket and a colorful bandana, stands before a vast concrete wall in the heart, holding a can of spray paint, spray-painting a colorful bird on a mottled wall. |
- Video 3 |
- 50 |
- 6 |
-
-
- | In the haunting backdrop of a war-torn city, where ruins and crumbled walls tell a story of devastation, a poignant close-up frames a young girl. Her face is smudged with ash, a silent testament to the chaos around her. Her eyes glistening with a mix of sorrow and resilience, capturing the raw emotion of a world that has lost its innocence to the ravages of conflict. |
- Video 4 |
- 50 |
- 6 |
-
-
+
+
+ Demo Videos with 50 Inference Steps and 6.0 Guidance Scale.
+
+
+ |
+ A detailed wooden toy ship with intricately carved masts and sails is seen gliding smoothly over a plush, blue carpet that mimics the waves of the sea. The ship's hull is painted a rich brown, with tiny windows. The carpet, soft and textured, provides a perfect backdrop, resembling an oceanic expanse. Surrounding the ship are various other toys and children's items, hinting at a playful environment. The scene captures the innocence and imagination of childhood, with the toy ship's journey symbolizing endless adventures in a whimsical, indoor setting.
+ |
+
+
+ |
+
+ The camera follows behind a white vintage SUV with a black roof rack as it speeds up a steep dirt road surrounded by pine trees on a steep mountain slope, dust kicks up from its tires, the sunlight shines on the SUV as it speeds along the dirt road, casting a warm glow over the scene. The dirt road curves gently into the distance, with no other cars or vehicles in sight. The trees on either side of the road are redwoods, with patches of greenery scattered throughout. The car is seen from the rear following the curve with ease, making it seem as if it is on a rugged drive through the rugged terrain. The dirt road itself is surrounded by steep hills and mountains, with a clear blue sky above with wispy clouds.
+ |
+
+
+ |
+
+
+ |
+ A street artist, clad in a worn-out denim jacket and a colorful bandana, stands before a vast concrete wall in the heart, holding a can of spray paint, spray-painting a colorful bird on a mottled wall.
+ |
+
+
+ |
+
+ In the haunting backdrop of a war-torn city, where ruins and crumbled walls tell a story of devastation, a poignant close-up frames a young girl. Her face is smudged with ash, a silent testament to the chaos around her. Her eyes glistening with a mix of sorrow and resilience, capturing the raw emotion of a world that has lost its innocence to the ravages of conflict.
+ |
+
+
+ |
+
+
""")
- def generate(prompt, num_inference_steps, guidance_scale, progress=gr.Progress(track_tqdm=True)):
- tensor = infer(prompt, num_inference_steps, guidance_scale, progress=progress)
- video_path = save_video(tensor)
+
+ def generate(prompt, num_inference_steps, guidance_scale, upscale_ckpt, progress=gr.Progress(track_tqdm=True)):
+ global UP_SCALE_MODEL
+ if not UP_SCALE_MODEL:
+ # Load the upscale model with progress tracking
+ UP_SCALE_MODEL = load_sd_upscale(upscale_ckpt)
+
+ latents = infer(prompt, num_inference_steps, guidance_scale, progress=progress)
+ if UP_SCALE_MODEL:
+ latents = upscale_batch_and_concatenate(UP_SCALE_MODEL, latents)
+
+ batch_size = latents.shape[0]
+ batch_video_frames = []
+ for batch_idx in range(batch_size):
+ pt_image = latents[batch_idx]
+ pt_image = torch.stack(
+ [pt_image[i] for i in range(pt_image.shape[0])]
+ )
+
+ image_np = VaeImageProcessor.pt_to_numpy(pt_image) # (形状为 [49, 512, 480, 3])
+
+ image_pil = VaeImageProcessor.numpy_to_pil(image_np)
+
+ batch_video_frames.append(image_pil)
+ video_path = save_video(batch_video_frames[0])
video_update = gr.update(visible=True, value=video_path)
gif_path = convert_to_gif(video_path)
gif_update = gr.update(visible=True, value=gif_path)
return video_path, video_update, gif_update
+
def enhance_prompt_func(prompt):
return convert_prompt(prompt, retry_times=1)
+
generate_button.click(
generate,
- inputs=[prompt, num_inference_steps, guidance_scale],
- outputs=[video_output, download_video_button, download_gif_button],
+ inputs=[prompt, num_inference_steps, guidance_scale, up_scale_model_ckpt],
+ outputs=[video_output, download_video_button, download_gif_button]
)
- enhance_button.click(enhance_prompt_func, inputs=[prompt], outputs=[prompt])
+ enhance_button.click(
+ enhance_prompt_func,
+ inputs=[prompt],
+ outputs=[prompt]
+ )
if __name__ == "__main__":
- demo.launch(server_name="127.0.0.1", server_port=7870, share=True)
+ demo.launch(server_port=7870)
diff --git a/inference/utils.py b/inference/utils.py
new file mode 100644
index 0000000..19a3b65
--- /dev/null
+++ b/inference/utils.py
@@ -0,0 +1,144 @@
+import math
+
+import torch
+
+import itertools
+
+import safetensors.torch
+import tqdm
+import logging
+
+logger = logging.getLogger(__file__)
+
+
+def load_torch_file(ckpt, device=None, dtype=torch.float16):
+ if device is None:
+ device = torch.device("cpu")
+ if ckpt.lower().endswith(".safetensors") or ckpt.lower().endswith(".sft"):
+ sd = safetensors.torch.load_file(ckpt, device=device.type)
+ else:
+ if not 'weights_only' in torch.load.__code__.co_varnames:
+ logger.warning(
+ "Warning torch.load doesn't support weights_only on this pytorch version, loading unsafely.")
+
+ pl_sd = torch.load(ckpt, map_location=device, weights_only=True)
+ if "global_step" in pl_sd:
+ logger.debug(f"Global Step: {pl_sd['global_step']}")
+ if "state_dict" in pl_sd:
+ sd = pl_sd["state_dict"]
+ else:
+ sd = pl_sd
+
+ # Convert all tensors in the state_dict to the specified dtype
+ sd = {k: v.to(dtype) for k, v in sd.items()}
+ return sd
+
+
+def state_dict_prefix_replace(state_dict, replace_prefix, filter_keys=False):
+ if filter_keys:
+ out = {}
+ else:
+ out = state_dict
+ for rp in replace_prefix:
+ replace = list(map(lambda a: (a, "{}{}".format(replace_prefix[rp], a[len(rp):])),
+ filter(lambda a: a.startswith(rp), state_dict.keys())))
+ for x in replace:
+ w = state_dict.pop(x[0])
+ out[x[1]] = w
+ return out
+
+
+def module_size(module):
+ module_mem = 0
+ sd = module.state_dict()
+ for k in sd:
+ t = sd[k]
+ module_mem += t.nelement() * t.element_size()
+ return module_mem
+
+
+def get_tiled_scale_steps(width, height, tile_x, tile_y, overlap):
+ return math.ceil((height / (tile_y - overlap))) * math.ceil((width / (tile_x - overlap)))
+
+
+@torch.inference_mode()
+def tiled_scale_multidim(samples, function, tile=(64, 64), overlap=8, upscale_amount=4, out_channels=3,
+ output_device="cpu", pbar=None):
+ dims = len(tile)
+ print(f"samples dtype:{samples.dtype}")
+ output = torch.empty(
+ [samples.shape[0], out_channels] + list(map(lambda a: round(a * upscale_amount), samples.shape[2:])),
+ device=output_device)
+
+ for b in range(samples.shape[0]):
+ s = samples[b:b + 1]
+ out = torch.zeros([s.shape[0], out_channels] + list(map(lambda a: round(a * upscale_amount), s.shape[2:])),
+ device=output_device)
+ out_div = torch.zeros([s.shape[0], out_channels] + list(map(lambda a: round(a * upscale_amount), s.shape[2:])),
+ device=output_device)
+
+ for it in itertools.product(*map(lambda a: range(0, a[0], a[1] - overlap), zip(s.shape[2:], tile))):
+ s_in = s
+ upscaled = []
+
+ for d in range(dims):
+ pos = max(0, min(s.shape[d + 2] - overlap, it[d]))
+ l = min(tile[d], s.shape[d + 2] - pos)
+ s_in = s_in.narrow(d + 2, pos, l)
+ upscaled.append(round(pos * upscale_amount))
+
+ ps = function(s_in).to(output_device)
+ mask = torch.ones_like(ps)
+ feather = round(overlap * upscale_amount)
+ for t in range(feather):
+ for d in range(2, dims + 2):
+ m = mask.narrow(d, t, 1)
+ m *= ((1.0 / feather) * (t + 1))
+ m = mask.narrow(d, mask.shape[d] - 1 - t, 1)
+ m *= ((1.0 / feather) * (t + 1))
+
+ o = out
+ o_d = out_div
+ for d in range(dims):
+ o = o.narrow(d + 2, upscaled[d], mask.shape[d + 2])
+ o_d = o_d.narrow(d + 2, upscaled[d], mask.shape[d + 2])
+
+ o += ps * mask
+ o_d += mask
+
+ if pbar is not None:
+ pbar.update(1)
+
+ output[b:b + 1] = out / out_div
+ return output
+
+
+def tiled_scale(samples, function, tile_x=64, tile_y=64, overlap=8, upscale_amount=4, out_channels=3,
+ output_device="cpu", pbar=None):
+ return tiled_scale_multidim(samples, function, (tile_y, tile_x), overlap, upscale_amount, out_channels,
+ output_device, pbar)
+
+
+
+class ProgressBar:
+ def __init__(self, total):
+
+ self.total = total
+ self.current = 0
+ self.b_unit = tqdm.tqdm(
+ total=total, desc="ProgressBar context index: 0"
+ )
+
+ def update(self, value):
+
+ if value > self.total:
+ value = self.total
+ self.current = value
+ if self.b_unit is not None:
+ self.b_unit.set_description(
+ "ProgressBar context index: {}".format(self.current)
+ )
+ self.b_unit.refresh()
+
+ # 更新进度
+ self.b_unit.update(self.current)
diff --git a/requirements.txt b/requirements.txt
index 05e7d5c..8256d12 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -11,4 +11,10 @@ streamlit==1.37.0 # For streamlit web demo
imageio==2.34.2 # For diffusers inference export video
imageio-ffmpeg==0.5.1 # For diffusers inference export video
openai==1.40.6 # For prompt refiner
-moviepy==1.0.3 # For export video
\ No newline at end of file
+moviepy==1.0.3 # For export video
+
+#
+safetensors>=0.4.2
+spandrel
+spaces
+tqdm