update default params

cogvideox/api/api.py

@@ -77,7 +77,7 @@ def infer_forward_api(_: gr.Blocks, app: FastAPI, controller):
         lora_model_path = datas.get('lora_model_path', 'none')
         lora_alpha_slider = datas.get('lora_alpha_slider', 0.55)
         prompt_textbox = datas.get('prompt_textbox', None)
-        negative_prompt_textbox = datas.get('negative_prompt_textbox', 'The video is not of a high quality, it has a low resolution, and the audio quality is not clear. Strange motion trajectory, a poor composition and deformed video, low resolution, duplicate and ugly, strange body structure, long and strange neck, bad teeth, bad eyes, bad limbs, bad hands, rotating camera, blurry camera, shaking camera. Deformation, low-resolution, blurry, ugly, distortion.')
+        negative_prompt_textbox = datas.get('negative_prompt_textbox', 'The video is not of a high quality, it has a low resolution. Watermark present in each frame. Strange motion trajectory. ')
         sampler_dropdown = datas.get('sampler_dropdown', 'Euler')
         sample_step_slider = datas.get('sample_step_slider', 30)
         resize_method = datas.get('resize_method', "Generate by")

cogvideox/api/post_infer.py

@@ -32,10 +32,10 @@ def post_infer(generation_method, length_slider, url='http://127.0.0.1:7860'):
         "motion_module_path": "none",
         "lora_model_path": "none", 
         "lora_alpha_slider": 0.55, 
-        "prompt_textbox": "This video shows Mount saint helens, washington - the stunning scenery of a rocky mountains during golden hours - wide shot. A soaring drone footage captures the majestic beauty of a coastal cliff, its red and yellow stratified rock faces rich in color and against the vibrant turquoise of the sea.", 
-        "negative_prompt_textbox": "Strange motion trajectory, a poor composition and deformed video, worst quality, normal quality, low quality, low resolution, duplicate and ugly, strange body structure, long and strange neck, bad teeth, bad eyes, bad limbs, bad hands, rotating camera, blurry camera, shaking camera", 
+        "prompt_textbox": "A young woman with beautiful and clear eyes and blonde hair standing and white dress in a forest wearing a crown. She seems to be lost in thought, and the camera focuses on her face. The video is of high quality, and the view is very clear. High quality, masterpiece, best quality, highres, ultra-detailed, fantastic.", 
+        "negative_prompt_textbox": "The video is not of a high quality, it has a low resolution. Watermark present in each frame. Strange motion trajectory. ", 
         "sampler_dropdown": "Euler", 
-        "sample_step_slider": 30, 
+        "sample_step_slider": 50, 
         "width_slider": 672, 
         "height_slider": 384, 
         "generation_method": "Video Generation",
@@ -55,23 +55,16 @@ if __name__ == '__main__':
     # -------------------------- #
     #  Step 1: update edition
     # -------------------------- #
-    edition = "v3"
-    outputs = post_update_edition(edition)
-    print('Output update edition: ', outputs)
-
-    # -------------------------- #
-    #  Step 2: update edition
-    # -------------------------- #
-    diffusion_transformer_path = "models/Diffusion_Transformer/cogvideox_funV3-XL-2-512x512"
+    diffusion_transformer_path = "models/Diffusion_Transformer/CogVideoX-Fun-2b-InP"
     outputs = post_diffusion_transformer(diffusion_transformer_path)
     print('Output update edition: ', outputs)
 
     # -------------------------- #
-    #  Step 3: infer
+    #  Step 2: infer
     # -------------------------- #
     # "Video Generation" and "Image Generation"
     generation_method = "Video Generation"
-    length_slider = 72
+    length_slider = 49
     outputs = post_infer(generation_method, length_slider)
     
     # Get decoded data

cogvideox/ui/ui.py

@@ -493,13 +493,13 @@ def ui(low_gpu_memory_mode, weight_dtype):
             )
             
             prompt_textbox = gr.Textbox(label="Prompt (正向提示词)", lines=2, value="A young woman with beautiful and clear eyes and blonde hair standing and white dress in a forest wearing a crown. She seems to be lost in thought, and the camera focuses on her face. The video is of high quality, and the view is very clear. High quality, masterpiece, best quality, highres, ultra-detailed, fantastic.")
-            negative_prompt_textbox = gr.Textbox(label="Negative prompt (负向提示词)", lines=2, value="The video is not of a high quality, it has a low resolution, and the audio quality is not clear. Strange motion trajectory, a poor composition and deformed video, low resolution, duplicate and ugly, strange body structure, long and strange neck, bad teeth, bad eyes, bad limbs, bad hands, rotating camera, blurry camera, shaking camera. Deformation, low-resolution, blurry, ugly, distortion." )
+            negative_prompt_textbox = gr.Textbox(label="Negative prompt (负向提示词)", lines=2, value="The video is not of a high quality, it has a low resolution. Watermark present in each frame. Strange motion trajectory. " )
                 
             with gr.Row():
                 with gr.Column():
                     with gr.Row():
                         sampler_dropdown   = gr.Dropdown(label="Sampling method (采样器种类)", choices=list(scheduler_dict.keys()), value=list(scheduler_dict.keys())[0])
-                        sample_step_slider = gr.Slider(label="Sampling steps (生成步数)", value=30, minimum=10, maximum=100, step=1)
+                        sample_step_slider = gr.Slider(label="Sampling steps (生成步数)", value=50, minimum=10, maximum=100, step=1)
                         
                     resize_method = gr.Radio(
                         ["Generate by", "Resize according to Reference"],
@@ -924,13 +924,13 @@ def ui_modelscope(model_name, savedir_sample, low_gpu_memory_mode, weight_dtype)
             )
 
             prompt_textbox = gr.Textbox(label="Prompt (正向提示词)", lines=2, value="A young woman with beautiful and clear eyes and blonde hair standing and white dress in a forest wearing a crown. She seems to be lost in thought, and the camera focuses on her face. The video is of high quality, and the view is very clear. High quality, masterpiece, best quality, highres, ultra-detailed, fantastic.")
-            negative_prompt_textbox = gr.Textbox(label="Negative prompt (负向提示词)", lines=2, value="The video is not of a high quality, it has a low resolution, and the audio quality is not clear. Strange motion trajectory, a poor composition and deformed video, low resolution, duplicate and ugly, strange body structure, long and strange neck, bad teeth, bad eyes, bad limbs, bad hands, rotating camera, blurry camera, shaking camera. Deformation, low-resolution, blurry, ugly, distortion." )
+            negative_prompt_textbox = gr.Textbox(label="Negative prompt (负向提示词)", lines=2, value="The video is not of a high quality, it has a low resolution. Watermark present in each frame. Strange motion trajectory. " )
                 
             with gr.Row():
                 with gr.Column():
                     with gr.Row():
                         sampler_dropdown   = gr.Dropdown(label="Sampling method (采样器种类)", choices=list(scheduler_dict.keys()), value=list(scheduler_dict.keys())[0])
-                        sample_step_slider = gr.Slider(label="Sampling steps (生成步数)", value=20, minimum=10, maximum=30, step=1, interactive=False)
+                        sample_step_slider = gr.Slider(label="Sampling steps (生成步数)", value=50, minimum=10, maximum=50, step=1, interactive=False)
                     
                     resize_method = gr.Radio(
                         ["Generate by", "Resize according to Reference"],
@@ -1258,13 +1258,13 @@ def ui_eas(model_name, savedir_sample):
             )
             
             prompt_textbox = gr.Textbox(label="Prompt", lines=2, value="A young woman with beautiful and clear eyes and blonde hair standing and white dress in a forest wearing a crown. She seems to be lost in thought, and the camera focuses on her face. The video is of high quality, and the view is very clear. High quality, masterpiece, best quality, highres, ultra-detailed, fantastic.")
-            negative_prompt_textbox = gr.Textbox(label="Negative prompt", lines=2, value="The video is not of a high quality, it has a low resolution, and the audio quality is not clear. Strange motion trajectory, a poor composition and deformed video, low resolution, duplicate and ugly, strange body structure, long and strange neck, bad teeth, bad eyes, bad limbs, bad hands, rotating camera, blurry camera, shaking camera. Deformation, low-resolution, blurry, ugly, distortion. " )
+            negative_prompt_textbox = gr.Textbox(label="Negative prompt", lines=2, value="The video is not of a high quality, it has a low resolution. Watermark present in each frame. Strange motion trajectory.  " )
                 
             with gr.Row():
                 with gr.Column():
                     with gr.Row():
                         sampler_dropdown   = gr.Dropdown(label="Sampling method", choices=list(scheduler_dict.keys()), value=list(scheduler_dict.keys())[0])
-                        sample_step_slider = gr.Slider(label="Sampling steps", value=20, minimum=10, maximum=30, step=1, interactive=False)
+                        sample_step_slider = gr.Slider(label="Sampling steps", value=50, minimum=10, maximum=50, step=1, interactive=False)
                     
                     resize_method = gr.Radio(
                         ["Generate by", "Resize according to Reference"],

comfyui/v1/cogvideoxfunv1_workflow_i2v.json

@@ -176,7 +176,7 @@
         "Node name for S&R": "TextBox"
       },
       "widgets_values": [
-        "The video is not of a high quality, it has a low resolution, and the audio quality is not clear. Strange motion trajectory, a poor composition and deformed video, low resolution, duplicate and ugly, strange body structure, long and strange neck, bad teeth, bad eyes, bad limbs, bad hands, rotating camera, blurry camera, shaking camera. Deformation, low-resolution, blurry, ugly, distortion."
+        "The video is not of a high quality, it has a low resolution. Watermark present in each frame. Strange motion trajectory. "
       ]
     },
     {

comfyui/v1/cogvideoxfunv1_workflow_t2v.json

@@ -78,7 +78,7 @@
         "Node name for S&R": "TextBox"
       },
       "widgets_values": [
-        "The video is not of a high quality, it has a low resolution, and the audio quality is not clear. Strange motion trajectory, a poor composition and deformed video, low resolution, duplicate and ugly, strange body structure, long and strange neck, bad teeth, bad eyes, bad limbs, bad hands, rotating camera, blurry camera, shaking camera. Deformation, low-resolution, blurry, ugly, distortion."
+        "The video is not of a high quality, it has a low resolution. Watermark present in each frame. Strange motion trajectory. "
       ]
     },
     {

comfyui/v1/cogvideoxfunv1_workflow_v2v.json

@@ -184,7 +184,7 @@
         "Node name for S&R": "TextBox"
       },
       "widgets_values": [
-        "The video is not of a high quality, it has a low resolution, and the audio quality is not clear. Strange motion trajectory, a poor composition and deformed video, low resolution, duplicate and ugly, strange body structure, long and strange neck, bad teeth, bad eyes, bad limbs, bad hands, rotating camera, blurry camera, shaking camera. Deformation, low-resolution, blurry, ugly, distortion."
+        "The video is not of a high quality, it has a low resolution. Watermark present in each frame. Strange motion trajectory. "
       ]
     },
     {

predict_i2v.py

@@ -51,11 +51,11 @@ validation_image_start  = "asset/1.png"
 validation_image_end    = None
 
 # prompts
-prompt                  = "A dog is shaking head. The video is of high quality, and the view is very clear. High quality, masterpiece, best quality, highres, ultra-detailed, fantastic."
-negative_prompt         = "The video is not of a high quality, it has a low resolution, and the audio quality is not clear. Strange motion trajectory, a poor composition and deformed video, low resolution, duplicate and ugly, strange body structure, long and strange neck, bad teeth, bad eyes, bad limbs, bad hands, rotating camera, blurry camera, shaking camera. Deformation, low-resolution, blurry, ugly, distortion. "
+prompt                  = "A young woman with beautiful and clear eyes and blonde hair standing and white dress in a forest wearing a crown. She seems to be lost in thought, and the camera focuses on her face. The video is of high quality, and the view is very clear. High quality, masterpiece, best quality, highres, ultra-detailed, fantastic."
+negative_prompt         = "The video is not of a high quality, it has a low resolution. Watermark present in each frame. Strange motion trajectory.  "
 guidance_scale          = 6.0
 seed                    = 43
-num_inference_steps     = 25
+num_inference_steps     = 50
 lora_weight             = 0.55
 save_path               = "samples/cogvideox-fun-videos_i2v"
 

predict_t2v.py

@@ -42,11 +42,11 @@ fps                 = 8
 # Use torch.float16 if GPU does not support torch.bfloat16
 # ome graphics cards, such as v100, 2080ti, do not support torch.bfloat16
 weight_dtype        = torch.bfloat16
-prompt              = "A dog is shaking head. The video is of high quality, and the view is very clear. High quality, masterpiece, best quality, highres, ultra-detailed, fantastic."
-negative_prompt     = "The video is not of a high quality, it has a low resolution, and the audio quality is not clear. Strange motion trajectory, a poor composition and deformed video, low resolution, duplicate and ugly, strange body structure, long and strange neck, bad teeth, bad eyes, bad limbs, bad hands, rotating camera, blurry camera, shaking camera. Deformation, low-resolution, blurry, ugly, distortion. "
+prompt              = "A young woman with beautiful and clear eyes and blonde hair standing and white dress in a forest wearing a crown. She seems to be lost in thought, and the camera focuses on her face. The video is of high quality, and the view is very clear. High quality, masterpiece, best quality, highres, ultra-detailed, fantastic."
+negative_prompt     = "The video is not of a high quality, it has a low resolution. Watermark present in each frame. Strange motion trajectory.  "
 guidance_scale      = 6.0
 seed                = 43
-num_inference_steps = 25
+num_inference_steps = 50
 lora_weight         = 0.55
 save_path           = "samples/cogvideox-fun-videos-t2v"
 

predict_v2v.py

@@ -47,11 +47,11 @@ validation_video        = "asset/03480_03600_good_scenes.mp4"
 denoise_strength        = 0.70
 
 # prompts
-prompt                  = "A dog is shaking head. The video is of high quality, and the view is very clear. High quality, masterpiece, best quality, highres, ultra-detailed, fantastic."
-negative_prompt         = "The video is not of a high quality, it has a low resolution, and the audio quality is not clear. Strange motion trajectory, a poor composition and deformed video, low resolution, duplicate and ugly, strange body structure, long and strange neck, bad teeth, bad eyes, bad limbs, bad hands, rotating camera, blurry camera, shaking camera. Deformation, low-resolution, blurry, ugly, distortion. "
+prompt                  = "A young woman with beautiful and clear eyes and blonde hair standing and white dress in a forest wearing a crown. She seems to be lost in thought, and the camera focuses on her face. The video is of high quality, and the view is very clear. High quality, masterpiece, best quality, highres, ultra-detailed, fantastic."
+negative_prompt         = "The video is not of a high quality, it has a low resolution. Watermark present in each frame. Strange motion trajectory.  "
 guidance_scale          = 6.0
 seed                    = 43
-num_inference_steps     = 25
+num_inference_steps     = 50
 lora_weight             = 0.55
 save_path               = "samples/cogvideox-fun-videos_v2v"