saicharan1234 commited on
Commit
9552c2b
1 Parent(s): b569eb3

Upload folder using huggingface_hub

Browse files
Files changed (2) hide show
  1. README.md +25 -0
  2. config.yaml +48 -0
README.md ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: creativeml-openrail-m
3
+ base_model: CompVis/stable-diffusion-v1-4
4
+ training_prompt: A person of East Asian ethnicity standing in a well-lit office environment with large windows, speaking directly to the camera, wearing a white shirt, and conveying a calm and professional demeanor. The background is slightly blurred, showcasing greenery and modern office decor, with minimal distractions
5
+ tags:
6
+ - stable-diffusion
7
+ - stable-diffusion-diffusers
8
+ - text-to-image
9
+ - diffusers
10
+ - text-to-video
11
+ - tune-a-video
12
+ inference: false
13
+ ---
14
+
15
+ # Tune-A-Video - talking-man
16
+
17
+ ## Model description
18
+ - Base model: [CompVis/stable-diffusion-v1-4](https://huggingface.co/CompVis/stable-diffusion-v1-4)
19
+ - Training prompt: A person of East Asian ethnicity standing in a well-lit office environment with large windows, speaking directly to the camera, wearing a white shirt, and conveying a calm and professional demeanor. The background is slightly blurred, showcasing greenery and modern office decor, with minimal distractions
20
+
21
+
22
+
23
+ ## Related papers:
24
+ - [Tune-A-Video](https://arxiv.org/abs/2212.11565): One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation
25
+ - [Stable-Diffusion](https://arxiv.org/abs/2112.10752): High-Resolution Image Synthesis with Latent Diffusion Models
config.yaml ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ pretrained_model_path: checkpoints/CompVis/stable-diffusion-v1-4
2
+ output_dir: /home/user/app/experiments/talking-man
3
+ train_data:
4
+ video_path: /tmp/gradio/f79f070ba10b1b7872faa157ada00e09644ef2f2/Untitled Video.mp4
5
+ prompt: A person of East Asian ethnicity standing in a well-lit office environment
6
+ with large windows, speaking directly to the camera, wearing a white shirt, and
7
+ conveying a calm and professional demeanor. The background is slightly blurred,
8
+ showcasing greenery and modern office decor, with minimal distractions
9
+ n_sample_frames: 8
10
+ width: 512
11
+ height: 512
12
+ sample_start_idx: 0
13
+ sample_frame_rate: 1
14
+ validation_data:
15
+ prompts:
16
+ - A person of East Asian descent is standing in a bright office setting with large
17
+ windows, addressing the camera directly. They are dressed in a white shirt and
18
+ project a calm, professional demeanor. The background is slightly out of focus,
19
+ highlighting greenery and modern office furnishings, with minimal visual distractions
20
+ video_length: 8
21
+ width: 512
22
+ height: 512
23
+ num_inference_steps: 50
24
+ guidance_scale: 7.5
25
+ validation_steps: 100
26
+ trainable_modules:
27
+ - attn1.to_q
28
+ - attn2.to_q
29
+ - attn_temp
30
+ train_batch_size: 1
31
+ max_train_steps: 300
32
+ learning_rate: 3.5e-05
33
+ scale_lr: false
34
+ lr_scheduler: constant
35
+ lr_warmup_steps: 0
36
+ adam_beta1: 0.9
37
+ adam_beta2: 0.999
38
+ adam_weight_decay: 0.01
39
+ adam_epsilon: 1.0e-08
40
+ max_grad_norm: 1.0
41
+ gradient_accumulation_steps: 1
42
+ gradient_checkpointing: true
43
+ checkpointing_steps: 1000
44
+ resume_from_checkpoint: null
45
+ mixed_precision: fp16
46
+ use_8bit_adam: false
47
+ enable_xformers_memory_efficient_attention: true
48
+ seed: 31118