rp2024 commited on
Commit
0a183d6
1 Parent(s): 0befda7

Upload . with huggingface_hub

Browse files
Files changed (2) hide show
  1. README.md +25 -0
  2. config.yaml +42 -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 bird is flapping its wing
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 - birdgif-test
16
+
17
+ ## Model description
18
+ - Base model: [CompVis/stable-diffusion-v1-4](https://huggingface.co/CompVis/stable-diffusion-v1-4)
19
+ - Training prompt: a bird is flapping its wing
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 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ pretrained_model_path: checkpoints/CompVis/stable-diffusion-v1-4
2
+ output_dir: /home/user/app/experiments/birdgif-test
3
+ train_data:
4
+ video_path: /tmp/bird-wings-flying-featurexbavjmqd.gif
5
+ prompt: a bird is flapping its wing
6
+ n_sample_frames: 8
7
+ width: 512
8
+ height: 512
9
+ sample_start_idx: 0
10
+ sample_frame_rate: 1
11
+ validation_data:
12
+ prompts:
13
+ - a bird is flapping its wing
14
+ video_length: 8
15
+ width: 512
16
+ height: 512
17
+ num_inference_steps: 50
18
+ guidance_scale: 7.5
19
+ validation_steps: 100
20
+ trainable_modules:
21
+ - attn1.to_q
22
+ - attn2.to_q
23
+ - attn_temp
24
+ train_batch_size: 1
25
+ max_train_steps: 300
26
+ learning_rate: 3.5e-05
27
+ scale_lr: false
28
+ lr_scheduler: constant
29
+ lr_warmup_steps: 0
30
+ adam_beta1: 0.9
31
+ adam_beta2: 0.999
32
+ adam_weight_decay: 0.01
33
+ adam_epsilon: 1.0e-08
34
+ max_grad_norm: 1.0
35
+ gradient_accumulation_steps: 1
36
+ gradient_checkpointing: true
37
+ checkpointing_steps: 1000
38
+ resume_from_checkpoint: null
39
+ mixed_precision: fp16
40
+ use_8bit_adam: false
41
+ enable_xformers_memory_efficient_attention: true
42
+ seed: 0