Failed to load versions. Head to the versions page to see all versions for this model.
You're looking at a specific version of this model. Jump to the model overview.
zsxkib /animate-diff:a0850d5a
Input
Run this model in Node.js with one line of code:
npm install replicate
REPLICATE_API_TOKEN
environment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
import Replicate from "replicate";
const replicate = new Replicate({
auth: process.env.REPLICATE_API_TOKEN,
});
Run zsxkib/animate-diff using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run(
"zsxkib/animate-diff:a0850d5ac812f025a141591fe7abac5a7a778ac1690a548891830e235f6add03",
{
input: {
H: 512,
L: 16,
W: 512,
seed: 255224557,
alpha: 1,
steps: 25,
prompt: "photo of vocano, rocks, storm weather, wind, lava waves, lightning, 8k uhd, dslr, soft lighting, high quality, film grain, Fujifilm XT3",
n_prompt: "blur, haze, deformed iris, deformed pupils, semi-realistic, cgi, 3d, render, sketch, cartoon, drawing, anime, mutated hands and fingers, deformed, distorted, disfigured, poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, disconnected limbs, mutation, mutated, ugly, disgusting, amputation",
guidance_scale: 7.5,
dreambooth_type: "rcnzCartoon3d_v10",
lora_model_path: "",
motion_module_type: "mm_sd_v15_v2",
pretrained_model_path: "models/StableDiffusion/stable-diffusion-v1-5",
motion_module_lora_type: "ZoomIn"
}
}
);
// To access the file URL:
console.log(output[0].url()); //=> "http://example.com"
// To write the file to disk:
fs.writeFile("my-image.png", output[0]);
To learn more, take a look at the guide on getting started with Node.js.
pip install replicate
REPLICATE_API_TOKEN
environment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
import replicate
Run zsxkib/animate-diff using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run(
"zsxkib/animate-diff:a0850d5ac812f025a141591fe7abac5a7a778ac1690a548891830e235f6add03",
input={
"H": 512,
"L": 16,
"W": 512,
"seed": 255224557,
"alpha": 1,
"steps": 25,
"prompt": "photo of vocano, rocks, storm weather, wind, lava waves, lightning, 8k uhd, dslr, soft lighting, high quality, film grain, Fujifilm XT3",
"n_prompt": "blur, haze, deformed iris, deformed pupils, semi-realistic, cgi, 3d, render, sketch, cartoon, drawing, anime, mutated hands and fingers, deformed, distorted, disfigured, poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, disconnected limbs, mutation, mutated, ugly, disgusting, amputation",
"guidance_scale": 7.5,
"dreambooth_type": "rcnzCartoon3d_v10",
"lora_model_path": "",
"motion_module_type": "mm_sd_v15_v2",
"pretrained_model_path": "models/StableDiffusion/stable-diffusion-v1-5",
"motion_module_lora_type": "ZoomIn"
}
)
print(output)
To learn more, take a look at the guide on getting started with Python.
REPLICATE_API_TOKEN
environment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Run zsxkib/animate-diff using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
curl -s -X POST \
-H "Authorization: Bearer $REPLICATE_API_TOKEN" \
-H "Content-Type: application/json" \
-H "Prefer: wait" \
-d $'{
"version": "zsxkib/animate-diff:a0850d5ac812f025a141591fe7abac5a7a778ac1690a548891830e235f6add03",
"input": {
"H": 512,
"L": 16,
"W": 512,
"seed": 255224557,
"alpha": 1,
"steps": 25,
"prompt": "photo of vocano, rocks, storm weather, wind, lava waves, lightning, 8k uhd, dslr, soft lighting, high quality, film grain, Fujifilm XT3",
"n_prompt": "blur, haze, deformed iris, deformed pupils, semi-realistic, cgi, 3d, render, sketch, cartoon, drawing, anime, mutated hands and fingers, deformed, distorted, disfigured, poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, disconnected limbs, mutation, mutated, ugly, disgusting, amputation",
"guidance_scale": 7.5,
"dreambooth_type": "rcnzCartoon3d_v10",
"lora_model_path": "",
"motion_module_type": "mm_sd_v15_v2",
"pretrained_model_path": "models/StableDiffusion/stable-diffusion-v1-5",
"motion_module_lora_type": "ZoomIn"
}
}' \
https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Add a payment method to run this model.
By signing in, you agree to our
terms of service and privacy policy
Output
{
"completed_at": "2023-09-27T05:20:13.801298Z",
"created_at": "2023-09-27T05:17:56.643025Z",
"data_removed": false,
"error": null,
"id": "g5fxhedbc7c6qjeht3wymsmdma",
"input": {
"H": 512,
"L": 16,
"W": 512,
"seed": 255224557,
"alpha": 1,
"steps": 25,
"prompt": "photo of vocano, rocks, storm weather, wind, lava waves, lightning, 8k uhd, dslr, soft lighting, high quality, film grain, Fujifilm XT3",
"n_prompt": "blur, haze, deformed iris, deformed pupils, semi-realistic, cgi, 3d, render, sketch, cartoon, drawing, anime, mutated hands and fingers, deformed, distorted, disfigured, poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, disconnected limbs, mutation, mutated, ugly, disgusting, amputation",
"guidance_scale": 7.5,
"dreambooth_type": "rcnzCartoon3d_v10",
"lora_model_path": "",
"motion_module_type": "mm_sd_v15_v2",
"pretrained_model_path": "models/StableDiffusion/stable-diffusion-v1-5",
"motion_module_lora_type": "ZoomIn"
},
"logs": "loaded temporal unet's pretrained weights from models/StableDiffusion/stable-diffusion-v1-5/unet ...\n### missing keys: 588;\n### unexpected keys: 0;\n### Temporal Module Parameters: 453.20928 M\nload motion module from models/Motion_Module/mm_sd_v15_v2.ckpt\nload dreambooth model from models/DreamBooth_LoRA/rcnzCartoon3d_v10.safetensors\nSome weights of the model checkpoint at openai/clip-vit-large-patch14 were not used when initializing CLIPTextModel: ['vision_model.encoder.layers.9.self_attn.k_proj.weight', 'vision_model.encoder.layers.22.self_attn.k_proj.weight', 'vision_model.encoder.layers.5.mlp.fc1.weight', 'vision_model.encoder.layers.20.layer_norm2.bias', 'vision_model.encoder.layers.19.mlp.fc2.weight', 'vision_model.encoder.layers.6.layer_norm1.weight', 'vision_model.encoder.layers.7.mlp.fc1.bias', 'vision_model.encoder.layers.17.self_attn.k_proj.weight', 'vision_model.encoder.layers.0.self_attn.v_proj.weight', 'vision_model.encoder.layers.21.self_attn.q_proj.bias', 'vision_model.encoder.layers.3.self_attn.k_proj.bias', 'vision_model.encoder.layers.10.mlp.fc1.bias', 'vision_model.encoder.layers.15.layer_norm2.bias', 'vision_model.encoder.layers.20.mlp.fc1.bias', 'vision_model.encoder.layers.19.self_attn.k_proj.weight', 'vision_model.encoder.layers.11.self_attn.q_proj.bias', 'vision_model.encoder.layers.10.self_attn.v_proj.bias', 'vision_model.embeddings.patch_embedding.weight', 'vision_model.encoder.layers.6.self_attn.k_proj.bias', 'vision_model.encoder.layers.8.mlp.fc1.weight', 'vision_model.encoder.layers.0.self_attn.k_proj.weight', 'vision_model.encoder.layers.20.self_attn.v_proj.bias', 'vision_model.encoder.layers.2.self_attn.k_proj.bias', 'vision_model.encoder.layers.17.layer_norm1.bias', 'vision_model.encoder.layers.12.mlp.fc1.weight', 'vision_model.encoder.layers.4.self_attn.q_proj.bias', 'vision_model.encoder.layers.1.layer_norm1.weight', 'vision_model.encoder.layers.16.self_attn.k_proj.bias', 'vision_model.encoder.layers.14.self_attn.k_proj.bias', 'vision_model.encoder.layers.3.self_attn.k_proj.weight', 'vision_model.encoder.layers.8.self_attn.out_proj.weight', 'vision_model.encoder.layers.15.self_attn.q_proj.bias', 'vision_model.encoder.layers.2.self_attn.v_proj.weight', 'vision_model.encoder.layers.17.mlp.fc2.weight', 'vision_model.encoder.layers.18.self_attn.k_proj.weight', 'vision_model.encoder.layers.6.mlp.fc2.bias', 'vision_model.encoder.layers.17.self_attn.out_proj.bias', 'visual_projection.weight', 'vision_model.encoder.layers.15.mlp.fc1.bias', 'vision_model.encoder.layers.23.layer_norm1.bias', 'vision_model.encoder.layers.23.mlp.fc1.bias', 'vision_model.encoder.layers.22.self_attn.out_proj.weight', 'vision_model.encoder.layers.5.self_attn.k_proj.weight', 'vision_model.encoder.layers.22.self_attn.out_proj.bias', 'vision_model.encoder.layers.9.self_attn.v_proj.weight', 'vision_model.encoder.layers.21.self_attn.k_proj.bias', 'vision_model.encoder.layers.10.layer_norm2.bias', 'vision_model.encoder.layers.21.mlp.fc1.bias', 'vision_model.encoder.layers.7.self_attn.v_proj.weight', 'vision_model.encoder.layers.5.self_attn.out_proj.weight', 'vision_model.encoder.layers.1.self_attn.q_proj.bias', 'vision_model.encoder.layers.23.mlp.fc2.weight', 'vision_model.pre_layrnorm.bias', 'vision_model.encoder.layers.12.self_attn.out_proj.bias', 'vision_model.encoder.layers.13.self_attn.out_proj.weight', 'vision_model.encoder.layers.13.self_attn.v_proj.bias', 'vision_model.encoder.layers.9.mlp.fc2.bias', 'vision_model.encoder.layers.2.self_attn.q_proj.weight', 'vision_model.encoder.layers.5.self_attn.k_proj.bias', 'vision_model.encoder.layers.18.mlp.fc1.bias', 'vision_model.encoder.layers.2.self_attn.k_proj.weight', 'vision_model.encoder.layers.6.self_attn.out_proj.weight', 'text_projection.weight', 'vision_model.encoder.layers.7.self_attn.q_proj.bias', 'vision_model.encoder.layers.8.self_attn.q_proj.weight', 'vision_model.encoder.layers.15.self_attn.v_proj.weight', 'vision_model.pre_layrnorm.weight', 'vision_model.encoder.layers.20.self_attn.out_proj.weight', 'vision_model.encoder.layers.1.layer_norm2.bias', 'vision_model.encoder.layers.18.layer_norm2.bias', 'vision_model.encoder.layers.11.mlp.fc2.weight', 'vision_model.encoder.layers.21.mlp.fc2.weight', 'vision_model.encoder.layers.10.self_attn.v_proj.weight', 'vision_model.encoder.layers.4.layer_norm2.bias', 'vision_model.encoder.layers.23.layer_norm1.weight', 'vision_model.encoder.layers.13.layer_norm2.bias', 'vision_model.encoder.layers.0.mlp.fc1.weight', 'vision_model.encoder.layers.10.layer_norm1.weight', 'vision_model.encoder.layers.2.self_attn.out_proj.bias', 'vision_model.encoder.layers.9.self_attn.v_proj.bias', 'vision_model.encoder.layers.4.self_attn.q_proj.weight', 'vision_model.encoder.layers.6.self_attn.out_proj.bias', 'vision_model.encoder.layers.20.mlp.fc1.weight', 'vision_model.encoder.layers.23.mlp.fc2.bias', 'vision_model.encoder.layers.15.layer_norm1.weight', 'vision_model.encoder.layers.16.layer_norm1.bias', 'vision_model.encoder.layers.17.mlp.fc1.weight', 'vision_model.encoder.layers.2.mlp.fc1.weight', 'vision_model.encoder.layers.21.mlp.fc2.bias', 'vision_model.encoder.layers.5.self_attn.q_proj.weight', 'vision_model.encoder.layers.11.mlp.fc2.bias', 'vision_model.encoder.layers.4.layer_norm2.weight', 'vision_model.encoder.layers.7.self_attn.k_proj.bias', 'vision_model.encoder.layers.13.mlp.fc1.weight', 'vision_model.encoder.layers.10.self_attn.q_proj.weight', 'vision_model.encoder.layers.11.self_attn.k_proj.bias', 'vision_model.encoder.layers.15.layer_norm1.bias', 'vision_model.encoder.layers.17.mlp.fc1.bias', 'vision_model.encoder.layers.1.self_attn.k_proj.bias', 'vision_model.encoder.layers.6.layer_norm2.weight', 'vision_model.encoder.layers.20.layer_norm2.weight', 'vision_model.encoder.layers.18.mlp.fc2.bias', 'vision_model.encoder.layers.18.self_attn.v_proj.bias', 'vision_model.encoder.layers.1.layer_norm2.weight', 'vision_model.encoder.layers.8.self_attn.k_proj.bias', 'vision_model.embeddings.position_embedding.weight', 'vision_model.encoder.layers.19.layer_norm1.bias', 'vision_model.encoder.layers.23.layer_norm2.weight', 'vision_model.encoder.layers.18.layer_norm1.bias', 'vision_model.encoder.layers.8.mlp.fc2.weight', 'vision_model.encoder.layers.0.layer_norm2.bias', 'vision_model.encoder.layers.5.mlp.fc2.bias', 'vision_model.encoder.layers.4.self_attn.v_proj.bias', 'vision_model.encoder.layers.4.layer_norm1.weight', 'vision_model.encoder.layers.9.self_attn.k_proj.bias', 'vision_model.encoder.layers.0.self_attn.out_proj.bias', 'vision_model.encoder.layers.19.self_attn.q_proj.bias', 'vision_model.encoder.layers.2.layer_norm2.bias', 'vision_model.encoder.layers.19.layer_norm1.weight', 'vision_model.encoder.layers.5.layer_norm1.bias', 'vision_model.encoder.layers.18.mlp.fc2.weight', 'vision_model.encoder.layers.2.self_attn.out_proj.weight', 'vision_model.encoder.layers.14.mlp.fc1.weight', 'vision_model.encoder.layers.17.layer_norm2.bias', 'vision_model.encoder.layers.23.self_attn.k_proj.weight', 'vision_model.encoder.layers.15.self_attn.q_proj.weight', 'vision_model.encoder.layers.23.layer_norm2.bias', 'vision_model.encoder.layers.7.self_attn.out_proj.bias', 'vision_model.encoder.layers.6.layer_norm1.bias', 'vision_model.encoder.layers.13.layer_norm1.bias', 'vision_model.encoder.layers.21.layer_norm1.bias', 'vision_model.encoder.layers.0.mlp.fc2.bias', 'vision_model.encoder.layers.9.mlp.fc1.bias', 'vision_model.post_layernorm.weight', 'vision_model.encoder.layers.3.layer_norm1.weight', 'vision_model.encoder.layers.6.self_attn.k_proj.weight', 'vision_model.encoder.layers.8.self_attn.q_proj.bias', 'vision_model.encoder.layers.3.mlp.fc1.bias', 'vision_model.encoder.layers.7.self_attn.k_proj.weight', 'vision_model.encoder.layers.22.self_attn.q_proj.weight', 'vision_model.encoder.layers.20.self_attn.q_proj.bias', 'vision_model.post_layernorm.bias', 'vision_model.encoder.layers.19.self_attn.v_proj.bias', 'vision_model.encoder.layers.9.layer_norm2.weight', 'vision_model.encoder.layers.17.self_attn.k_proj.bias', 'vision_model.encoder.layers.16.mlp.fc2.weight', 'vision_model.encoder.layers.13.self_attn.k_proj.weight', 'vision_model.encoder.layers.17.layer_norm2.weight', 'vision_model.encoder.layers.8.mlp.fc2.bias', 'vision_model.encoder.layers.4.layer_norm1.bias', 'vision_model.encoder.layers.13.self_attn.v_proj.weight', 'vision_model.encoder.layers.4.self_attn.v_proj.weight', 'vision_model.encoder.layers.16.self_attn.out_proj.weight', 'vision_model.encoder.layers.3.layer_norm2.weight', 'vision_model.encoder.layers.4.self_attn.k_proj.bias', 'vision_model.encoder.layers.20.layer_norm1.bias', 'vision_model.encoder.layers.2.mlp.fc2.bias', 'vision_model.encoder.layers.12.layer_norm1.bias', 'vision_model.encoder.layers.11.mlp.fc1.bias', 'vision_model.encoder.layers.9.mlp.fc1.weight', 'vision_model.encoder.layers.9.self_attn.out_proj.bias', 'vision_model.encoder.layers.19.self_attn.out_proj.weight', 'vision_model.encoder.layers.6.self_attn.v_proj.weight', 'vision_model.encoder.layers.14.self_attn.v_proj.weight', 'vision_model.encoder.layers.2.mlp.fc1.bias', 'vision_model.encoder.layers.13.mlp.fc1.bias', 'vision_model.encoder.layers.0.layer_norm1.weight', 'vision_model.encoder.layers.17.self_attn.v_proj.weight', 'vision_model.encoder.layers.23.self_attn.out_proj.bias', 'vision_model.encoder.layers.21.mlp.fc1.weight', 'vision_model.encoder.layers.22.layer_norm2.weight', 'vision_model.encoder.layers.8.self_attn.out_proj.bias', 'vision_model.encoder.layers.12.layer_norm2.bias', 'vision_model.encoder.layers.20.self_attn.out_proj.bias', 'vision_model.encoder.layers.2.layer_norm1.bias', 'vision_model.encoder.layers.8.layer_norm1.bias', 'vision_model.encoder.layers.14.layer_norm2.bias', 'vision_model.encoder.layers.12.self_attn.q_proj.bias', 'vision_model.encoder.layers.10.self_attn.out_proj.weight', 'vision_model.encoder.layers.7.self_attn.v_proj.bias', 'vision_model.encoder.layers.11.self_attn.q_proj.weight', 'vision_model.encoder.layers.22.layer_norm1.weight', 'vision_model.encoder.layers.6.mlp.fc2.weight', 'vision_model.encoder.layers.4.mlp.fc1.bias', 'vision_model.encoder.layers.9.layer_norm1.weight', 'vision_model.encoder.layers.19.mlp.fc1.weight', 'vision_model.encoder.layers.4.mlp.fc2.bias', 'vision_model.encoder.layers.7.mlp.fc2.bias', 'vision_model.encoder.layers.16.self_attn.v_proj.bias', 'vision_model.encoder.layers.5.layer_norm2.bias', 'vision_model.encoder.layers.2.self_attn.v_proj.bias', 'vision_model.encoder.layers.19.layer_norm2.weight', 'vision_model.encoder.layers.13.mlp.fc2.weight', 'vision_model.encoder.layers.16.self_attn.out_proj.bias', 'vision_model.encoder.layers.20.self_attn.v_proj.weight', 'vision_model.encoder.layers.18.self_attn.k_proj.bias', 'vision_model.encoder.layers.6.self_attn.q_proj.weight', 'vision_model.encoder.layers.19.mlp.fc1.bias', 'vision_model.encoder.layers.0.self_attn.out_proj.weight', 'vision_model.encoder.layers.10.self_attn.out_proj.bias', 'vision_model.encoder.layers.13.self_attn.k_proj.bias', 'vision_model.encoder.layers.10.mlp.fc2.weight', 'vision_model.encoder.layers.1.mlp.fc1.bias', 'vision_model.encoder.layers.14.mlp.fc1.bias', 'vision_model.encoder.layers.13.self_attn.out_proj.bias', 'vision_model.encoder.layers.2.self_attn.q_proj.bias', 'logit_scale', 'vision_model.encoder.layers.21.self_attn.q_proj.weight', 'vision_model.encoder.layers.4.mlp.fc2.weight', 'vision_model.encoder.layers.19.self_attn.v_proj.weight', 'vision_model.encoder.layers.17.self_attn.q_proj.weight', 'vision_model.encoder.layers.8.self_attn.v_proj.weight', 'vision_model.encoder.layers.13.mlp.fc2.bias', 'vision_model.encoder.layers.15.mlp.fc2.bias', 'vision_model.encoder.layers.18.self_attn.q_proj.bias', 'vision_model.encoder.layers.10.self_attn.k_proj.weight', 'vision_model.encoder.layers.10.mlp.fc1.weight', 'vision_model.encoder.layers.17.layer_norm1.weight', 'vision_model.encoder.layers.20.mlp.fc2.bias', 'vision_model.encoder.layers.23.self_attn.q_proj.weight', 'vision_model.encoder.layers.12.self_attn.k_proj.bias', 'vision_model.encoder.layers.0.self_attn.q_proj.bias', 'vision_model.encoder.layers.20.self_attn.q_proj.weight', 'vision_model.encoder.layers.16.layer_norm2.weight', 'vision_model.encoder.layers.3.self_attn.v_proj.weight', 'vision_model.encoder.layers.12.layer_norm1.weight', 'vision_model.encoder.layers.0.mlp.fc2.weight', 'vision_model.encoder.layers.14.self_attn.k_proj.weight', 'vision_model.encoder.layers.4.self_attn.out_proj.weight', 'vision_model.encoder.layers.7.layer_norm2.bias', 'vision_model.encoder.layers.22.mlp.fc1.bias', 'vision_model.encoder.layers.16.mlp.fc1.bias', 'vision_model.encoder.layers.8.self_attn.k_proj.weight', 'vision_model.encoder.layers.1.mlp.fc2.bias', 'vision_model.encoder.layers.14.self_attn.out_proj.bias', 'vision_model.encoder.layers.14.self_attn.out_proj.weight', 'vision_model.encoder.layers.1.self_attn.v_proj.bias', 'vision_model.encoder.layers.10.self_attn.q_proj.bias', 'vision_model.encoder.layers.14.layer_norm2.weight', 'vision_model.encoder.layers.21.layer_norm2.weight', 'vision_model.encoder.layers.13.self_attn.q_proj.bias', 'vision_model.encoder.layers.1.self_attn.out_proj.bias', 'vision_model.encoder.layers.16.mlp.fc2.bias', 'vision_model.encoder.layers.4.self_attn.k_proj.weight', 'vision_model.encoder.layers.3.self_attn.out_proj.weight', 'vision_model.encoder.layers.11.self_attn.out_proj.weight', 'vision_model.encoder.layers.0.self_attn.q_proj.weight', 'vision_model.encoder.layers.0.self_attn.v_proj.bias', 'vision_model.encoder.layers.12.layer_norm2.weight', 'vision_model.encoder.layers.11.self_attn.k_proj.weight', 'vision_model.encoder.layers.6.self_attn.q_proj.bias', 'vision_model.encoder.layers.11.layer_norm1.weight', 'vision_model.encoder.layers.3.layer_norm1.bias', 'vision_model.encoder.layers.12.self_attn.v_proj.weight', 'vision_model.encoder.layers.7.layer_norm1.weight', 'vision_model.encoder.layers.10.layer_norm2.weight', 'vision_model.encoder.layers.5.self_attn.out_proj.bias', 'vision_model.encoder.layers.7.self_attn.out_proj.weight', 'vision_model.encoder.layers.23.self_attn.v_proj.bias', 'vision_model.encoder.layers.1.self_attn.k_proj.weight', 'vision_model.encoder.layers.11.self_attn.v_proj.weight', 'vision_model.encoder.layers.8.self_attn.v_proj.bias', 'vision_model.encoder.layers.22.layer_norm2.bias', 'vision_model.encoder.layers.2.layer_norm2.weight', 'vision_model.encoder.layers.18.self_attn.out_proj.weight', 'vision_model.encoder.layers.16.mlp.fc1.weight', 'vision_model.encoder.layers.19.self_attn.out_proj.bias', 'vision_model.encoder.layers.11.layer_norm2.weight', 'vision_model.encoder.layers.6.self_attn.v_proj.bias', 'vision_model.encoder.layers.11.layer_norm1.bias', 'vision_model.encoder.layers.23.self_attn.q_proj.bias', 'vision_model.encoder.layers.16.layer_norm2.bias', 'vision_model.encoder.layers.8.layer_norm1.weight', 'vision_model.encoder.layers.16.self_attn.v_proj.weight', 'vision_model.encoder.layers.23.self_attn.out_proj.weight', 'vision_model.encoder.layers.1.self_attn.q_proj.weight', 'vision_model.encoder.layers.14.mlp.fc2.weight', 'vision_model.encoder.layers.21.layer_norm1.weight', 'vision_model.encoder.layers.19.self_attn.q_proj.weight', 'vision_model.encoder.layers.13.layer_norm2.weight', 'vision_model.encoder.layers.14.self_attn.v_proj.bias', 'vision_model.encoder.layers.12.self_attn.q_proj.weight', 'vision_model.encoder.layers.22.mlp.fc2.bias', 'vision_model.encoder.layers.3.self_attn.v_proj.bias', 'vision_model.encoder.layers.1.layer_norm1.bias', 'vision_model.encoder.layers.3.self_attn.q_proj.bias', 'vision_model.encoder.layers.7.mlp.fc1.weight', 'vision_model.encoder.layers.11.self_attn.out_proj.bias', 'vision_model.encoder.layers.16.self_attn.q_proj.weight', 'vision_model.encoder.layers.9.mlp.fc2.weight', 'vision_model.encoder.layers.7.self_attn.q_proj.weight', 'vision_model.encoder.layers.3.layer_norm2.bias', 'vision_model.encoder.layers.19.mlp.fc2.bias', 'vision_model.encoder.layers.20.self_attn.k_proj.bias', 'vision_model.encoder.layers.5.self_attn.q_proj.bias', 'vision_model.encoder.layers.3.mlp.fc2.bias', 'vision_model.encoder.layers.18.self_attn.out_proj.bias', 'vision_model.encoder.layers.22.mlp.fc2.weight', 'vision_model.encoder.layers.5.self_attn.v_proj.weight', 'vision_model.encoder.layers.8.layer_norm2.bias', 'vision_model.encoder.layers.15.self_attn.out_proj.weight', 'vision_model.encoder.layers.18.self_attn.q_proj.weight', 'vision_model.encoder.layers.3.self_attn.q_proj.weight', 'vision_model.encoder.layers.21.self_attn.out_proj.weight', 'vision_model.encoder.layers.18.layer_norm1.weight', 'vision_model.encoder.layers.17.self_attn.out_proj.weight', 'vision_model.encoder.layers.14.mlp.fc2.bias', 'vision_model.encoder.layers.15.self_attn.out_proj.bias', 'vision_model.encoder.layers.12.self_attn.v_proj.bias', 'vision_model.encoder.layers.11.mlp.fc1.weight', 'vision_model.encoder.layers.12.mlp.fc1.bias', 'vision_model.encoder.layers.23.self_attn.v_proj.weight', 'vision_model.encoder.layers.17.self_attn.q_proj.bias', 'vision_model.encoder.layers.21.self_attn.k_proj.weight', 'vision_model.encoder.layers.21.layer_norm2.bias', 'vision_model.encoder.layers.0.mlp.fc1.bias', 'vision_model.encoder.layers.18.mlp.fc1.weight', 'vision_model.encoder.layers.15.self_attn.k_proj.weight', 'vision_model.encoder.layers.16.self_attn.k_proj.weight', 'vision_model.encoder.layers.1.self_attn.out_proj.weight', 'vision_model.encoder.layers.2.mlp.fc2.weight', 'vision_model.encoder.layers.16.self_attn.q_proj.bias', 'vision_model.encoder.layers.1.mlp.fc1.weight', 'vision_model.encoder.layers.9.layer_norm2.bias', 'vision_model.encoder.layers.3.mlp.fc2.weight', 'vision_model.encoder.layers.15.self_attn.k_proj.bias', 'vision_model.encoder.layers.22.self_attn.k_proj.bias', 'vision_model.encoder.layers.15.self_attn.v_proj.bias', 'vision_model.encoder.layers.0.layer_norm1.bias', 'vision_model.encoder.layers.12.self_attn.out_proj.weight', 'vision_model.encoder.layers.5.self_attn.v_proj.bias', 'vision_model.encoder.layers.22.mlp.fc1.weight', 'vision_model.encoder.layers.1.self_attn.v_proj.weight', 'vision_model.encoder.layers.20.self_attn.k_proj.weight', 'vision_model.encoder.layers.17.mlp.fc2.bias', 'vision_model.encoder.layers.12.mlp.fc2.weight', 'vision_model.encoder.layers.17.self_attn.v_proj.bias', 'vision_model.encoder.layers.21.self_attn.out_proj.bias', 'vision_model.encoder.layers.3.self_attn.out_proj.bias', 'vision_model.encoder.layers.6.mlp.fc1.bias', 'vision_model.encoder.layers.5.layer_norm2.weight', 'vision_model.encoder.layers.21.self_attn.v_proj.bias', 'vision_model.encoder.layers.16.layer_norm1.weight', 'vision_model.encoder.layers.11.self_attn.v_proj.bias', 'vision_model.encoder.layers.12.self_attn.k_proj.weight', 'vision_model.encoder.layers.5.layer_norm1.weight', 'vision_model.encoder.layers.13.self_attn.q_proj.weight', 'vision_model.encoder.layers.10.layer_norm1.bias', 'vision_model.encoder.layers.15.mlp.fc1.weight', 'vision_model.embeddings.position_ids', 'vision_model.encoder.layers.10.self_attn.k_proj.bias', 'vision_model.encoder.layers.14.layer_norm1.weight', 'vision_model.encoder.layers.20.layer_norm1.weight', 'vision_model.encoder.layers.22.layer_norm1.bias', 'vision_model.encoder.layers.7.layer_norm2.weight', 'vision_model.encoder.layers.15.layer_norm2.weight', 'vision_model.encoder.layers.8.mlp.fc1.bias', 'vision_model.encoder.layers.9.self_attn.q_proj.bias', 'vision_model.encoder.layers.22.self_attn.v_proj.bias', 'vision_model.encoder.layers.23.self_attn.k_proj.bias', 'vision_model.encoder.layers.9.self_attn.out_proj.weight', 'vision_model.encoder.layers.7.mlp.fc2.weight', 'vision_model.encoder.layers.2.layer_norm1.weight', 'vision_model.encoder.layers.22.self_attn.q_proj.bias', 'vision_model.encoder.layers.18.self_attn.v_proj.weight', 'vision_model.encoder.layers.0.self_attn.k_proj.bias', 'vision_model.encoder.layers.11.layer_norm2.bias', 'vision_model.encoder.layers.14.self_attn.q_proj.bias', 'vision_model.encoder.layers.19.self_attn.k_proj.bias', 'vision_model.encoder.layers.6.layer_norm2.bias', 'vision_model.encoder.layers.19.layer_norm2.bias', 'vision_model.encoder.layers.14.self_attn.q_proj.weight', 'vision_model.encoder.layers.8.layer_norm2.weight', 'vision_model.encoder.layers.14.layer_norm1.bias', 'vision_model.encoder.layers.4.self_attn.out_proj.bias', 'vision_model.encoder.layers.18.layer_norm2.weight', 'vision_model.embeddings.class_embedding', 'vision_model.encoder.layers.23.mlp.fc1.weight', 'vision_model.encoder.layers.7.layer_norm1.bias', 'vision_model.encoder.layers.21.self_attn.v_proj.weight', 'vision_model.encoder.layers.0.layer_norm2.weight', 'vision_model.encoder.layers.3.mlp.fc1.weight', 'vision_model.encoder.layers.22.self_attn.v_proj.weight', 'vision_model.encoder.layers.20.mlp.fc2.weight', 'vision_model.encoder.layers.1.mlp.fc2.weight', 'vision_model.encoder.layers.15.mlp.fc2.weight', 'vision_model.encoder.layers.4.mlp.fc1.weight', 'vision_model.encoder.layers.6.mlp.fc1.weight', 'vision_model.encoder.layers.12.mlp.fc2.bias', 'vision_model.encoder.layers.13.layer_norm1.weight', 'vision_model.encoder.layers.9.self_attn.q_proj.weight', 'vision_model.encoder.layers.5.mlp.fc1.bias', 'vision_model.encoder.layers.10.mlp.fc2.bias', 'vision_model.encoder.layers.5.mlp.fc2.weight', 'vision_model.encoder.layers.9.layer_norm1.bias']\n- This IS expected if you are initializing CLIPTextModel from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model).\n- This IS NOT expected if you are initializing CLIPTextModel from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).\nload motion LoRA from models/MotionLoRA/v2_lora_ZoomIn.ckpt\ncurrent seed: 255224557\nsampling photo of vocano, rocks, storm weather, wind, lava waves, lightning, 8k uhd, dslr, soft lighting, high quality, film grain, Fujifilm XT3 ...\n 0%| | 0/25 [00:00<?, ?it/s]\n 4%|▍ | 1/25 [00:02<00:54, 2.27s/it]\n 8%|▊ | 2/25 [00:04<00:52, 2.28s/it]\n 12%|█▏ | 3/25 [00:06<00:50, 2.28s/it]\n 16%|█▌ | 4/25 [00:09<00:48, 2.29s/it]\n 20%|██ | 5/25 [00:11<00:45, 2.29s/it]\n 24%|██▍ | 6/25 [00:13<00:43, 2.29s/it]\n 28%|██▊ | 7/25 [00:16<00:41, 2.29s/it]\n 32%|███▏ | 8/25 [00:18<00:38, 2.29s/it]\n 36%|███▌ | 9/25 [00:20<00:36, 2.30s/it]\n 40%|████ | 10/25 [00:22<00:34, 2.30s/it]\n 44%|████▍ | 11/25 [00:25<00:32, 2.30s/it]\n 48%|████▊ | 12/25 [00:27<00:29, 2.29s/it]\n 52%|█████▏ | 13/25 [00:29<00:27, 2.29s/it]\n 56%|█████▌ | 14/25 [00:32<00:25, 2.29s/it]\n 60%|██████ | 15/25 [00:34<00:22, 2.29s/it]\n 64%|██████▍ | 16/25 [00:36<00:20, 2.29s/it]\n 68%|██████▊ | 17/25 [00:38<00:18, 2.29s/it]\n 72%|███████▏ | 18/25 [00:41<00:16, 2.29s/it]\n 76%|███████▌ | 19/25 [00:43<00:13, 2.29s/it]\n 80%|████████ | 20/25 [00:45<00:11, 2.29s/it]\n 84%|████████▍ | 21/25 [00:48<00:09, 2.29s/it]\n 88%|████████▊ | 22/25 [00:50<00:06, 2.29s/it]\n 92%|█████████▏| 23/25 [00:52<00:04, 2.29s/it]\n 96%|█████████▌| 24/25 [00:54<00:02, 2.29s/it]\n100%|██████████| 25/25 [00:57<00:00, 2.29s/it]\n100%|██████████| 25/25 [00:57<00:00, 2.29s/it]\n 0%| | 0/16 [00:00<?, ?it/s]\n 31%|███▏ | 5/16 [00:00<00:00, 38.50it/s]\n 56%|█████▋ | 9/16 [00:00<00:00, 17.10it/s]\n 75%|███████▌ | 12/16 [00:00<00:00, 14.53it/s]\n 88%|████████▊ | 14/16 [00:00<00:00, 13.60it/s]\n100%|██████████| 16/16 [00:01<00:00, 12.96it/s]\n100%|██████████| 16/16 [00:01<00:00, 14.72it/s]\nsave to samples/3fe6f708d6cbea0df905f54a72a841e4-2023-09-27T05-18-58/sample/photoofvocanorocksstorm.gif",
"metrics": {
"predict_time": 75.713918,
"total_time": 137.158273
},
"output": [
"https://pbxt.replicate.delivery/yCUm0TcRnV7RHJfybeh9LIjxLn4fNgfaSMDZY6GxcPEvYbhGB/0-photoofvocanorocksstorm.gif"
],
"started_at": "2023-09-27T05:18:58.087380Z",
"status": "succeeded",
"urls": {
"get": "https://api.replicate.com/v1/predictions/g5fxhedbc7c6qjeht3wymsmdma",
"cancel": "https://api.replicate.com/v1/predictions/g5fxhedbc7c6qjeht3wymsmdma/cancel"
},
"version": "a0850d5ac812f025a141591fe7abac5a7a778ac1690a548891830e235f6add03"
}
loaded temporal unet's pretrained weights from models/StableDiffusion/stable-diffusion-v1-5/unet ...
### missing keys: 588;
### unexpected keys: 0;
### Temporal Module Parameters: 453.20928 M
load motion module from models/Motion_Module/mm_sd_v15_v2.ckpt
load dreambooth model from models/DreamBooth_LoRA/rcnzCartoon3d_v10.safetensors
Some weights of the model checkpoint at openai/clip-vit-large-patch14 were not used when initializing CLIPTextModel: ['vision_model.encoder.layers.9.self_attn.k_proj.weight', 'vision_model.encoder.layers.22.self_attn.k_proj.weight', 'vision_model.encoder.layers.5.mlp.fc1.weight', 'vision_model.encoder.layers.20.layer_norm2.bias', 'vision_model.encoder.layers.19.mlp.fc2.weight', 'vision_model.encoder.layers.6.layer_norm1.weight', 'vision_model.encoder.layers.7.mlp.fc1.bias', 'vision_model.encoder.layers.17.self_attn.k_proj.weight', 'vision_model.encoder.layers.0.self_attn.v_proj.weight', 'vision_model.encoder.layers.21.self_attn.q_proj.bias', 'vision_model.encoder.layers.3.self_attn.k_proj.bias', 'vision_model.encoder.layers.10.mlp.fc1.bias', 'vision_model.encoder.layers.15.layer_norm2.bias', 'vision_model.encoder.layers.20.mlp.fc1.bias', 'vision_model.encoder.layers.19.self_attn.k_proj.weight', 'vision_model.encoder.layers.11.self_attn.q_proj.bias', 'vision_model.encoder.layers.10.self_attn.v_proj.bias', 'vision_model.embeddings.patch_embedding.weight', 'vision_model.encoder.layers.6.self_attn.k_proj.bias', 'vision_model.encoder.layers.8.mlp.fc1.weight', 'vision_model.encoder.layers.0.self_attn.k_proj.weight', 'vision_model.encoder.layers.20.self_attn.v_proj.bias', 'vision_model.encoder.layers.2.self_attn.k_proj.bias', 'vision_model.encoder.layers.17.layer_norm1.bias', 'vision_model.encoder.layers.12.mlp.fc1.weight', 'vision_model.encoder.layers.4.self_attn.q_proj.bias', 'vision_model.encoder.layers.1.layer_norm1.weight', 'vision_model.encoder.layers.16.self_attn.k_proj.bias', 'vision_model.encoder.layers.14.self_attn.k_proj.bias', 'vision_model.encoder.layers.3.self_attn.k_proj.weight', 'vision_model.encoder.layers.8.self_attn.out_proj.weight', 'vision_model.encoder.layers.15.self_attn.q_proj.bias', 'vision_model.encoder.layers.2.self_attn.v_proj.weight', 'vision_model.encoder.layers.17.mlp.fc2.weight', 'vision_model.encoder.layers.18.self_attn.k_proj.weight', 'vision_model.encoder.layers.6.mlp.fc2.bias', 'vision_model.encoder.layers.17.self_attn.out_proj.bias', 'visual_projection.weight', 'vision_model.encoder.layers.15.mlp.fc1.bias', 'vision_model.encoder.layers.23.layer_norm1.bias', 'vision_model.encoder.layers.23.mlp.fc1.bias', 'vision_model.encoder.layers.22.self_attn.out_proj.weight', 'vision_model.encoder.layers.5.self_attn.k_proj.weight', 'vision_model.encoder.layers.22.self_attn.out_proj.bias', 'vision_model.encoder.layers.9.self_attn.v_proj.weight', 'vision_model.encoder.layers.21.self_attn.k_proj.bias', 'vision_model.encoder.layers.10.layer_norm2.bias', 'vision_model.encoder.layers.21.mlp.fc1.bias', 'vision_model.encoder.layers.7.self_attn.v_proj.weight', 'vision_model.encoder.layers.5.self_attn.out_proj.weight', 'vision_model.encoder.layers.1.self_attn.q_proj.bias', 'vision_model.encoder.layers.23.mlp.fc2.weight', 'vision_model.pre_layrnorm.bias', 'vision_model.encoder.layers.12.self_attn.out_proj.bias', 'vision_model.encoder.layers.13.self_attn.out_proj.weight', 'vision_model.encoder.layers.13.self_attn.v_proj.bias', 'vision_model.encoder.layers.9.mlp.fc2.bias', 'vision_model.encoder.layers.2.self_attn.q_proj.weight', 'vision_model.encoder.layers.5.self_attn.k_proj.bias', 'vision_model.encoder.layers.18.mlp.fc1.bias', 'vision_model.encoder.layers.2.self_attn.k_proj.weight', 'vision_model.encoder.layers.6.self_attn.out_proj.weight', 'text_projection.weight', 'vision_model.encoder.layers.7.self_attn.q_proj.bias', 'vision_model.encoder.layers.8.self_attn.q_proj.weight', 'vision_model.encoder.layers.15.self_attn.v_proj.weight', 'vision_model.pre_layrnorm.weight', 'vision_model.encoder.layers.20.self_attn.out_proj.weight', 'vision_model.encoder.layers.1.layer_norm2.bias', 'vision_model.encoder.layers.18.layer_norm2.bias', 'vision_model.encoder.layers.11.mlp.fc2.weight', 'vision_model.encoder.layers.21.mlp.fc2.weight', 'vision_model.encoder.layers.10.self_attn.v_proj.weight', 'vision_model.encoder.layers.4.layer_norm2.bias', 'vision_model.encoder.layers.23.layer_norm1.weight', 'vision_model.encoder.layers.13.layer_norm2.bias', 'vision_model.encoder.layers.0.mlp.fc1.weight', 'vision_model.encoder.layers.10.layer_norm1.weight', 'vision_model.encoder.layers.2.self_attn.out_proj.bias', 'vision_model.encoder.layers.9.self_attn.v_proj.bias', 'vision_model.encoder.layers.4.self_attn.q_proj.weight', 'vision_model.encoder.layers.6.self_attn.out_proj.bias', 'vision_model.encoder.layers.20.mlp.fc1.weight', 'vision_model.encoder.layers.23.mlp.fc2.bias', 'vision_model.encoder.layers.15.layer_norm1.weight', 'vision_model.encoder.layers.16.layer_norm1.bias', 'vision_model.encoder.layers.17.mlp.fc1.weight', 'vision_model.encoder.layers.2.mlp.fc1.weight', 'vision_model.encoder.layers.21.mlp.fc2.bias', 'vision_model.encoder.layers.5.self_attn.q_proj.weight', 'vision_model.encoder.layers.11.mlp.fc2.bias', 'vision_model.encoder.layers.4.layer_norm2.weight', 'vision_model.encoder.layers.7.self_attn.k_proj.bias', 'vision_model.encoder.layers.13.mlp.fc1.weight', 'vision_model.encoder.layers.10.self_attn.q_proj.weight', 'vision_model.encoder.layers.11.self_attn.k_proj.bias', 'vision_model.encoder.layers.15.layer_norm1.bias', 'vision_model.encoder.layers.17.mlp.fc1.bias', 'vision_model.encoder.layers.1.self_attn.k_proj.bias', 'vision_model.encoder.layers.6.layer_norm2.weight', 'vision_model.encoder.layers.20.layer_norm2.weight', 'vision_model.encoder.layers.18.mlp.fc2.bias', 'vision_model.encoder.layers.18.self_attn.v_proj.bias', 'vision_model.encoder.layers.1.layer_norm2.weight', 'vision_model.encoder.layers.8.self_attn.k_proj.bias', 'vision_model.embeddings.position_embedding.weight', 'vision_model.encoder.layers.19.layer_norm1.bias', 'vision_model.encoder.layers.23.layer_norm2.weight', 'vision_model.encoder.layers.18.layer_norm1.bias', 'vision_model.encoder.layers.8.mlp.fc2.weight', 'vision_model.encoder.layers.0.layer_norm2.bias', 'vision_model.encoder.layers.5.mlp.fc2.bias', 'vision_model.encoder.layers.4.self_attn.v_proj.bias', 'vision_model.encoder.layers.4.layer_norm1.weight', 'vision_model.encoder.layers.9.self_attn.k_proj.bias', 'vision_model.encoder.layers.0.self_attn.out_proj.bias', 'vision_model.encoder.layers.19.self_attn.q_proj.bias', 'vision_model.encoder.layers.2.layer_norm2.bias', 'vision_model.encoder.layers.19.layer_norm1.weight', 'vision_model.encoder.layers.5.layer_norm1.bias', 'vision_model.encoder.layers.18.mlp.fc2.weight', 'vision_model.encoder.layers.2.self_attn.out_proj.weight', 'vision_model.encoder.layers.14.mlp.fc1.weight', 'vision_model.encoder.layers.17.layer_norm2.bias', 'vision_model.encoder.layers.23.self_attn.k_proj.weight', 'vision_model.encoder.layers.15.self_attn.q_proj.weight', 'vision_model.encoder.layers.23.layer_norm2.bias', 'vision_model.encoder.layers.7.self_attn.out_proj.bias', 'vision_model.encoder.layers.6.layer_norm1.bias', 'vision_model.encoder.layers.13.layer_norm1.bias', 'vision_model.encoder.layers.21.layer_norm1.bias', 'vision_model.encoder.layers.0.mlp.fc2.bias', 'vision_model.encoder.layers.9.mlp.fc1.bias', 'vision_model.post_layernorm.weight', 'vision_model.encoder.layers.3.layer_norm1.weight', 'vision_model.encoder.layers.6.self_attn.k_proj.weight', 'vision_model.encoder.layers.8.self_attn.q_proj.bias', 'vision_model.encoder.layers.3.mlp.fc1.bias', 'vision_model.encoder.layers.7.self_attn.k_proj.weight', 'vision_model.encoder.layers.22.self_attn.q_proj.weight', 'vision_model.encoder.layers.20.self_attn.q_proj.bias', 'vision_model.post_layernorm.bias', 'vision_model.encoder.layers.19.self_attn.v_proj.bias', 'vision_model.encoder.layers.9.layer_norm2.weight', 'vision_model.encoder.layers.17.self_attn.k_proj.bias', 'vision_model.encoder.layers.16.mlp.fc2.weight', 'vision_model.encoder.layers.13.self_attn.k_proj.weight', 'vision_model.encoder.layers.17.layer_norm2.weight', 'vision_model.encoder.layers.8.mlp.fc2.bias', 'vision_model.encoder.layers.4.layer_norm1.bias', 'vision_model.encoder.layers.13.self_attn.v_proj.weight', 'vision_model.encoder.layers.4.self_attn.v_proj.weight', 'vision_model.encoder.layers.16.self_attn.out_proj.weight', 'vision_model.encoder.layers.3.layer_norm2.weight', 'vision_model.encoder.layers.4.self_attn.k_proj.bias', 'vision_model.encoder.layers.20.layer_norm1.bias', 'vision_model.encoder.layers.2.mlp.fc2.bias', 'vision_model.encoder.layers.12.layer_norm1.bias', 'vision_model.encoder.layers.11.mlp.fc1.bias', 'vision_model.encoder.layers.9.mlp.fc1.weight', 'vision_model.encoder.layers.9.self_attn.out_proj.bias', 'vision_model.encoder.layers.19.self_attn.out_proj.weight', 'vision_model.encoder.layers.6.self_attn.v_proj.weight', 'vision_model.encoder.layers.14.self_attn.v_proj.weight', 'vision_model.encoder.layers.2.mlp.fc1.bias', 'vision_model.encoder.layers.13.mlp.fc1.bias', 'vision_model.encoder.layers.0.layer_norm1.weight', 'vision_model.encoder.layers.17.self_attn.v_proj.weight', 'vision_model.encoder.layers.23.self_attn.out_proj.bias', 'vision_model.encoder.layers.21.mlp.fc1.weight', 'vision_model.encoder.layers.22.layer_norm2.weight', 'vision_model.encoder.layers.8.self_attn.out_proj.bias', 'vision_model.encoder.layers.12.layer_norm2.bias', 'vision_model.encoder.layers.20.self_attn.out_proj.bias', 'vision_model.encoder.layers.2.layer_norm1.bias', 'vision_model.encoder.layers.8.layer_norm1.bias', 'vision_model.encoder.layers.14.layer_norm2.bias', 'vision_model.encoder.layers.12.self_attn.q_proj.bias', 'vision_model.encoder.layers.10.self_attn.out_proj.weight', 'vision_model.encoder.layers.7.self_attn.v_proj.bias', 'vision_model.encoder.layers.11.self_attn.q_proj.weight', 'vision_model.encoder.layers.22.layer_norm1.weight', 'vision_model.encoder.layers.6.mlp.fc2.weight', 'vision_model.encoder.layers.4.mlp.fc1.bias', 'vision_model.encoder.layers.9.layer_norm1.weight', 'vision_model.encoder.layers.19.mlp.fc1.weight', 'vision_model.encoder.layers.4.mlp.fc2.bias', 'vision_model.encoder.layers.7.mlp.fc2.bias', 'vision_model.encoder.layers.16.self_attn.v_proj.bias', 'vision_model.encoder.layers.5.layer_norm2.bias', 'vision_model.encoder.layers.2.self_attn.v_proj.bias', 'vision_model.encoder.layers.19.layer_norm2.weight', 'vision_model.encoder.layers.13.mlp.fc2.weight', 'vision_model.encoder.layers.16.self_attn.out_proj.bias', 'vision_model.encoder.layers.20.self_attn.v_proj.weight', 'vision_model.encoder.layers.18.self_attn.k_proj.bias', 'vision_model.encoder.layers.6.self_attn.q_proj.weight', 'vision_model.encoder.layers.19.mlp.fc1.bias', 'vision_model.encoder.layers.0.self_attn.out_proj.weight', 'vision_model.encoder.layers.10.self_attn.out_proj.bias', 'vision_model.encoder.layers.13.self_attn.k_proj.bias', 'vision_model.encoder.layers.10.mlp.fc2.weight', 'vision_model.encoder.layers.1.mlp.fc1.bias', 'vision_model.encoder.layers.14.mlp.fc1.bias', 'vision_model.encoder.layers.13.self_attn.out_proj.bias', 'vision_model.encoder.layers.2.self_attn.q_proj.bias', 'logit_scale', 'vision_model.encoder.layers.21.self_attn.q_proj.weight', 'vision_model.encoder.layers.4.mlp.fc2.weight', 'vision_model.encoder.layers.19.self_attn.v_proj.weight', 'vision_model.encoder.layers.17.self_attn.q_proj.weight', 'vision_model.encoder.layers.8.self_attn.v_proj.weight', 'vision_model.encoder.layers.13.mlp.fc2.bias', 'vision_model.encoder.layers.15.mlp.fc2.bias', 'vision_model.encoder.layers.18.self_attn.q_proj.bias', 'vision_model.encoder.layers.10.self_attn.k_proj.weight', 'vision_model.encoder.layers.10.mlp.fc1.weight', 'vision_model.encoder.layers.17.layer_norm1.weight', 'vision_model.encoder.layers.20.mlp.fc2.bias', 'vision_model.encoder.layers.23.self_attn.q_proj.weight', 'vision_model.encoder.layers.12.self_attn.k_proj.bias', 'vision_model.encoder.layers.0.self_attn.q_proj.bias', 'vision_model.encoder.layers.20.self_attn.q_proj.weight', 'vision_model.encoder.layers.16.layer_norm2.weight', 'vision_model.encoder.layers.3.self_attn.v_proj.weight', 'vision_model.encoder.layers.12.layer_norm1.weight', 'vision_model.encoder.layers.0.mlp.fc2.weight', 'vision_model.encoder.layers.14.self_attn.k_proj.weight', 'vision_model.encoder.layers.4.self_attn.out_proj.weight', 'vision_model.encoder.layers.7.layer_norm2.bias', 'vision_model.encoder.layers.22.mlp.fc1.bias', 'vision_model.encoder.layers.16.mlp.fc1.bias', 'vision_model.encoder.layers.8.self_attn.k_proj.weight', 'vision_model.encoder.layers.1.mlp.fc2.bias', 'vision_model.encoder.layers.14.self_attn.out_proj.bias', 'vision_model.encoder.layers.14.self_attn.out_proj.weight', 'vision_model.encoder.layers.1.self_attn.v_proj.bias', 'vision_model.encoder.layers.10.self_attn.q_proj.bias', 'vision_model.encoder.layers.14.layer_norm2.weight', 'vision_model.encoder.layers.21.layer_norm2.weight', 'vision_model.encoder.layers.13.self_attn.q_proj.bias', 'vision_model.encoder.layers.1.self_attn.out_proj.bias', 'vision_model.encoder.layers.16.mlp.fc2.bias', 'vision_model.encoder.layers.4.self_attn.k_proj.weight', 'vision_model.encoder.layers.3.self_attn.out_proj.weight', 'vision_model.encoder.layers.11.self_attn.out_proj.weight', 'vision_model.encoder.layers.0.self_attn.q_proj.weight', 'vision_model.encoder.layers.0.self_attn.v_proj.bias', 'vision_model.encoder.layers.12.layer_norm2.weight', 'vision_model.encoder.layers.11.self_attn.k_proj.weight', 'vision_model.encoder.layers.6.self_attn.q_proj.bias', 'vision_model.encoder.layers.11.layer_norm1.weight', 'vision_model.encoder.layers.3.layer_norm1.bias', 'vision_model.encoder.layers.12.self_attn.v_proj.weight', 'vision_model.encoder.layers.7.layer_norm1.weight', 'vision_model.encoder.layers.10.layer_norm2.weight', 'vision_model.encoder.layers.5.self_attn.out_proj.bias', 'vision_model.encoder.layers.7.self_attn.out_proj.weight', 'vision_model.encoder.layers.23.self_attn.v_proj.bias', 'vision_model.encoder.layers.1.self_attn.k_proj.weight', 'vision_model.encoder.layers.11.self_attn.v_proj.weight', 'vision_model.encoder.layers.8.self_attn.v_proj.bias', 'vision_model.encoder.layers.22.layer_norm2.bias', 'vision_model.encoder.layers.2.layer_norm2.weight', 'vision_model.encoder.layers.18.self_attn.out_proj.weight', 'vision_model.encoder.layers.16.mlp.fc1.weight', 'vision_model.encoder.layers.19.self_attn.out_proj.bias', 'vision_model.encoder.layers.11.layer_norm2.weight', 'vision_model.encoder.layers.6.self_attn.v_proj.bias', 'vision_model.encoder.layers.11.layer_norm1.bias', 'vision_model.encoder.layers.23.self_attn.q_proj.bias', 'vision_model.encoder.layers.16.layer_norm2.bias', 'vision_model.encoder.layers.8.layer_norm1.weight', 'vision_model.encoder.layers.16.self_attn.v_proj.weight', 'vision_model.encoder.layers.23.self_attn.out_proj.weight', 'vision_model.encoder.layers.1.self_attn.q_proj.weight', 'vision_model.encoder.layers.14.mlp.fc2.weight', 'vision_model.encoder.layers.21.layer_norm1.weight', 'vision_model.encoder.layers.19.self_attn.q_proj.weight', 'vision_model.encoder.layers.13.layer_norm2.weight', 'vision_model.encoder.layers.14.self_attn.v_proj.bias', 'vision_model.encoder.layers.12.self_attn.q_proj.weight', 'vision_model.encoder.layers.22.mlp.fc2.bias', 'vision_model.encoder.layers.3.self_attn.v_proj.bias', 'vision_model.encoder.layers.1.layer_norm1.bias', 'vision_model.encoder.layers.3.self_attn.q_proj.bias', 'vision_model.encoder.layers.7.mlp.fc1.weight', 'vision_model.encoder.layers.11.self_attn.out_proj.bias', 'vision_model.encoder.layers.16.self_attn.q_proj.weight', 'vision_model.encoder.layers.9.mlp.fc2.weight', 'vision_model.encoder.layers.7.self_attn.q_proj.weight', 'vision_model.encoder.layers.3.layer_norm2.bias', 'vision_model.encoder.layers.19.mlp.fc2.bias', 'vision_model.encoder.layers.20.self_attn.k_proj.bias', 'vision_model.encoder.layers.5.self_attn.q_proj.bias', 'vision_model.encoder.layers.3.mlp.fc2.bias', 'vision_model.encoder.layers.18.self_attn.out_proj.bias', 'vision_model.encoder.layers.22.mlp.fc2.weight', 'vision_model.encoder.layers.5.self_attn.v_proj.weight', 'vision_model.encoder.layers.8.layer_norm2.bias', 'vision_model.encoder.layers.15.self_attn.out_proj.weight', 'vision_model.encoder.layers.18.self_attn.q_proj.weight', 'vision_model.encoder.layers.3.self_attn.q_proj.weight', 'vision_model.encoder.layers.21.self_attn.out_proj.weight', 'vision_model.encoder.layers.18.layer_norm1.weight', 'vision_model.encoder.layers.17.self_attn.out_proj.weight', 'vision_model.encoder.layers.14.mlp.fc2.bias', 'vision_model.encoder.layers.15.self_attn.out_proj.bias', 'vision_model.encoder.layers.12.self_attn.v_proj.bias', 'vision_model.encoder.layers.11.mlp.fc1.weight', 'vision_model.encoder.layers.12.mlp.fc1.bias', 'vision_model.encoder.layers.23.self_attn.v_proj.weight', 'vision_model.encoder.layers.17.self_attn.q_proj.bias', 'vision_model.encoder.layers.21.self_attn.k_proj.weight', 'vision_model.encoder.layers.21.layer_norm2.bias', 'vision_model.encoder.layers.0.mlp.fc1.bias', 'vision_model.encoder.layers.18.mlp.fc1.weight', 'vision_model.encoder.layers.15.self_attn.k_proj.weight', 'vision_model.encoder.layers.16.self_attn.k_proj.weight', 'vision_model.encoder.layers.1.self_attn.out_proj.weight', 'vision_model.encoder.layers.2.mlp.fc2.weight', 'vision_model.encoder.layers.16.self_attn.q_proj.bias', 'vision_model.encoder.layers.1.mlp.fc1.weight', 'vision_model.encoder.layers.9.layer_norm2.bias', 'vision_model.encoder.layers.3.mlp.fc2.weight', 'vision_model.encoder.layers.15.self_attn.k_proj.bias', 'vision_model.encoder.layers.22.self_attn.k_proj.bias', 'vision_model.encoder.layers.15.self_attn.v_proj.bias', 'vision_model.encoder.layers.0.layer_norm1.bias', 'vision_model.encoder.layers.12.self_attn.out_proj.weight', 'vision_model.encoder.layers.5.self_attn.v_proj.bias', 'vision_model.encoder.layers.22.mlp.fc1.weight', 'vision_model.encoder.layers.1.self_attn.v_proj.weight', 'vision_model.encoder.layers.20.self_attn.k_proj.weight', 'vision_model.encoder.layers.17.mlp.fc2.bias', 'vision_model.encoder.layers.12.mlp.fc2.weight', 'vision_model.encoder.layers.17.self_attn.v_proj.bias', 'vision_model.encoder.layers.21.self_attn.out_proj.bias', 'vision_model.encoder.layers.3.self_attn.out_proj.bias', 'vision_model.encoder.layers.6.mlp.fc1.bias', 'vision_model.encoder.layers.5.layer_norm2.weight', 'vision_model.encoder.layers.21.self_attn.v_proj.bias', 'vision_model.encoder.layers.16.layer_norm1.weight', 'vision_model.encoder.layers.11.self_attn.v_proj.bias', 'vision_model.encoder.layers.12.self_attn.k_proj.weight', 'vision_model.encoder.layers.5.layer_norm1.weight', 'vision_model.encoder.layers.13.self_attn.q_proj.weight', 'vision_model.encoder.layers.10.layer_norm1.bias', 'vision_model.encoder.layers.15.mlp.fc1.weight', 'vision_model.embeddings.position_ids', 'vision_model.encoder.layers.10.self_attn.k_proj.bias', 'vision_model.encoder.layers.14.layer_norm1.weight', 'vision_model.encoder.layers.20.layer_norm1.weight', 'vision_model.encoder.layers.22.layer_norm1.bias', 'vision_model.encoder.layers.7.layer_norm2.weight', 'vision_model.encoder.layers.15.layer_norm2.weight', 'vision_model.encoder.layers.8.mlp.fc1.bias', 'vision_model.encoder.layers.9.self_attn.q_proj.bias', 'vision_model.encoder.layers.22.self_attn.v_proj.bias', 'vision_model.encoder.layers.23.self_attn.k_proj.bias', 'vision_model.encoder.layers.9.self_attn.out_proj.weight', 'vision_model.encoder.layers.7.mlp.fc2.weight', 'vision_model.encoder.layers.2.layer_norm1.weight', 'vision_model.encoder.layers.22.self_attn.q_proj.bias', 'vision_model.encoder.layers.18.self_attn.v_proj.weight', 'vision_model.encoder.layers.0.self_attn.k_proj.bias', 'vision_model.encoder.layers.11.layer_norm2.bias', 'vision_model.encoder.layers.14.self_attn.q_proj.bias', 'vision_model.encoder.layers.19.self_attn.k_proj.bias', 'vision_model.encoder.layers.6.layer_norm2.bias', 'vision_model.encoder.layers.19.layer_norm2.bias', 'vision_model.encoder.layers.14.self_attn.q_proj.weight', 'vision_model.encoder.layers.8.layer_norm2.weight', 'vision_model.encoder.layers.14.layer_norm1.bias', 'vision_model.encoder.layers.4.self_attn.out_proj.bias', 'vision_model.encoder.layers.18.layer_norm2.weight', 'vision_model.embeddings.class_embedding', 'vision_model.encoder.layers.23.mlp.fc1.weight', 'vision_model.encoder.layers.7.layer_norm1.bias', 'vision_model.encoder.layers.21.self_attn.v_proj.weight', 'vision_model.encoder.layers.0.layer_norm2.weight', 'vision_model.encoder.layers.3.mlp.fc1.weight', 'vision_model.encoder.layers.22.self_attn.v_proj.weight', 'vision_model.encoder.layers.20.mlp.fc2.weight', 'vision_model.encoder.layers.1.mlp.fc2.weight', 'vision_model.encoder.layers.15.mlp.fc2.weight', 'vision_model.encoder.layers.4.mlp.fc1.weight', 'vision_model.encoder.layers.6.mlp.fc1.weight', 'vision_model.encoder.layers.12.mlp.fc2.bias', 'vision_model.encoder.layers.13.layer_norm1.weight', 'vision_model.encoder.layers.9.self_attn.q_proj.weight', 'vision_model.encoder.layers.5.mlp.fc1.bias', 'vision_model.encoder.layers.10.mlp.fc2.bias', 'vision_model.encoder.layers.5.mlp.fc2.weight', 'vision_model.encoder.layers.9.layer_norm1.bias']
- This IS expected if you are initializing CLIPTextModel from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model).
- This IS NOT expected if you are initializing CLIPTextModel from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).
load motion LoRA from models/MotionLoRA/v2_lora_ZoomIn.ckpt
current seed: 255224557
sampling photo of vocano, rocks, storm weather, wind, lava waves, lightning, 8k uhd, dslr, soft lighting, high quality, film grain, Fujifilm XT3 ...
0%| | 0/25 [00:00<?, ?it/s]
4%|▍ | 1/25 [00:02<00:54, 2.27s/it]
8%|▊ | 2/25 [00:04<00:52, 2.28s/it]
12%|█▏ | 3/25 [00:06<00:50, 2.28s/it]
16%|█▌ | 4/25 [00:09<00:48, 2.29s/it]
20%|██ | 5/25 [00:11<00:45, 2.29s/it]
24%|██▍ | 6/25 [00:13<00:43, 2.29s/it]
28%|██▊ | 7/25 [00:16<00:41, 2.29s/it]
32%|███▏ | 8/25 [00:18<00:38, 2.29s/it]
36%|███▌ | 9/25 [00:20<00:36, 2.30s/it]
40%|████ | 10/25 [00:22<00:34, 2.30s/it]
44%|████▍ | 11/25 [00:25<00:32, 2.30s/it]
48%|████▊ | 12/25 [00:27<00:29, 2.29s/it]
52%|█████▏ | 13/25 [00:29<00:27, 2.29s/it]
56%|█████▌ | 14/25 [00:32<00:25, 2.29s/it]
60%|██████ | 15/25 [00:34<00:22, 2.29s/it]
64%|██████▍ | 16/25 [00:36<00:20, 2.29s/it]
68%|██████▊ | 17/25 [00:38<00:18, 2.29s/it]
72%|███████▏ | 18/25 [00:41<00:16, 2.29s/it]
76%|███████▌ | 19/25 [00:43<00:13, 2.29s/it]
80%|████████ | 20/25 [00:45<00:11, 2.29s/it]
84%|████████▍ | 21/25 [00:48<00:09, 2.29s/it]
88%|████████▊ | 22/25 [00:50<00:06, 2.29s/it]
92%|█████████▏| 23/25 [00:52<00:04, 2.29s/it]
96%|█████████▌| 24/25 [00:54<00:02, 2.29s/it]
100%|██████████| 25/25 [00:57<00:00, 2.29s/it]
100%|██████████| 25/25 [00:57<00:00, 2.29s/it]
0%| | 0/16 [00:00<?, ?it/s]
31%|███▏ | 5/16 [00:00<00:00, 38.50it/s]
56%|█████▋ | 9/16 [00:00<00:00, 17.10it/s]
75%|███████▌ | 12/16 [00:00<00:00, 14.53it/s]
88%|████████▊ | 14/16 [00:00<00:00, 13.60it/s]
100%|██████████| 16/16 [00:01<00:00, 12.96it/s]
100%|██████████| 16/16 [00:01<00:00, 14.72it/s]
save to samples/3fe6f708d6cbea0df905f54a72a841e4-2023-09-27T05-18-58/sample/photoofvocanorocksstorm.gif