cloneofsimo/vintedois_lora 🔢🖼️❓📝 → 🖼️

▶️ 5.7K runs 📅 Feb 2023 ⚙️ Cog 0.6.1
image-lora-training image-to-image text-to-image

Performance

10.7sTypical run time
5.7KTotal runs

About

LoRA, fp16 vintedois-diffusion-v0-1

Example Output

Prompt:

"close up portrait of <1> in a Sci Fi suit - 4k uhd, hyper detailed, photorealistic, steampunk, lovecraft colors, dan mumford colors, psychedelic black light, epic composition"

Output

Example output

Performance Metrics

10.65s Prediction Time
10.72s Total Time
All Input Parameters 
{
  "width": 512,
  "height": 512,
  "prompt": "close up portrait of <1> in a Sci Fi suit - 4k uhd, hyper detailed, photorealistic, steampunk, lovecraft colors, dan mumford colors, psychedelic black light, epic composition",
  "lora_urls": "https://replicate.delivery/pbxt/tLNfiG3fK2jZo0CrBG4cNTJNhEi7r117ANUBjWrLTkQRMraQA/tmpg9tq4is5me.safetensors",
  "scheduler": "DPMSolverMultistep",
  "lora_scales": "0.5",
  "num_outputs": 1,
  "guidance_scale": "7",
  "negative_prompt": "blurry, bad anatomy, blurred, watermark, grainy, signature",
  "num_inference_steps": "30"
}
Input Parameters
seed Type: integer
Random seed. Leave blank to randomize the seed
image Type: string
(Img2Img) Inital image to generate variations of. If this is not none, Img2Img will be invoked.
width Default: 512
Width of output image. Maximum size is 1024x768 or 768x1024 because of memory limits
height Default: 512
Height of output image. Maximum size is 1024x768 or 768x1024 because of memory limits
prompt Type: stringDefault: a photo of <1> riding a horse on mars
Input prompt. Use <1>, <2>, <3>, etc., to specify LoRA concepts
lora_urls Type: stringDefault:
List of urls for safetensors of lora models, seperated with | .
scheduler Default: DPMSolverMultistep
Choose a scheduler.
lora_scales Type: stringDefault: 0.5
List of scales for safetensors of lora models, seperated with |
num_outputs Type: integerDefault: 1Range: 1 - 4
Number of images to output.
adapter_type Default: sketch
(T2I-adapter) Choose an adapter type for the additional condition.
guidance_scale Type: numberDefault: 7.5Range: 1 - 20
Scale for classifier-free guidance
negative_prompt Type: stringDefault:
Specify things to not see in the output
prompt_strength Type: numberDefault: 0.8
(Img2Img) Prompt strength when providing the image. 1.0 corresponds to full destruction of information in init image
num_inference_steps Type: integerDefault: 50Range: 1 - 500
Number of denoising steps
adapter_condition_image Type: string
(T2I-adapter) Adapter Condition Image to gain extra control over generation. If this is not none, T2I adapter will be invoked. Width, Height of this image must match the above parameter, or dimension of the Img2Img image.
Output Schema

Output

Type: array • Items Type: string • Items Format: uri

Example Execution Logs 
Using seed: 25844
Using disk cache...
Embedding <s1> replaced to <s0-0>
Embedding <s2> replaced to <s0-1>
<s0-0>
The tokenizer already contains the token <s0-0>.
Replacing <s0-0> embedding.
<s0-1>
The tokenizer already contains the token <s0-1>.
Replacing <s0-1> embedding.
merging time: 3.018888473510742
  0%|          | 0/30 [00:00<?, ?it/s]
  3%|▎         | 1/30 [00:00<00:07,  3.78it/s]
  7%|▋         | 2/30 [00:00<00:06,  4.26it/s]
 10%|█         | 3/30 [00:00<00:06,  4.45it/s]
 13%|█▎        | 4/30 [00:00<00:05,  4.57it/s]
 17%|█▋        | 5/30 [00:01<00:05,  4.56it/s]
 20%|██        | 6/30 [00:01<00:05,  4.54it/s]
 23%|██▎       | 7/30 [00:01<00:05,  4.60it/s]
 27%|██▋       | 8/30 [00:01<00:04,  4.62it/s]
 30%|███       | 9/30 [00:01<00:04,  4.67it/s]
 33%|███▎      | 10/30 [00:02<00:04,  4.63it/s]
 37%|███▋      | 11/30 [00:02<00:04,  4.59it/s]
 40%|████      | 12/30 [00:02<00:03,  4.64it/s]
 43%|████▎     | 13/30 [00:02<00:03,  4.66it/s]
 47%|████▋     | 14/30 [00:03<00:03,  4.66it/s]
 50%|█████     | 15/30 [00:03<00:03,  4.64it/s]
 53%|█████▎    | 16/30 [00:03<00:03,  4.61it/s]
 57%|█████▋    | 17/30 [00:03<00:02,  4.60it/s]
 60%|██████    | 18/30 [00:03<00:02,  4.63it/s]
 63%|██████▎   | 19/30 [00:04<00:02,  4.63it/s]
 67%|██████▋   | 20/30 [00:04<00:02,  4.63it/s]
 70%|███████   | 21/30 [00:04<00:01,  4.65it/s]
 73%|███████▎  | 22/30 [00:04<00:01,  4.62it/s]
 77%|███████▋  | 23/30 [00:05<00:01,  4.65it/s]
 80%|████████  | 24/30 [00:05<00:01,  4.65it/s]
 83%|████████▎ | 25/30 [00:05<00:01,  4.62it/s]
 87%|████████▋ | 26/30 [00:05<00:00,  4.65it/s]
 90%|█████████ | 27/30 [00:05<00:00,  4.65it/s]
 93%|█████████▎| 28/30 [00:06<00:00,  4.64it/s]
 97%|█████████▋| 29/30 [00:06<00:00,  4.65it/s]
100%|██████████| 30/30 [00:06<00:00,  4.63it/s]
100%|██████████| 30/30 [00:06<00:00,  4.60it/s]
Version Details
Version ID
c43a53a23c00fdd1e2f0c403aecdc17296d58cc1dd455ae0fa613a0e5eb8232f
Version Created
March 1, 2023
Run on Replicate →