fermatresearch/magic-style-transfer 🔢🖼️📝❓✓ → 🖼️

▶️ 50.3K runs 📅 Mar 2024 ⚙️ Cog 0.9.5 🔗 GitHub
image-style-transfer image-to-image

About

Restyle an image with the style of another one. I strongly suggest to upscale the results with Clarity AI

Example Output

Prompt:

"modern interior living room"

Output

Example output

Performance Metrics

14.57s Prediction Time
168.72s Total Time
All Input Parameters 
{
  "image": "https://replicate.delivery/pbxt/KbUKCMMihGkSc5MXYYYkjEI6hlf1GNmGgwugu6JfSQATqiCN/3d.jpeg",
  "prompt": "modern interior living room",
  "ip_image": "https://replicate.delivery/pbxt/KbUKD3uoQjyTzdWbeAqYrypl0RWVJc0gI5UHHa3yYWNaqIoc/DALL%C2%B7E%202024-03-20%2017.57.33%20-%20Create%20a%20professional%20photograph%20of%20a%20modern%20interior%20design.%20This%20image%20should%20capture%20a%20living%20room%20space%20that%20combines%20contemporary%20elegance%20with%20c.webp",
  "ip_scale": 1,
  "strength": 1,
  "scheduler": "K_EULER",
  "lora_scale": 0.9,
  "num_outputs": 1,
  "guidance_scale": 4,
  "resizing_scale": 1,
  "apply_watermark": true,
  "negative_prompt": "",
  "background_color": "#A2A2A2",
  "num_inference_steps": 30,
  "condition_canny_scale": 0.5,
  "condition_depth_scale": 0.5
}
Input Parameters
seed Type: integer
Random seed. Leave blank to randomize the seed
image Type: string
Input image
prompt Type: stringDefault: An astronaut riding a rainbow unicorn
Input prompt
ip_image Type: string
Input image for img2img or inpaint mode
ip_scale Type: numberDefault: 0.3Range: 0 - 1
IP Adapter strength.
strength Type: numberDefault: 0.9Range: 0 - 1
When img2img is active, the denoising strength. 1 means total destruction of the input image.
scheduler Default: K_EULER
scheduler
lora_scale Type: numberDefault: 0.9Range: 0 - 1
LoRA additive scale. Only applicable on trained models.
num_outputs Type: integerDefault: 1Range: 1 - 4
Number of images to output
lora_weights Type: string
Replicate LoRA weights to use. Leave blank to use the default weights.
guidance_scale Type: numberDefault: 4Range: 1 - 50
Scale for classifier-free guidance
resizing_scale Type: numberDefault: 1Range: 1 - 10
If you want the image to have a solid margin. Scale of the solid margin. 1.0 means no resizing.
apply_watermark Type: booleanDefault: true
Applies a watermark to enable determining if an image is generated in downstream applications. If you have other provisions for generating or deploying images safely, you can use this to disable watermarking.
negative_prompt Type: stringDefault:
Input Negative Prompt
background_color Type: stringDefault: #A2A2A2
When passing an image with alpha channel, it will be replaced with this color
num_inference_steps Type: integerDefault: 30Range: 1 - 500
Number of denoising steps
condition_canny_scale Type: numberDefault: 0.15Range: 0 - 2
The bigger this number is, the more ControlNet interferes
condition_depth_scale Type: numberDefault: 0.35Range: 0 - 2
The bigger this number is, the more ControlNet interferes
Output Schema

Output

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

Example Execution Logs 
Using seed: 28214
Prompt: modern interior living room
Original width:1024, height:1024
Aspect Ratio: 1.00
new_width:1024, new_height:1024
You have 2 ControlNets and you have passed 1 prompts. The conditionings will be fixed across the prompts.
  0%|          | 0/30 [00:00<?, ?it/s]
  3%|▎         | 1/30 [00:00<00:13,  2.17it/s]
  7%|▋         | 2/30 [00:00<00:10,  2.69it/s]
 10%|█         | 3/30 [00:01<00:10,  2.59it/s]
 13%|█▎        | 4/30 [00:01<00:10,  2.55it/s]
 17%|█▋        | 5/30 [00:01<00:09,  2.52it/s]
 20%|██        | 6/30 [00:02<00:09,  2.51it/s]
 23%|██▎       | 7/30 [00:02<00:09,  2.50it/s]
 27%|██▋       | 8/30 [00:03<00:08,  2.49it/s]
 30%|███       | 9/30 [00:03<00:08,  2.49it/s]
 33%|███▎      | 10/30 [00:03<00:08,  2.49it/s]
 37%|███▋      | 11/30 [00:04<00:07,  2.49it/s]
 40%|████      | 12/30 [00:04<00:07,  2.49it/s]
 43%|████▎     | 13/30 [00:05<00:06,  2.49it/s]
 47%|████▋     | 14/30 [00:05<00:06,  2.49it/s]
 50%|█████     | 15/30 [00:05<00:06,  2.49it/s]
 53%|█████▎    | 16/30 [00:06<00:05,  2.49it/s]
 57%|█████▋    | 17/30 [00:06<00:05,  2.48it/s]
 60%|██████    | 18/30 [00:07<00:04,  2.48it/s]
 63%|██████▎   | 19/30 [00:07<00:04,  2.48it/s]
 67%|██████▋   | 20/30 [00:08<00:04,  2.49it/s]
 70%|███████   | 21/30 [00:08<00:03,  2.48it/s]
 73%|███████▎  | 22/30 [00:08<00:03,  2.49it/s]
 77%|███████▋  | 23/30 [00:09<00:02,  2.49it/s]
 80%|████████  | 24/30 [00:09<00:02,  2.49it/s]
 83%|████████▎ | 25/30 [00:10<00:02,  2.49it/s]
 87%|████████▋ | 26/30 [00:10<00:01,  2.49it/s]
 90%|█████████ | 27/30 [00:10<00:01,  2.49it/s]
 93%|█████████▎| 28/30 [00:11<00:00,  2.49it/s]
 97%|█████████▋| 29/30 [00:11<00:00,  2.49it/s]
100%|██████████| 30/30 [00:12<00:00,  2.49it/s]
100%|██████████| 30/30 [00:12<00:00,  2.49it/s]
Version Details
Version ID
3b5fa5d360c361090f11164292e45cc5d14cea8d089591d47c580cac9ec1c7ca
Version Created
March 20, 2024
Run on Replicate →