elizabeth815/linocut πŸ–ΌοΈπŸ”’β“πŸ“βœ“ β†’ πŸ–ΌοΈ

▢️ 101 runs πŸ“… Oct 2025 βš™οΈ Cog 0.13.6
image-to-image linocut lora text-to-image

About

Experimenting with lino cut effects

Example Output

Prompt:

"

{
"prompt": "linotree β€” A towering California redwood tree dominates the scene, viewed from below so the trunk stretches dramatically upward into the canopy. The bark is described with intricate carved lines and rhythmic hatch marks, while layers of foliage create a sense of depth. Color layers suggest depth of field: rich earthy browns in the foreground, deep greens in the mid-ground, and pale misty greens fading into the distance. Reduction-print friendly, whimsical tone. Consider abstract shapes and over the top flourishes that hint at nature and natural forms. Use yayoi kusama as inspiration.

General Style Prompt (linotree):
β€œWhimsical linocut-inspired imagery with bold carved lines, strong silhouettes, and playful charm. Limited color palette of 2–4 flat tones, suitable for reduction printing. Ink textures, paper grain, and carved marks are celebrated. The mood is lighthearted, imaginative, and folk-art inspired β€” simple, graphic, and reduction-print friendly.”",

"negative_prompt": "photorealism, gradients, glossy 3D rendering, painterly washes, watercolor, oil paint, cluttered detail, busy backgrounds, muted palettes, neon glow, documentary realism",

"image": "https://your-reference-image-url-here.jpg",
"strength": 0.6,
"num_inference_steps": 30,
"guidance_scale": 7.0,
"scheduler": "DPMSolverMultistep"
}

"

Output

Example outputExample outputExample outputExample output

Performance Metrics

29.92s Prediction Time
29.93s Total Time
All Input Parameters
{
  "model": "dev",
  "prompt": "{\n  \"prompt\": \"linotree β€” A towering California redwood tree dominates the scene, viewed from below so the trunk stretches dramatically upward into the canopy. The bark is described with intricate carved lines and rhythmic hatch marks, while layers of foliage create a sense of depth. Color layers suggest depth of field: rich earthy browns in the foreground, deep greens in the mid-ground, and pale misty greens fading into the distance. Reduction-print friendly, whimsical tone. Consider abstract shapes and over the top flourishes that hint at nature and natural forms. Use yayoi kusama as inspiration. \\n\\nGeneral Style Prompt (linotree):\\nβ€œWhimsical linocut-inspired imagery with bold carved lines, strong silhouettes, and playful charm. Limited color palette of 2–4 flat tones, suitable for reduction printing. Ink textures, paper grain, and carved marks are celebrated. The mood is lighthearted, imaginative, and folk-art inspired β€” simple, graphic, and reduction-print friendly.”\",\n  \n  \"negative_prompt\": \"photorealism, gradients, glossy 3D rendering, painterly washes, watercolor, oil paint, cluttered detail, busy backgrounds, muted palettes, neon glow, documentary realism\",\n\n  \"image\": \"https://your-reference-image-url-here.jpg\",  \n  \"strength\": 0.6,\n  \"num_inference_steps\": 30,\n  \"guidance_scale\": 7.0,\n  \"scheduler\": \"DPMSolverMultistep\"\n}\n",
  "go_fast": false,
  "lora_scale": 1,
  "megapixels": "1",
  "num_outputs": 4,
  "aspect_ratio": "1:1",
  "output_format": "webp",
  "guidance_scale": 3,
  "output_quality": 80,
  "prompt_strength": 0.38,
  "extra_lora_scale": 1,
  "num_inference_steps": 28
}
Input Parameters
mask Type: string
Image mask for image inpainting mode. If provided, aspect_ratio, width, and height inputs are ignored.
seed Type: integer
Random seed. Set for reproducible generation
image Type: string
Input image for image to image or inpainting mode. If provided, aspect_ratio, width, and height inputs are ignored.
model Default: dev
Which model to run inference with. The dev model performs best with around 28 inference steps but the schnell model only needs 4 steps.
width Type: integerRange: 256 - 1440
Width of generated image. Only works if `aspect_ratio` is set to custom. Will be rounded to nearest multiple of 16. Incompatible with fast generation
height Type: integerRange: 256 - 1440
Height of generated image. Only works if `aspect_ratio` is set to custom. Will be rounded to nearest multiple of 16. Incompatible with fast generation
prompt (required) Type: string
Prompt for generated image. If you include the `trigger_word` used in the training process you are more likely to activate the trained object, style, or concept in the resulting image.
go_fast Type: booleanDefault: false
Run faster predictions with model optimized for speed (currently fp8 quantized); disable to run in original bf16
extra_lora Type: string
Load LoRA weights. Supports Replicate models in the format <owner>/<username> or <owner>/<username>/<version>, HuggingFace URLs in the format huggingface.co/<owner>/<model-name>, CivitAI URLs in the format civitai.com/models/<id>[/<model-name>], or arbitrary .safetensors URLs from the Internet. For example, 'fofr/flux-pixar-cars'
lora_scale Type: numberDefault: 1Range: -1 - 3
Determines how strongly the main LoRA should be applied. Sane results between 0 and 1 for base inference. For go_fast we apply a 1.5x multiplier to this value; we've generally seen good performance when scaling the base value by that amount. You may still need to experiment to find the best value for your particular lora.
megapixels Default: 1
Approximate number of megapixels for generated image
num_outputs Type: integerDefault: 1Range: 1 - 4
Number of outputs to generate
aspect_ratio Default: 1:1
Aspect ratio for the generated image. If custom is selected, uses height and width below & will run in bf16 mode
output_format Default: webp
Format of the output images
guidance_scale Type: numberDefault: 3Range: 0 - 10
Guidance scale for the diffusion process. Lower values can give more realistic images. Good values to try are 2, 2.5, 3 and 3.5
output_quality Type: integerDefault: 80Range: 0 - 100
Quality when saving the output images, from 0 to 100. 100 is best quality, 0 is lowest quality. Not relevant for .png outputs
prompt_strength Type: numberDefault: 0.8Range: 0 - 1
Prompt strength when using img2img. 1.0 corresponds to full destruction of information in image
extra_lora_scale Type: numberDefault: 1Range: -1 - 3
Determines how strongly the extra LoRA should be applied. Sane results between 0 and 1 for base inference. For go_fast we apply a 1.5x multiplier to this value; we've generally seen good performance when scaling the base value by that amount. You may still need to experiment to find the best value for your particular lora.
replicate_weights Type: string
Load LoRA weights. Supports Replicate models in the format <owner>/<username> or <owner>/<username>/<version>, HuggingFace URLs in the format huggingface.co/<owner>/<model-name>, CivitAI URLs in the format civitai.com/models/<id>[/<model-name>], or arbitrary .safetensors URLs from the Internet. For example, 'fofr/flux-pixar-cars'
num_inference_steps Type: integerDefault: 28Range: 1 - 50
Number of denoising steps. More steps can give more detailed images, but take longer.
disable_safety_checker Type: booleanDefault: false
Disable safety checker for generated images.
Output Schema

Output

Type: array β€’ Items Type: string β€’ Items Format: uri

Example Execution Logs
Loaded LoRAs in 0.53s
Using seed: 63239
Prompt: {
"prompt": "linotree β€” A towering California redwood tree dominates the scene, viewed from below so the trunk stretches dramatically upward into the canopy. The bark is described with intricate carved lines and rhythmic hatch marks, while layers of foliage create a sense of depth. Color layers suggest depth of field: rich earthy browns in the foreground, deep greens in the mid-ground, and pale misty greens fading into the distance. Reduction-print friendly, whimsical tone. Consider abstract shapes and over the top flourishes that hint at nature and natural forms. Use yayoi kusama as inspiration. \n\nGeneral Style Prompt (linotree):\nβ€œWhimsical linocut-inspired imagery with bold carved lines, strong silhouettes, and playful charm. Limited color palette of 2–4 flat tones, suitable for reduction printing. Ink textures, paper grain, and carved marks are celebrated. The mood is lighthearted, imaginative, and folk-art inspired β€” simple, graphic, and reduction-print friendly.”",
"negative_prompt": "photorealism, gradients, glossy 3D rendering, painterly washes, watercolor, oil paint, cluttered detail, busy backgrounds, muted palettes, neon glow, documentary realism",
"image": "https://your-reference-image-url-here.jpg",
"strength": 0.6,
"num_inference_steps": 30,
"guidance_scale": 7.0,
"scheduler": "DPMSolverMultistep"
}
[!] txt2img mode
  0%|          | 0/28 [00:00<?, ?it/s]
  4%|β–Ž         | 1/28 [00:00<00:26,  1.01it/s]
  7%|β–‹         | 2/28 [00:01<00:22,  1.15it/s]
 11%|β–ˆ         | 3/28 [00:02<00:23,  1.08it/s]
 14%|β–ˆβ–        | 4/28 [00:03<00:22,  1.06it/s]
 18%|β–ˆβ–Š        | 5/28 [00:04<00:22,  1.04it/s]
 21%|β–ˆβ–ˆβ–       | 6/28 [00:05<00:21,  1.03it/s]
 25%|β–ˆβ–ˆβ–Œ       | 7/28 [00:06<00:20,  1.02it/s]
 29%|β–ˆβ–ˆβ–Š       | 8/28 [00:07<00:19,  1.02it/s]
 32%|β–ˆβ–ˆβ–ˆβ–      | 9/28 [00:08<00:18,  1.02it/s]
 36%|β–ˆβ–ˆβ–ˆβ–Œ      | 10/28 [00:09<00:17,  1.02it/s]
 39%|β–ˆβ–ˆβ–ˆβ–‰      | 11/28 [00:10<00:16,  1.01it/s]
 43%|β–ˆβ–ˆβ–ˆβ–ˆβ–Ž     | 12/28 [00:11<00:15,  1.01it/s]
 46%|β–ˆβ–ˆβ–ˆβ–ˆβ–‹     | 13/28 [00:12<00:14,  1.01it/s]
 50%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆ     | 14/28 [00:13<00:13,  1.01it/s]
 54%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Ž    | 15/28 [00:14<00:12,  1.01it/s]
 57%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–‹    | 16/28 [00:15<00:11,  1.01it/s]
 61%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ    | 17/28 [00:16<00:10,  1.01it/s]
 64%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–   | 18/28 [00:17<00:09,  1.01it/s]
 68%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Š   | 19/28 [00:18<00:08,  1.01it/s]
 71%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–  | 20/28 [00:19<00:07,  1.01it/s]
 75%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Œ  | 21/28 [00:20<00:06,  1.00it/s]
 79%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Š  | 22/28 [00:21<00:05,  1.00it/s]
 82%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ– | 23/28 [00:22<00:04,  1.00it/s]
 86%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Œ | 24/28 [00:23<00:03,  1.00it/s]
 89%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–‰ | 25/28 [00:24<00:02,  1.00it/s]
 93%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Ž| 26/28 [00:25<00:01,  1.00it/s]
 96%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–‹| 27/28 [00:26<00:00,  1.00it/s]
100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 28/28 [00:27<00:00,  1.01it/s]
100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 28/28 [00:27<00:00,  1.02it/s]
Total safe images: 4 out of 4
Version Details
Version ID
280d5d502d79257ad2f7d95dc876e4257fe041c7023f9eaaf4847f33b5166026
Version Created
October 29, 2025
Run on Replicate β†’