ori299/mc-thumbnails-v1 🖼️🔢❓📝✓ → 🖼️

▶️ 637 runs 📅 Sep 2024 ⚙️ Cog 0.9.20
image-to-image lora minecraft text-to-image

About

Example Output

Prompt:

"

Create a TOK featuring a Minecraft village scene. On the left side of the canvas, depict a charming, well-maintained village with cobblestone paths, neat wooden houses with thatched roofs, and villagers engaging in daily activities like farming and trading. The village is surrounded by lush greenery, including a small garden with crops and a few animals like cows and pigs. The sky is clear with a bright sun, and the overall atmosphere is peaceful and welcoming.

On the right side, illustrate a rugged, mountainous terrain. Show a mining area with exposed stone and ores, and a few miners in protective gear working with pickaxes and shovels. Add details like mining carts and a makeshift shelter with torches for light. The landscape should be rough and uneven, with steep cliffs and sparse vegetation. The sky is overcast with some dark clouds, reflecting the challenging environment of mining.

The background should clearly emphasize the contrast between the peaceful, organized village and the rugged, industrious mining area, showcasing the different aspects of Minecraft life.

"

Output

Example outputExample output

Performance Metrics

43.67s Prediction Time
43.68s Total Time
All Input Parameters
{
  "model": "dev",
  "prompt": "Create a TOK featuring a Minecraft village scene. On the left side of the canvas, depict a charming, well-maintained village with cobblestone paths, neat wooden houses with thatched roofs, and villagers engaging in daily activities like farming and trading. The village is surrounded by lush greenery, including a small garden with crops and a few animals like cows and pigs. The sky is clear with a bright sun, and the overall atmosphere is peaceful and welcoming.\n\nOn the right side, illustrate a rugged, mountainous terrain. Show a mining area with exposed stone and ores, and a few miners in protective gear working with pickaxes and shovels. Add details like mining carts and a makeshift shelter with torches for light. The landscape should be rough and uneven, with steep cliffs and sparse vegetation. The sky is overcast with some dark clouds, reflecting the challenging environment of mining.\n\nThe background should clearly emphasize the contrast between the peaceful, organized village and the rugged, industrious mining area, showcasing the different aspects of Minecraft life.",
  "lora_scale": 1,
  "num_outputs": 2,
  "aspect_ratio": "16:9",
  "output_format": "png",
  "guidance_scale": 3.5,
  "output_quality": 80,
  "extra_lora_scale": 0.8,
  "num_inference_steps": 50
}
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: arrayItems Type: stringItems Format: uri

Example Execution Logs
Using seed: 42811
Prompt: Create a TOK featuring a Minecraft village scene. On the left side of the canvas, depict a charming, well-maintained village with cobblestone paths, neat wooden houses with thatched roofs, and villagers engaging in daily activities like farming and trading. The village is surrounded by lush greenery, including a small garden with crops and a few animals like cows and pigs. The sky is clear with a bright sun, and the overall atmosphere is peaceful and welcoming.
On the right side, illustrate a rugged, mountainous terrain. Show a mining area with exposed stone and ores, and a few miners in protective gear working with pickaxes and shovels. Add details like mining carts and a makeshift shelter with torches for light. The landscape should be rough and uneven, with steep cliffs and sparse vegetation. The sky is overcast with some dark clouds, reflecting the challenging environment of mining.
The background should clearly emphasize the contrast between the peaceful, organized village and the rugged, industrious mining area, showcasing the different aspects of Minecraft life.
txt2img mode
Using dev model
free=9292853874688
Downloading weights
2024-09-01T18:12:04Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmp74nw80ff/weights url=https://replicate.delivery/yhqm/Pk9VqajjHNpeCqhq9r1wvvhW6fNo4TehVbfRGraiwEQ0dXiNB/trained_model.tar
2024-09-01T18:12:07Z | INFO  | [ Complete ] dest=/tmp/tmp74nw80ff/weights size="301 MB" total_elapsed=3.290s url=https://replicate.delivery/yhqm/Pk9VqajjHNpeCqhq9r1wvvhW6fNo4TehVbfRGraiwEQ0dXiNB/trained_model.tar
Downloaded weights in 3.33s
Loaded LoRAs in 16.02s
The following part of your input was truncated because CLIP can only handle sequences up to 77 tokens: ['is clear with a bright sun, and the overall atmosphere is peaceful and welcoming. on the right side, illustrate a rugged, mountainous terrain. show a mining area with exposed stone and ores, and a few miners in protective gear working with pickaxes and shovels. add details like mining carts and a makeshift shelter with torches for light. the landscape should be rough and uneven, with steep cliffs and sparse vegetation. the sky is overcast with some dark clouds, reflecting the challenging environment of mining. the background should clearly emphasize the contrast between the peaceful, organized village and the rugged, industrious mining area, showcasing the different aspects of minecraft life.', 'is clear with a bright sun, and the overall atmosphere is peaceful and welcoming. on the right side, illustrate a rugged, mountainous terrain. show a mining area with exposed stone and ores, and a few miners in protective gear working with pickaxes and shovels. add details like mining carts and a makeshift shelter with torches for light. the landscape should be rough and uneven, with steep cliffs and sparse vegetation. the sky is overcast with some dark clouds, reflecting the challenging environment of mining. the background should clearly emphasize the contrast between the peaceful, organized village and the rugged, industrious mining area, showcasing the different aspects of minecraft life.']
  0%|          | 0/50 [00:00<?, ?it/s]
  2%|▏         | 1/50 [00:00<00:25,  1.90it/s]
  4%|▍         | 2/50 [00:00<00:22,  2.18it/s]
  6%|▌         | 3/50 [00:01<00:23,  2.04it/s]
  8%|▊         | 4/50 [00:01<00:23,  1.98it/s]
 10%|█         | 5/50 [00:02<00:23,  1.95it/s]
 12%|█▏        | 6/50 [00:03<00:22,  1.93it/s]
 14%|█▍        | 7/50 [00:03<00:22,  1.92it/s]
 16%|█▌        | 8/50 [00:04<00:21,  1.91it/s]
 18%|█▊        | 9/50 [00:04<00:21,  1.91it/s]
 20%|██        | 10/50 [00:05<00:21,  1.90it/s]
 22%|██▏       | 11/50 [00:05<00:20,  1.90it/s]
 24%|██▍       | 12/50 [00:06<00:19,  1.90it/s]
 26%|██▌       | 13/50 [00:06<00:19,  1.90it/s]
 28%|██▊       | 14/50 [00:07<00:18,  1.90it/s]
 30%|███       | 15/50 [00:07<00:18,  1.90it/s]
 32%|███▏      | 16/50 [00:08<00:17,  1.90it/s]
 34%|███▍      | 17/50 [00:08<00:17,  1.90it/s]
 36%|███▌      | 18/50 [00:09<00:16,  1.90it/s]
 38%|███▊      | 19/50 [00:09<00:16,  1.90it/s]
 40%|████      | 20/50 [00:10<00:15,  1.90it/s]
 42%|████▏     | 21/50 [00:10<00:15,  1.90it/s]
 44%|████▍     | 22/50 [00:11<00:14,  1.89it/s]
 46%|████▌     | 23/50 [00:12<00:14,  1.90it/s]
 48%|████▊     | 24/50 [00:12<00:13,  1.90it/s]
 50%|█████     | 25/50 [00:13<00:13,  1.90it/s]
 52%|█████▏    | 26/50 [00:13<00:12,  1.90it/s]
 54%|█████▍    | 27/50 [00:14<00:12,  1.90it/s]
 56%|█████▌    | 28/50 [00:14<00:11,  1.90it/s]
 58%|█████▊    | 29/50 [00:15<00:11,  1.90it/s]
 60%|██████    | 30/50 [00:15<00:10,  1.90it/s]
 62%|██████▏   | 31/50 [00:16<00:10,  1.90it/s]
 64%|██████▍   | 32/50 [00:16<00:09,  1.90it/s]
 66%|██████▌   | 33/50 [00:17<00:08,  1.90it/s]
 68%|██████▊   | 34/50 [00:17<00:08,  1.90it/s]
 70%|███████   | 35/50 [00:18<00:07,  1.90it/s]
 72%|███████▏  | 36/50 [00:18<00:07,  1.90it/s]
 74%|███████▍  | 37/50 [00:19<00:06,  1.90it/s]
 76%|███████▌  | 38/50 [00:19<00:06,  1.90it/s]
 78%|███████▊  | 39/50 [00:20<00:05,  1.89it/s]
 80%|████████  | 40/50 [00:20<00:05,  1.89it/s]
 82%|████████▏ | 41/50 [00:21<00:04,  1.89it/s]
 84%|████████▍ | 42/50 [00:22<00:04,  1.89it/s]
 86%|████████▌ | 43/50 [00:22<00:03,  1.89it/s]
 88%|████████▊ | 44/50 [00:23<00:03,  1.89it/s]
 90%|█████████ | 45/50 [00:23<00:02,  1.89it/s]
 92%|█████████▏| 46/50 [00:24<00:02,  1.89it/s]
 94%|█████████▍| 47/50 [00:24<00:01,  1.89it/s]
 96%|█████████▌| 48/50 [00:25<00:01,  1.89it/s]
 98%|█████████▊| 49/50 [00:25<00:00,  1.89it/s]
100%|██████████| 50/50 [00:26<00:00,  1.89it/s]
100%|██████████| 50/50 [00:26<00:00,  1.90it/s]
Version Details
Version ID
35a4af359d251a502e7f72eac8bab16ad23718650f4ad0690701dc40681f4cf0
Version Created
September 1, 2024
Run on Replicate →