usamaehsan/multi-controlnet-x-ip-adapter-vision-v2 🔢📝❓✓🖼️ → 🖼️

▶️ 5.2K runs 📅 Feb 2024 ⚙️ Cog 0.9.4
image-inpainting sketch-to-image text-to-image

About

Example Output

Prompt:

"jungle"

Output

Example output

Performance Metrics

5.24s Prediction Time
219.07s Total Time
All Input Parameters
{
  "eta": 0,
  "prompt": "jungle",
  "max_width": 512,
  "scheduler": "DDIM",
  "guess_mode": false,
  "max_height": 512,
  "num_outputs": 1,
  "guidance_scale": 7,
  "ip_adapter_ckpt": "ip-adapter_sd15.bin",
  "negative_prompt": "Longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality",
  "img2img_strength": 0.5,
  "ip_adapter_weight": 1,
  "sorted_controlnets": "tile, inpainting, lineart",
  "num_inference_steps": 20,
  "disable_safety_check": false,
  "film_grain_lora_weight": 0,
  "tile_conditioning_scale": 1,
  "add_more_detail_lora_scale": 0.5,
  "detail_tweaker_lora_weight": 0,
  "lineart_conditioning_scale": 1,
  "scribble_conditioning_scale": 1,
  "epi_noise_offset_lora_weight": 0,
  "brightness_conditioning_scale": 1,
  "inpainting_conditioning_scale": 1,
  "color_temprature_slider_lora_weight": 0
}
Input Parameters
eta Type: numberDefault: 0
Controls the amount of noise that is added to the input data during the denoising diffusion process. Higher value -> more noise
seed Type: integer
Seed
prompt (required) Type: string
Prompt - using compel, use +++ to increase words weight:: doc: https://github.com/damian0815/compel/tree/main/doc || https://invoke-ai.github.io/InvokeAI/features/PROMPTS/#attention-weighting
max_width Type: integerDefault: 512
Max width/Resolution of image
scheduler Default: DDIM
Choose a scheduler.
guess_mode Type: booleanDefault: false
In this mode, the ControlNet encoder will try best to recognize the content of the input image even if you remove all prompts. The `guidance_scale` between 3.0 and 5.0 is recommended.
mask_image Type: string
mask image for inpainting controlnet
max_height Type: integerDefault: 512
Max height/Resolution of image
tile_image Type: string
Control image for tile controlnet
num_outputs Type: integerDefault: 1Range: 1 - 10
Number of images to generate
img2img_image Type: string
Image2image image
lineart_image Type: string
Control image for canny controlnet
guidance_scale Type: numberDefault: 7Range: 0.1 - 30
Scale for classifier-free guidance
scribble_image Type: string
Control image for scribble controlnet
ip_adapter_ckpt Default: ip-adapter_sd15.bin
IP Adapter checkpoint
negative_prompt Type: stringDefault: Longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality
Negative prompt - using compel, use +++ to increase words weight//// negative-embeddings available ///// FastNegativeV2 , boring_e621_v4 , verybadimagenegative_v1 || to use them, write their keyword in negative prompt
brightness_image Type: string
Control image for brightness controlnet
img2img_strength Type: numberDefault: 0.5
img2img strength, does not work when inpainting image is given, 0.1-same image, 0.99-complete destruction of image
inpainting_image Type: string
Control image for inpainting controlnet
ip_adapter_image Type: string
IP Adapter image
ip_adapter_weight Type: numberDefault: 1
IP Adapter weight
sorted_controlnets Type: stringDefault: tile, inpainting, lineart
Comma seperated string of controlnet names, list of names: tile, inpainting, lineart,depth ,scribble , brightness /// example value: tile, inpainting, lineart
num_inference_steps Type: integerDefault: 20
Steps to run denoising
disable_safety_check Type: booleanDefault: false
Disable safety check. Use at your own risk!
film_grain_lora_weight Type: numberDefault: 0
disabled on 0
negative_auto_mask_text Type: string
comma seperated list of objects you dont want to mask, AI will auto delete these objects from mask, only works if positive_auto_mask_text is given
positive_auto_mask_text Type: string
comma seperated list of objects for mask, AI will auto create mask of these objects, if mask text is given, mask image will not work
tile_conditioning_scale Type: numberDefault: 1
Conditioning scale for tile controlnet
add_more_detail_lora_scale Type: numberDefault: 0.5
Scale/ weight of more_details lora, more scale = more details, disabled on 0
detail_tweaker_lora_weight Type: numberDefault: 0
disabled on 0
lineart_conditioning_scale Type: numberDefault: 1
Conditioning scale for canny controlnet
scribble_conditioning_scale Type: numberDefault: 1
Conditioning scale for scribble controlnet
epi_noise_offset_lora_weight Type: numberDefault: 0
disabled on 0
brightness_conditioning_scale Type: numberDefault: 1
Conditioning scale for brightness controlnet
inpainting_conditioning_scale Type: numberDefault: 1
Conditioning scale for brightness controlnet
color_temprature_slider_lora_weight Type: numberDefault: 0
disabled on 0
Output Schema

Output

Type: arrayItems Type: stringItems Format: uri

Example Execution Logs
Time taken until build pipe: 0.00 seconds
using ip adapter:: example/cat.png
loading ip adapter
Time taken to load IP adapter model: 0.01 seconds
Time taken to load image encoder model: 0.00 seconds
Time taken to build pipe: 0.24 seconds
Time taken to apply scheduler-- : 0.00 seconds
Time taken to cuda-- : 0.00 seconds
Using seed: 25977
Time taken until ip -- : 0.00 seconds
Time taken to load ip-- : 2.16 seconds
  0%|          | 0/20 [00:00<?, ?it/s]
  5%|▌         | 1/20 [00:00<00:04,  4.72it/s]
 15%|█▌        | 3/20 [00:00<00:01,  9.93it/s]
 25%|██▌       | 5/20 [00:00<00:01, 12.53it/s]
 35%|███▌      | 7/20 [00:00<00:00, 14.09it/s]
 45%|████▌     | 9/20 [00:00<00:00, 15.05it/s]
 55%|█████▌    | 11/20 [00:00<00:00, 15.58it/s]
 65%|██████▌   | 13/20 [00:00<00:00, 15.88it/s]
 75%|███████▌  | 15/20 [00:01<00:00, 16.19it/s]
 85%|████████▌ | 17/20 [00:01<00:00, 16.38it/s]
 95%|█████████▌| 19/20 [00:01<00:00, 16.14it/s]
100%|██████████| 20/20 [00:01<00:00, 14.73it/s]
Time taken to generate image-- : 1.47 seconds
/root/.pyenv/versions/3.9.18/lib/python3.9/site-packages/peft/tuners/lora/layer.py:595: UserWarning: Already unmerged. Nothing to do.
warnings.warn("Already unmerged. Nothing to do.")
/root/.pyenv/versions/3.9.18/lib/python3.9/site-packages/peft/tuners/lora/layer.py:256: UserWarning: Already unmerged. Nothing to do.
warnings.warn("Already unmerged. Nothing to do.")
Version Details
Version ID
7a904d90b4a018eeb8e47dd850470ef651a6f4563fa20dc8b62deb0f344cb13a
Version Created
February 23, 2024
Run on Replicate →