goodguy1963/epicrealism-naturalsinfinal-byepinikion-v2 🖼️🔢❓📝 → 🖼️

▶️ 77 runs 📅 Mar 2025 ⚙️ Cog 0.14.3 🔗 GitHub ⚖️ License

image-inpainting image-to-image text-to-image

About

epicrealism-naturalsinfinal-SD1.5-by-epinikion + perfectdeliberate by Desync + More Details by Lykon

Example Output

Prompt:

"woman dancing"

Output

Performance Metrics

15.30s Prediction Time

281.19s Total Time

All Input Parameters

{
  "width": 1024,
  "height": 1024,
  "prompt": "woman dancing",
  "sampler": "DPMPP_2M",
  "model_name": "perfectdeliberate",
  "lora_weight": 0.8,
  "guidance_scale": 7.5,
  "lora_selection": "none",
  "scheduler_type": "karras",
  "negative_prompt": "worst quality, low quality, normal quality, lowres, low details, oversaturated, undersaturated, overexposed, underexposed, grayscale, bw, bad photo, bad photography, bad art, mutated, deformed, distorted, disfigured, body horror, watermark, text, meme, bad proportions, cropped head, out of frame, cut off, ugly, duplicate, mutilated, mutation, disgusting, bad anatomy, bad hands, three hands, three legs, bad feet, three feet",
  "prompt_strength": 0.8,
  "num_inference_steps": 30
}

Input Parameters

mask Type: string: Input mask for inpaint mode. Black areas will be preserved, white areas will be inpainted.
seed Type: integer: Random seed. Leave blank to randomize the seed
image Type: string: Input image for img2img or inpaint mode
width Default: 1024: Width of output image
height Default: 1024: Height of output image
prompt Type: string: Input prompt
sampler Default: DPMSolverMultistep: Choose a sampler
model_name Default: epic_realism_v4: Choose which model to use
lora_weight Type: numberDefault: 0.8Range: 0.5 - 3: LoRA weight (higher values increase effect strength)
guidance_scale Type: numberDefault: 7.5Range: 1 - 20: Scale for classifier-free guidance
lora_selection Default: none: Select a LoRA or LoRA combination to apply
scheduler_type Default: default: Choose a scheduler type
civitai_api_key Type: string: Your Civitai API key for downloading models (REQUIRED)
negative_prompt Type: stringDefault: worst quality, low quality, normal quality, lowres, low details, oversaturated, undersaturated, overexposed, underexposed, grayscale, bw, bad photo, bad photography, bad art, mutated, deformed, distorted, disfigured, body horror, watermark, text, meme, bad proportions, cropped head, out of frame, cut off, ugly, duplicate, mutilated, mutation, disgusting, bad anatomy, bad hands, three hands, three legs, bad feet, three feet: Specify things to not see in the output
prompt_strength Type: numberDefault: 0.8Range: 0 - 1: Prompt strength when using init image. 1.0 corresponds to full destruction of information in init image
num_inference_steps Type: integerDefault: 30Range: 1 - 500: Number of denoising steps

Output Schema

Output

Type: string • Format: uri

Example Execution Logs

Running prediction...
Using seed: 22573
Clearing CUDA cache before prediction
Loading model: PerfectDeliberate v5.0
Loading from /src/model/perfectdeliberate.safetensors
`text_config_dict` is provided which will be used to initialize `CLIPTextConfig`. The value `text_config["id2label"]` will be overriden.
`text_config_dict` is provided which will be used to initialize `CLIPTextConfig`. The value `text_config["bos_token_id"]` will be overriden.
`text_config_dict` is provided which will be used to initialize `CLIPTextConfig`. The value `text_config["eos_token_id"]` will be overriden.
/root/.pyenv/versions/3.11.10/lib/python3.11/site-packages/transformers/models/clip/feature_extraction_clip.py:28: FutureWarning: The class CLIPFeatureExtractor is deprecated and will be removed in version 5 of Transformers. Please use CLIPImageProcessor instead.
warnings.warn(
Using DPMPP_2M sampler with default configuration
No LoRAs selected
Running txt2img...
Enabling attention slicing for high resolution generation
  0%|          | 0/30 [00:00<?, ?it/s]
  3%|▎         | 1/30 [00:00<00:10,  2.83it/s]
  7%|▋         | 2/30 [00:00<00:07,  3.69it/s]
 10%|█         | 3/30 [00:00<00:06,  4.09it/s]
 13%|█▎        | 4/30 [00:00<00:06,  4.32it/s]
 17%|█▋        | 5/30 [00:01<00:05,  4.45it/s]
 20%|██        | 6/30 [00:01<00:05,  4.54it/s]
 23%|██▎       | 7/30 [00:01<00:05,  4.59it/s]
 27%|██▋       | 8/30 [00:01<00:04,  4.63it/s]
 30%|███       | 9/30 [00:02<00:04,  4.66it/s]
 33%|███▎      | 10/30 [00:02<00:04,  4.67it/s]
 37%|███▋      | 11/30 [00:02<00:04,  4.69it/s]
 40%|████      | 12/30 [00:02<00:03,  4.69it/s]
 43%|████▎     | 13/30 [00:02<00:03,  4.70it/s]
 47%|████▋     | 14/30 [00:03<00:03,  4.70it/s]
 50%|█████     | 15/30 [00:03<00:03,  4.71it/s]
 53%|█████▎    | 16/30 [00:03<00:02,  4.71it/s]
 57%|█████▋    | 17/30 [00:03<00:02,  4.71it/s]
 60%|██████    | 18/30 [00:03<00:02,  4.71it/s]
 63%|██████▎   | 19/30 [00:04<00:02,  4.71it/s]
 67%|██████▋   | 20/30 [00:04<00:02,  4.71it/s]
 70%|███████   | 21/30 [00:04<00:01,  4.71it/s]
 73%|███████▎  | 22/30 [00:04<00:01,  4.72it/s]
 77%|███████▋  | 23/30 [00:05<00:01,  4.72it/s]
 80%|████████  | 24/30 [00:05<00:01,  4.71it/s]
 83%|████████▎ | 25/30 [00:05<00:01,  4.72it/s]
 87%|████████▋ | 26/30 [00:05<00:00,  4.72it/s]
 90%|█████████ | 27/30 [00:05<00:00,  4.72it/s]
 93%|█████████▎| 28/30 [00:06<00:00,  4.72it/s]
 97%|█████████▋| 29/30 [00:06<00:00,  4.72it/s]
100%|██████████| 30/30 [00:06<00:00,  4.72it/s]
100%|██████████| 30/30 [00:06<00:00,  4.61it/s]

Version Details

Version ID: 5310130b210862f0f4c222c5f67d1e0ccde3b1aaf4a3abb2918cad7d3f2dce4b
Version Created: March 22, 2025

Run on Replicate →