sergeicu/sdxl-lcm-glass1 🖼️🔢📝❓✓ → 🖼️

▶️ 153 runs 📅 Nov 2023 ⚙️ Cog 0.8.6

About

Stable Diffusion XL + LCM + LoRa trained on images from Corning Museum of Glass (v1)

Example Output

Prompt:

"in the style of <s0><s1> someone has made a lovely flower brooch on a white plate"

Output

Performance Metrics

4.34s Prediction Time

63.34s Total Time

All Input Parameters

{
  "seed": 2,
  "image": "https://replicate.delivery/pbxt/JvnFqHX4Moir5tba0MokREnmS5VbeogGZBYOjDywHdzX0VuE/99012-nyan-cat-png-image-high-quality.png",
  "width": 1024,
  "height": 1024,
  "prompt": "in the style of <s0><s1> someone has made a lovely flower brooch on a white plate",
  "scheduler": "LCM",
  "lora_scale": 0.6,
  "num_outputs": 1,
  "guidance_scale": 2,
  "apply_watermark": true,
  "negative_prompt": "",
  "prompt_strength": 0.98,
  "num_inference_steps": 6
}

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 Type: integerDefault: 1024: Width of output image
height Type: integerDefault: 1024: Height of output image
prompt Type: stringDefault: An astronaut riding a rainbow unicorn, cinematic, dramatic: Input prompt
scheduler Default: LCM: scheduler
lora_scale Type: numberDefault: 0.6Range: 0 - 1: LoRA additive scale. Only applicable on trained models.
num_outputs Type: integerDefault: 1Range: 1 - 4: Number of images to output.
guidance_scale Type: numberDefault: 2Range: 1 - 20: Scale for classifier-free guidance
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
prompt_strength Type: numberDefault: 0.8Range: 0 - 1: Prompt strength when using img2img / inpaint. 1.0 corresponds to full destruction of information in image
replicate_weights Type: string: Replicate LoRA weights to use. Leave blank to use the default weights.
num_inference_steps Type: integerDefault: 6Range: 1 - 20: Number of denoising steps
disable_safety_checker Type: booleanDefault: false: Disable safety checker for generated images. This feature is only available through the API. See [https://replicate.com/docs/how-does-replicate-work#safety](https://replicate.com/docs/how-does-replicate-work#safety)

Output Schema

Output

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

Example Execution Logs

Using seed: 2
Ensuring enough disk space...
Free disk space: 2135558029312
Downloading weights: https://replicate.delivery/pbxt/8Nc9nEytcexRA62iPF8qDCmMgkcediq1vffH3cmwpICkGEqHB/trained_model.tar
b'Downloaded 186 MB bytes in 0.722s (258 MB/s)\nExtracted 186 MB in 0.057s (3.3 GB/s)\n'
Downloaded weights in 0.9748618602752686 seconds
Loading fine-tuned model
Does not have Unet. assume we are using LoRA
Loading Unet LoRA
Prompt: in the style of <s0><s1> someone has made a lovely flower brooch on a white plate
img2img mode
The config attributes {'skip_prk_steps': True} were passed to LCMScheduler, but are not expected and will be ignored. Please verify your scheduler_config.json configuration file.
  0%|          | 0/5 [00:00<?, ?it/s]/root/.pyenv/versions/3.10.13/lib/python3.10/site-packages/diffusers/models/attention_processor.py:1821: FutureWarning: `LoRAAttnProcessor2_0` is deprecated and will be removed in version 0.26.0. Make sure use AttnProcessor2_0 instead by settingLoRA layers to `self.{to_q,to_k,to_v,to_out[0]}.lora_layer` respectively. This will be done automatically when using `LoraLoaderMixin.load_lora_weights`
deprecate(
 20%|██        | 1/5 [00:00<00:01,  3.42it/s]
 40%|████      | 2/5 [00:00<00:00,  5.07it/s]
 60%|██████    | 3/5 [00:00<00:00,  6.01it/s]
 80%|████████  | 4/5 [00:00<00:00,  6.59it/s]
100%|██████████| 5/5 [00:00<00:00,  6.95it/s]
100%|██████████| 5/5 [00:00<00:00,  6.16it/s]

Version Details

Version ID: 1e795474496967ad8a3495be801a876f744d80e71e83cb246ca5e8003fef7b7d
Version Created: November 21, 2023

Run on Replicate →