Dooku Live Old Image Generation

Transform your ideas into stunning visuals with Dooku Live Old Image Generation. Ready to experience the power of AI? Start your journey here!

Platform: Replicate

Text-to-ImageImage-to-ImageImage InpaintingLoRA Fine-tuning

41 runs

H100

License Check Required

🚀Function Overview

Generates images from text prompts, with options for image-to-image translation, inpainting, and fine-tuning using LoRA weights.

Key Features

Prompts with trigger words for activating specific trained concepts
Image inputs for img2img or inpainting modes
Custom aspect ratio and resolution controls
Multiple generation speed modes (optimized FP8 vs original BF16)
Adjustable LoRA scaling for fine-tuned outputs
Safety checker toggle for generated images

Use Cases

•Creating cinematic character illustrations
•Image editing through inpainting
•Art style adaptation with custom LoRA weights
•Prototyping concept art for gaming

⚙️Input Parameters

prompt

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.

image

string

Input image for image to image or inpainting mode. If provided, aspect_ratio, width, and height inputs are ignored.

mask

string

Image mask for image inpainting mode. If provided, aspect_ratio, width, and height inputs are ignored.

aspect_ratio

string

Aspect ratio for the generated image. If custom is selected, uses height and width below & will run in bf16 mode

height

integer

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

width

integer

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

prompt_strength

number

Prompt strength when using img2img. 1.0 corresponds to full destruction of information in image

model

string

Which model to run inference with. The dev model performs best with around 28 inference steps but the schnell model only needs 4 steps.

num_outputs

integer

Number of outputs to generate

num_inference_steps

integer

Number of denoising steps. More steps can give more detailed images, but take longer.

guidance_scale

number

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

seed

integer

Random seed. Set for reproducible generation

output_format

string

Format of the output images

output_quality

integer

Quality when saving the output images, from 0 to 100. 100 is best quality, 0 is lowest quality. Not relevant for .png outputs

disable_safety_checker

boolean

Disable safety checker for generated images.

go_fast

boolean

Run faster predictions with model optimized for speed (currently fp8 quantized); disable to run in original bf16

megapixels

string

Approximate number of megapixels for generated image

lora_scale

number

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.

extra_lora

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'

extra_lora_scale

number

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.

💡Usage Examples

Example 1

Input Parameters

{
  "model": "dev",
  "prompt": "Close-up headshot of Count Dooku holding a red lightsaber with a brilliant white core, glowing intensely. A vivid red aura surrounds him, casting a powerful light on his stern, focused face. The iconic silver chain holding his dark cape is clearly visible across his shoulders. The lighting is dramatic and cinematic, with realistic shadows and subtle Sith ambiance in the background. The image should have a photorealistic style with sharp detail and a moody, dark tone.",
  "go_fast": false,
  "lora_scale": 1,
  "megapixels": "1",
  "num_outputs": 1,
  "aspect_ratio": "21:9",
  "output_format": "jpg",
  "guidance_scale": 3,
  "output_quality": 80,
  "prompt_strength": 0.8,
  "extra_lora_scale": 1,
  "num_inference_steps": 28
}

Output Results

https://replicate.delivery/xezq/I6qvvCPlqXoCLJqwlTJeHfbhotv64qxUa3K6qMFzIB3c0ZoUA/out-0.jpg

Quick Actions

Use NowView Documentation

Technical Specifications

Hardware Type: H100
Run Count: 41
Commercial Use: Unknown/Restricted
Platform: Replicate

Related Keywords

Text-to-ImageImage-to-ImageImage InpaintingLoRA Fine-tuningCinematic Character IllustrationsConcept Art Prototyping

Related Models

Leia Organa Image Generator

A model for generating and manipulating images of Leia Organa using text prompts and image inputs.

Bruna Depaula Image Generator

A model for generating and editing images using LoRA technology with support for inpainting and image-to-image processing.

Mindy Generator

A model for generating images using text prompts with support for image-to-image translation, inpainting, and LoRA integration.