Kontext-CAM-Right-View

prithivMLmods/Kontext-CAM-Right-View

Kontext-CAM-Right-View is a image-to-image model from prithivMLmods. Use it when you need one image transformed into another. It is set up for diffusers. The card lists the license as other.

Downloads · 30 days

14% of all-time downloads

All-time downloads

502

Public

Repo size

615 MB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors613 MB · 100%

At a glance

Task: Image-to-Image
Library: diffusers
License: other
Access: Public
Created: Nov 8, 2025
Updated: Nov 8, 2025
SHA: 928aac22

Base models

black-forest-labs/FLUX.1-Kontext-dev

Spaces

Model card

From the Hugging Face model README

Kontext-CAM-Right-View

The Kontext-CAM-Right-View is an experimental adapter for black-forest-lab's FLUX.1-Kontext-dev, designed to transform scenes into a right-side camera perspective while preserving natural lighting, accurate geometry, and realistic textures. The model maintains harmony with the original environment, shadows, and visual tone, ensuring smooth perspective transitions and authentic scene composition. It was trained on 800 image pairs (400 start images and 400 end images) to achieve precise, context-aware right-side viewpoint generation.

[!note] [photo content], generate the right-side perspective of the scene. Ensure natural lighting, accurate geometry, and realistic textures. Maintain harmony with the original image’s environment, shadows, and visual tone while providing the right-side visual continuation.

You modified the prompt, altering its properties and subjective elements. Note: this is an experimental adapter and may contain artifacts.

Sample Inferences : Demo

Parameter Settings

Setting	Value
Module Type	Adapter
Base Model	FLUX.1 Kontext Dev - fp8
Trigger Words	[photo content], generate the right-side perspective of the scene. Ensure natural lighting, accurate geometry, and realistic textures. Maintain harmony with the original image’s environment, shadows, and visual tone while providing the right-side visual continuation.
Image Processing Repeats	43
Epochs	23
Save Every N Epochs	1

Labeling: DeepCaption-VLA-7B(natural language & English)

Total Images Used for Training : 800 Image Pairs (400 Start, 400 End)

Training Parameters

Setting	Value
Seed	-
Clip Skip	-
Text Encoder LR	0.00001
UNet LR	0.00005
LR Scheduler	constant
Optimizer	AdamW8bit
Network Dimension	64
Network Alpha	32
Gradient Accumulation Steps	-

Label Parameters

Setting	Value
Shuffle Caption	-
Keep N Tokens	-

Advanced Parameters

Setting	Value
Noise Offset	0.03
Multires Noise Discount	0.1
Multires Noise Iterations	10
Conv Dimension	-
Conv Alpha	-
Batch Size	-
Steps	3200 & 300(warm up)
Sampler	euler

Trigger words

You should use [photo content] to trigger the image generation.

You should use generate the right-side perspective of the scene. Ensure natural lighting to trigger the image generation.

You should use accurate geometry to trigger the image generation.

You should use and realistic textures. Maintain harmony with the original image’s environment to trigger the image generation.

You should use shadows to trigger the image generation.

You should use and visual tone while providing the right-side visual continuation. to trigger the image generation.

Download model

Download them in the Files & versions tab.

Task: Image-to-Image
Library: diffusers
License: other
Languages: en
Fal Ai: live
Replicate: live
Wavespeed: live
Created: Nov 8, 2025
Updated: Nov 8, 2025