Downloads · 30 days
70
14% of all-time downloads
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
70
14% of all-time downloads
All-time downloads
502
Public
Repo size
615 MB
Likes
2
Public
Click a slice to open those files.
.safetensors613 MB · 100%
From the Hugging Face model README

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.
| 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)
| 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 | - |
| Setting | Value |
|---|---|
| Shuffle Caption | - |
| Keep N Tokens | - |
| 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 |
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 them in the Files & versions tab.