lovis93's picture
Upload README.md with huggingface_hub
3ca8dbc verified
|
raw
history blame
3.79 kB
metadata
license: creativeml-openrail-m
language:
  - en
tags:
  - flux
  - flux.1
  - flux-lora
  - lora
  - multi-angle
  - camera-angles
  - 3d-poses
  - text-to-image
  - image-generation
base_model: black-forest-labs/FLUX.1-dev
pipeline_tag: text-to-image
widget:
  - text: <sks> front view eye-level shot close-up, a robot
    output:
      url: poses_72_animated.gif

🎬 Flux Multi-Angles v2 - 72 Camera Poses LoRA

Generate images from any angle with precise camera control!

This LoRA enables 72 unique camera positions for FLUX.1, giving you complete control over viewing angles, elevations, and distances.

72 Poses Hemisphere

πŸ†• What's New in v2?

Feature v1 (24 Poses) v2 (72 Poses)
Azimuths 8 8
Elevations 3 9
Distances 1 (close-up) 3 (close-up, medium, wide)
Total Poses 24 72

24 vs 72 Comparison

πŸ“ Camera Configuration

8 Azimuth Angles (Horizontal)

Angle View Name
0Β° front view
45Β° front-right quarter view
90Β° right side view
135Β° back-right quarter view
180Β° back view
225Β° back-left quarter view
270Β° left side view
315Β° front-left quarter view

9 Elevation Angles (Vertical)

Angle Shot Type
0Β° eye-level shot
10Β° low-angle shot
20Β° mid-low shot
30Β° mid-angle shot
40Β° high-mid shot
45Β° high-angle shot
50Β° steep-mid shot
60Β° steep-angle shot
75Β° overhead shot

3 Distances (Depth)

Distance Radius
close-up 3.0
medium shot 4.0
wide shot 5.0

🎯 Prompt Format

<sks> [view] [elevation] shot [distance]

Examples

<sks> front view eye-level shot close-up
<sks> right side view high-angle shot medium shot
<sks> back view overhead shot wide shot
<sks> front-left quarter view mid-angle shot close-up

Complete Prompt Reference

72 Poses Prompts

πŸ“¦ Files Included

File Description Use Case
flux-multi-angles-v2-72poses-fal.safetensors FAL-compatible LoRA Use with FAL.ai API
flux-multi-angles-v2-72poses-comfy.safetensors ComfyUI-compatible LoRA Use with ComfyUI

πŸš€ Usage

With ComfyUI

  1. Download flux-multi-angles-v2-72poses-comfy.safetensors
  2. Place in your ComfyUI/models/loras/ folder
  3. Load FLUX.1-dev as base model
  4. Apply LoRA with strength 0.8-1.0
  5. Use the prompt format: <sks> [view] [elevation] shot [distance], [your subject]

With FAL.ai

  1. Use flux-multi-angles-v2-72poses-fal.safetensors
  2. Upload to FAL or reference from Hugging Face
  3. Use the same prompt format

Example Prompts

# Front view, eye level, close-up
"<sks> front view eye-level shot close-up, a futuristic robot"

# Side view, high angle, medium distance
"<sks> right side view high-angle shot medium shot, a sports car"

# Back view, overhead, wide shot
"<sks> back view overhead shot wide shot, a medieval castle"

βš™οΈ Recommended Settings

  • LoRA Strength: 0.8 - 1.0
  • CFG Scale: 3.5 - 7.0
  • Steps: 20-30
  • Base Model: FLUX.1-dev

πŸŽ₯ Animation Preview

72 Poses Animated

πŸ“„ License

This model is released under the CreativeML Open RAIL-M License.

πŸ‘€ Author

Created by lovis93 (@lovis93)

πŸ™ Acknowledgments

  • Black Forest Labs for FLUX.1
  • The Hugging Face community

If you find this model useful, please consider giving it a ⭐!