Text-to-Image
Diffusers
Safetensors
flux
flux-diffusers
controlnet
diffusers-training
4-bit precision
bitsandbytes
Instructions to use tommycik/ControlNetCannyReducedImproved with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use tommycik/ControlNetCannyReducedImproved with Diffusers:
pip install -U diffusers transformers accelerate
from diffusers import ControlNetModel, StableDiffusionControlNetPipeline controlnet = ControlNetModel.from_pretrained("tommycik/ControlNetCannyReducedImproved") pipe = StableDiffusionControlNetPipeline.from_pretrained( "black-forest-labs/FLUX.1-dev", controlnet=controlnet ) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
| { | |
| "_class_name": "FluxControlNetModel", | |
| "_diffusers_version": "0.36.0.dev0", | |
| "_name_or_path": "InstantX/FLUX.1-dev-Controlnet-Canny", | |
| "attention_head_dim": 128, | |
| "axes_dims_rope": [ | |
| 16, | |
| 56, | |
| 56 | |
| ], | |
| "conditioning_embedding_channels": null, | |
| "guidance_embeds": true, | |
| "in_channels": 64, | |
| "joint_attention_dim": 4096, | |
| "num_attention_heads": 24, | |
| "num_layers": 5, | |
| "num_mode": null, | |
| "num_single_layers": 0, | |
| "patch_size": 1, | |
| "pooled_projection_dim": 768, | |
| "quantization_config": { | |
| "_load_in_4bit": true, | |
| "_load_in_8bit": false, | |
| "bnb_4bit_compute_dtype": "bfloat16", | |
| "bnb_4bit_quant_storage": "uint8", | |
| "bnb_4bit_quant_type": "fp4", | |
| "bnb_4bit_use_double_quant": false, | |
| "llm_int8_enable_fp32_cpu_offload": false, | |
| "llm_int8_has_fp16_weight": false, | |
| "llm_int8_skip_modules": null, | |
| "llm_int8_threshold": 6.0, | |
| "load_in_4bit": true, | |
| "load_in_8bit": false, | |
| "quant_method": "bitsandbytes" | |
| } | |
| } | |