Flux.2 Dev Edit 8Steps Turbo
Execution
2m 13sbilled · 4,256 credits
7m 15sQueued 2.38s·Startup 4m 59s·GPU Execution 2m 13s
Inputs
Metadata
Prompts
CLIP Text Encode (Positive Prompt)
Apply the design from Reference Image 1 onto objects in Reference Image 2.
Unbypass (CTRL-B) the ReferenceLatent nodes to give ref images.
If you want to add more reference images, you can add multiple reference images by following the pattern.
If you don't want any reference image, just select all ReferenceLatent nodes and then use CTRL-B to bypass them, turning the workflow into a Text to Image workflow.
Groups
- Model
- Custom sampler
- Image size
- Prompt
- Reference images (up to 10)
- Turbo LoRA
Checkpoints
- https://huggingface.co/Comfy-Org/flux2-dev/resolve/main/split_files/vae/flux2-vae.safetensors
- flux2-vae.safetensors
- https://huggingface.co/Comfy-Org/flux2-dev/resolve/main/split_files/vae/flux2-vae.safetensors
- flux2-vae.safetensors
- flux2-vae.safetensors
- https://huggingface.co/Comfy-Org/flux2-dev/resolve/main/split_files/diffusion_models/flux2_dev_fp8mixed.safetensors
- flux2_dev_fp8mixed.safetensors
- https://huggingface.co/Comfy-Org/flux2-dev/resolve/main/split_files/diffusion_models/flux2_dev_fp8mixed.safetensors
- flux2_dev_fp8mixed.safetensors
- flux2_dev_fp8mixed.safetensors
- https://huggingface.co/Comfy-Org/flux2-dev/resolve/main/split_files/loras/Flux2TurboComfyv2.safetensors
- Flux2TurboComfyv2.safetensors
- Flux2TurboComfyv2.safetensors
- https://huggingface.co/Comfy-Org/flux2-dev/resolve/main/split_files/text_encoders/mistral_3_small_flux2_fp8.safetensors
- mistral_3_small_flux2_fp8.safetensors
- mistral_3_small_flux2_fp8.safetensors