This workflow enables generating images via speech and also edit the prompt via additional speech instructions. Alternatively there are text boxes to be used instead if preferred. The workflow uses the OpenFlux turbo and fast Loras for fast iterations.

This way you can rapidly try out different prompts without having to worry about the prompt structure and let chatGPT make adjustments to your prompts  for you.

Depending on your graphics card, generation times for the image itself can vary. If you have a lower end GPU try to lower the steps in the sampler further.

Video walkthrough: https://youtu.be/2734vcWTu44

Resources:

Flux dev de-distilled unet model:  https://huggingface.co/nyanko7/flux-dev-de-distill

Flux dev de-distilled unet model:  https://huggingface.co/nyanko7/flux-dev-de-distill

Lora:

Fast Lora: https://huggingface.co/ostris/OpenFLUX.1/blob/main/openflux1-v0.1.0-fast-lora.safetensors

Turbo Lora: https://huggingface.co/alimama-creative/FLUX.1-Turbo-Alpha

Realism Lora:  https://huggingface.co/XLabs-AI/flux-RealismLora

Detail Slider Lora:  https://civitai.com/images/28128089

Text encoders:

ViT-L-14-BEST-smooth-GmP-ft:

https://huggingface.co/zer0int/CLIP-GmP-ViT-L-14/resolve/main/ViT-L-14-BEST-smooth-GmP-ft.safetensors?download=true

t5-v1_1-xxl:

https://huggingface.co/city96/t5-v1_1-xxl-encoder-bf16/resolve/main/model.safetensors?download=true

Clip G:

https://huggingface.co/stabilityai/stable-diffusion-3.5-large/resolve/main/text_encoders/clip_g.safetensors?download=true