AI: Text to image in local - Revision history

Root at 21:16, 2 November 2025

2025-11-02T21:16:46Z

← Older revision		Revision as of 22:16, 2 November 2025
Line 110:		Line 110:

	* for adding new nodes, double click on an empty space		* for adding new nodes, double click on an empty space
	[[Category:AI ~~Resources~~]]		[[Category:AI: Generate media locally]]

Root at 12:08, 22 October 2025

2025-10-22T12:08:42Z

← Older revision		Revision as of 13:08, 22 October 2025
Line 74:		Line 74:
	<ul>		<ul>
	<li><p>Follow the guide for your OS: https://comfyui-wiki.com/en/install/install-comfyui</p>		<li><p>Follow the guide for your OS: https://comfyui-wiki.com/en/install/install-comfyui</p>
	<syntaxhighlight># For Ubuntu:		<syntaxhighlight lang="bash"># For Ubuntu:
	sudo apt install python3 python3-pip python3-venv		sudo apt install python3 python3-pip python3-venv
	python3 -m venv comfy-env		python3 -m venv comfy-env
Line 100:		Line 100:
	=== Launch comfyUI ===		=== Launch comfyUI ===

	<syntaxhighlight>comfy launch</syntaxhighlight>		<syntaxhighlight lang="bash">comfy launch</syntaxhighlight>
	<span id="load-template"></span>		<span id="load-template"></span>
	=== Load Template ===		=== Load Template ===

Root at 06:08, 20 October 2025

2025-10-20T06:08:48Z

← Older revision		Revision as of 07:08, 20 October 2025
Line 110:		Line 110:

	* for adding new nodes, double click on an empty space		* for adding new nodes, double click on an empty space
	~~<!-- From bodyContent 45907992.mraw -->~~

	[[Category:AI Resources]]		[[Category:AI Resources]]

Maintenance script: Added category AI Resources

2025-10-19T17:51:50Z

Added category AI Resources

← Older revision		Revision as of 18:51, 19 October 2025
Line 112:		Line 112:
	<!-- From bodyContent 45907992.mraw -->		<!-- From bodyContent 45907992.mraw -->

			[[Category:AI Resources]]

Maintenance script: Maintenance script moved page UserDocumentation:Knowledge Central/Resources/IT Resources/AI Resources/AI: Text to image in local to AI: Text to image in local: Cleaned title and categorized

2025-10-19T17:51:50Z

Maintenance script moved page UserDocumentation:Knowledge Central/Resources/IT Resources/AI Resources/AI: Text to image in local to AI: Text to image in local: Cleaned title and categorized

← Older revision	Revision as of 18:51, 19 October 2025
(No difference)

imported>Unknown user at 07:55, 16 September 2025

2025-09-16T07:55:26Z

← Older revision		Revision as of 08:55, 16 September 2025
Line 1:		Line 1:
			In this case, where are going to use Flux (https://bfl.ai/)

			Flux (styled often as '''FLUX''' or '''FLUX.1''') is a family of '''text-to-image generation models''' developed by ''Black Forest Labs (BFL)''.

			Key features & properties:

			{\| class="wikitable" table-width="760" layout="default" ac:local-id="c24da384-3fc5-4ebc-ad49-82129ee44632"
			\|-
			! Feature

			! Description

			\|-
			\| '''Architecture'''

			\| A “rectified flow transformer” model, ~12B parameters, combining approaches from diffusion, transformer flow matching, etc.

			\|-
			\| '''Model Variants / Licencing'''

			\| There are several variants:

			\|-
			\| – '''FLUX.1 [schnell]'''

			\| The fast, distilled version. Open source, Apache-2.0 • high speed, fewer inference steps.

			\|-
			\| – '''FLUX.1 [dev]'''

			\| More powerful, more resource-intensive, open weights under non-commercial licence. Better fidelity.

			\|-
			\| – '''FLUX.1 [pro]'''

			\| Commercial / API access only. Higher quality, possibly features not in open models.

			\|-
			\| '''Additional modes'''

			\| E.g. “Ultra”, “Raw” for very high resolution or photorealism. Also “Kontext” for editing / in-context image generation.

			\|-
			\| '''Usage'''

			\| Can be used via APIs, via HuggingFace / other model hubs, or locally with GUIs / “WebUIs” (Stable Diffusion‐style UIs like Forge, ComfyUI), etc.

			\|}

			So it’s kind of a next‐gen Stable Diffusion-like set of models, with some distilled/faster versions and some high-quality ones. Good prompt following, potentially strong image quality.


			-----

			<span id="use-cases-what-it-is-used-for"></span>
			=== Use cases / What it is used for ===

			* Generating images from text prompts (text→image).
			* Image editing / in-context generation: e.g. “Kontext” mode which allows combining text + image input to guide edits.
			* In creative workflows, concept art, renders, style transfer, etc.
			* Can be used as a base for fine-tuning (LoRA, etc.), or with low-bit quantization etc. to run on lower-VRAM hardware.

			<span id="how-to-install-run-flux-locally-cli-gui"></span>
			= How to install & run Flux locally (CLI + GUI) =

			<span id="graphical-user-interface"></span>
			== Graphical User Interface ==

			To do it, we need another software to manage the GUI, in this case we will use comfyUI. It works with a node-based workflow.

			<span id="installation"></span>
			=== Installation ===

			<ul>
			<li><p>Follow the guide for your OS: https://comfyui-wiki.com/en/install/install-comfyui</p>
			<syntaxhighlight># For Ubuntu:
			sudo apt install python3 python3-pip python3-venv
			python3 -m venv comfy-env
			source comfy-env/bin/activate

			pip install comfy-cli
			comfy --install-completion

			comfy install

			comfy --workspace=/path/to/your/workspace install
			#comfy --here install

			#GPU support for Nvidia
			pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu124
			#CPU support only
			pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cpu</syntaxhighlight></li>
			<li><p>Download Flux.1 dev here https://huggingface.co/black-forest-labs/FLUX.1-dev/tree/main. You need to signup and download file into local folder ~/comfyUI/models/difussion_models/. This will be the base model to use.</p></li>
			<li><p>Download VAE (used to learn and generate new data based on patterns and features from a given dataset) http://huggingface.co/stabilityai/sd-vae-ft-mse-original/blob/main/vae-ft-mse-840000-ema-pruned.safetensors and place it in models/vae</p></li>
			<li><p>Download CLIP Loader https://huggingface.co/comfyanonymous/flux_text_encoders/resolve/main/clip_l.safetensors and place it in models/text_encoders folder</p></li>
			<li><p>Download T5 https://huggingface.co/comfyanonymous/flux_text_encoders/resolve/main/t5xxl_fp16.safetensors and place it in models/text_encoders folder</p></li>
			<li><p>If you want to use a custom Model (checkpoint) or LoRA, you can download them from civitai.com</p></li></ul>

			<span id="launch-comfyui"></span>
			=== Launch comfyUI ===

			<syntaxhighlight>comfy launch</syntaxhighlight>
			<span id="load-template"></span>
			=== Load Template ===

			In the left side, there are multiple you can use.

			<span id="configure-workflow"></span>
			=== Configure workflow ===

			* for adding new nodes, double click on an empty space
	<!-- From bodyContent 45907992.mraw -->		<!-- From bodyContent 45907992.mraw -->

imported>Unknown user at 07:55, 16 September 2025

2025-09-16T07:55:26Z

New page