<h3 id="presetmodel-for-promptless-generation">Presetmodel for Promptless Generation</h3>Portrait Model (portrait/photography/facial/closeup)Portrait Release. With this Model wired to Preset Workflow, you can influence randomly generated Characters with selected Attributes. Create without LoRA´s. Just out of Base. Its a Model working with 30 Prompts/Vectors handwritten and used Ollama API inside ComfyUI (Qwen) .Category: Portrait/CharacterModel standallone is SFW. Mux/Merge with what ever you want. It will shown up. But ever set this Model at first Place in Muxing-Pipe. Otherwise you get freaky melted.....anything.Results depending on the used Basemodel from Krea2 Familiy. Have Fun with that, and success while discover the Posibillities. Workflows are inside the Images below.<span style="background-color:rgb(26, 27, 30);color:rgb(141, 141, 143);font-family:-apple-system, BlinkMacSystemFont, &quot;Segoe UI&quot;, Roboto, Helvetica, Arial, sans-serif, &quot;Apple Color Emoji&quot;, &quot;Segoe UI Emoji&quot;;font-size:16px">Best you merge (mux) this Preset with last (negative) Loadernode to influence. Try different Searchterms like: /brown eyes/black hair/colorful hair/piercing/smokey eyes/amber hair/... or use direct dial via Entry Nr.<span style="background-color:rgb(26, 27, 30);color:rgb(141, 141, 143);font-family:-apple-system, BlinkMacSystemFont, &quot;Segoe UI&quot;, Roboto, Helvetica, Arial, sans-serif, &quot;Apple Color Emoji&quot;, &quot;Segoe UI Emoji&quot;;font-size:16px">Set neg_influence to Searchterm or let randomize self. (descripted in Workflow)NOTE : This Model can only used with my Workflow and the special Customnodes in ComfyUI. It is a transformed Promptcollection, what makes it possible to shorten Pipeline and Generatingtimes.With this System, i aimed to change the Generatingprocess in a different Way. Mainly Prompts can merged or selected by view on Results. Basemodel are all Krea2 Versions and its weights. This is the first Stage and like i told - experimental. Generating Outputs, you can see on my Profile.Instructions to use, you find on my Article Generatingguide krea2. Including the Workflow and the needed Customnodes.Drop Model in Path: ...\ComfyUI_windows_portable\preset_storageInstructions you find: <a target="_blank" rel="ugc" href="https://civarchive.com/articles/33385/krea2-beyond-prompts-a-modular-preset-architecture-for-generative-image-pipelines">here</a>and the latest Version: <a target="_blank" rel="ugc" href="https://civarchive.com/articles/33906/krea2-deterministic-preset-muxing-v10-nsfw">Deterministic Promptless Generationv1.0</a>From now on, you can Record and reuse your Muxing Gen´s.Note: Samples (Images) are generated with my new Dev-workflow. You can use it, but need to ctrl/b blind out missing nodes. (Ollama API Node - not released jet.) If you wanna learn more about, take here a look around and com your suggestions: <a target="_blank" rel="ugc" href="https://civarchive.com/articles/34174/announcement-krea2-full-ai-workflow">Development Stage 2</a>Be a Part of that. &lt;3

Files with SHA256: 5ed43def28ea7715a80c7fb18183d1b193fa2d3f167efc0a14c60b7d6dfa4d6f