**Please, read the correspondent "About this version" for the model you download**My collection <a target="_blank" rel="ugc" href="https://civarchive.com/user/cbrescia/models?sort=Newest&amp;section=published">https://civarchive.com/user/cbrescia/models?sort=Newest&amp;section=published</a>Flux1-Hybrid: Blending Dev's Realism with Schnell's Speed and Improved Prompt AdherenceIntroduction:Introduce your new diffusion model, highlighting its unique combination of realism, speed, and prompt adherence. Emphasize the benefits of using this model compared to other popular options like Dev and Schnell. it is perfect for users with limited computational resources who want to generate high quality images quickly.Key Features:4-step generation: Produces high-quality images in a fraction of the time compared to many other models.Enhanced prompt adherence: Accurately captures the nuances of your prompts, resulting in more relevant and creative outputs.Photorealistic quality: Achieves a level of realism that rivals Dev, while maintaining the versatility of Schnell.CFG sensitivity: Provides fine-grained control over image generation through the CFG scale.Comparison with Other Models:Create a detailed comparison table:Feature Flux1-Hybrid Dev SchnellPrompt Adherence Excellent Very Good GoodRealism High Very High MediumVersatility High High HighEfficiency High (4 steps) Low MediumLighting Quality Very Good Excellent GoodDetail High Very High MediumArtistic Style Diverse Realistic ArtisticAnalysis:Prompt adherence: Our hybrid model consistently generates images that closely align with the provided prompts, outperforming Dev in this regard.Realism: While Dev excels in photorealism, our model offers a more balanced approach, combining realistic elements with artistic flair.Efficiency: The 4-step generation process makes our model significantly faster than Dev, without compromising on quality.Versatility: Our hybrid is capable of producing a wide range of styles, from photorealistic portraits to abstract art.Inference Time: Intel I5, 32 RAM, Nvidia 3060 12Gb, 45s (same settings, dev, 2m42s). tested with SwarmUI working on ComfyUI.Caveat: The time of generation of images is measured with the model preloaded. From the click on generate button until the image ends. The model first makes an initial image, which is then refined in 4 steps, the 4 steps last much less than the generation of the initial image.How to Use:Recommended settings: Random seed, CFG=1 (0.8-1.2) range, sampler: Euler, Scheduler: Normal/Simple, in the examples Resolution: 5:8 (768x1216).Clip,T5 encoders and vae are incorporated with Kijai Flux1-FP8. It´s recommended to use --lowvram interface flag to pass the handle of encoders to CPULimitations: the range of CFG for non distorted images is narrow. Realistic images are affected by CFG, abstract and landscapes not the same, so for images without humans, in dark images you can raise CFG, and for shinny ones you can lower it a bit more CFG (0.6-1.4). There´s no FluxGuidance as in dev model. Text is an issue to solve.Acknowledgements:Thank the teams: Express gratitude to the Black Forest Labs team for creating Flux1 and the ComfyUI community for their valuable insights.License: CC BY-NC 4.0, No commercialThe following photos contain each one a workflow to generate an image with Hybrid models, Baked and NoBaked versions, and save it in ComfyUI/Output directory. Just click and drag the image to the ComfyUI desktop to see the respective workflow.<a target="_blank" rel="ugc" href="https://cdrive.page.link/KcLFPz9evDfMHgWA7">https://cdrive.page.link/KcLFPz9evDfMHgWA7</a><a target="_blank" rel="ugc" href="https://cdrive.page.link/aTwDun5S6KLjt8Cu7">https://cdrive.page.link/aTwDun5S6KLjt8Cu7</a>FLUX.1 is a powerful tool, but the results may vary depending on the complexity of the prompt and the parameters used. Have fun experimenting and creating your own artwork!<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/41a37d79-a0e6-47f6-ad48-c8f8474f0998/width=525/41a37d79-a0e6-47f6-ad48-c8f8474f0998.jpeg" /><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/071a0da5-c08d-4411-a3f6-e707c31989e6/width=525/071a0da5-c08d-4411-a3f6-e707c31989e6.jpeg" />Up: Flux1 Dev, Down: Flux1 HybridPrompt: portrait photography of a alien supermodel, with glitter makeup.Seed:1826245848, Dev: 25 steps, Guidance 3.5, CFG 1, Sampler Euler, Scheduler Normal/Simple, Hybrid: 4 steps, CFG 1, Sampler Euler, Scheduler Normal/Simple<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/ad3a1433-a75e-45bd-bbb2-50e34754dc13/width=525/ad3a1433-a75e-45bd-bbb2-50e34754dc13.jpeg" /><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/cf5fcac2-e0f2-4806-a399-046221a49ac9/width=525/cf5fcac2-e0f2-4806-a399-046221a49ac9.jpeg" />Up. flux1 Dev. Down: HybridPrompt: Devil woman wearing headphones, in the style of mysterious abstractions, double exposure, bathed in vibrant neon colors. Face illuminated by a kaleidoscope of electric hues - cyan, magenta, yellow, and emerald green. Striking contrast between cool blues and warm oranges across the features. Iridescent, glitter-like particles scattered over the skin, creating a cosmic effect. Piercing eyes with multicolored reflectionsSeed:1959765719 Dev: 25 steps, Guidance 3.5, CFG 1 Sampler Euler, Scheduler Normal/Simple, Hybrid: 4 steps, CFG 1, Sampler Euler, Scheduler Normal/Simple<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/d48b5be1-6bed-4a2e-a695-e05e71f6fe63/width=525/d48b5be1-6bed-4a2e-a695-e05e71f6fe63.jpeg" /><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/80d85b4c-bff2-4dd9-9e2b-077997e4da40/width=525/80d85b4c-bff2-4dd9-9e2b-077997e4da40.jpeg" />UP: Flux1 Dev Down: Flux1 Hybridprompt: (1girl, pale white skinny 18 year old redhead nurse, white nurse outfit, short skirt,white stockings deep cleavage, very big juicy ass and wide hips, blue eyes, thick thighs, very very big natural milky jiggly breasts. curvy milf body, wavy black and red hair, pawg, fat ass, huge ass, cleavage, massive tits, huge breasts, detailed face, heavy breasts, horny face, mssv breasts), hospital, playfull, posing, horny look, bubble butt, posing for a photo,photorealistic, 8k uhd natural lighting, raw, rich, intricate details, key visual, atmospheric lighting, 35mm photograph, film, bokeh, professional, 4k, highly detailed, cinematic, colorful hospital background, 8k, dramatic lighting, highly detailed, hyper realistic, intricate, intricate sharp details,realistic, high resolution,Seed: 1176787681 Dev: 25 steps, Guidance, 3.5 CFG 1, Sampler Euler, Scheduler Normal/Simple, Hybrid: 4 steps, CFG 1, Sampler Euler, Scheduler Normal/Simple<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/169d6aa8-2678-4d98-83b9-da179cae6e98/width=525/169d6aa8-2678-4d98-83b9-da179cae6e98.jpeg" /><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/eceb2fbc-d57e-4d7e-b32c-0e4708e0d5e3/width=525/eceb2fbc-d57e-4d7e-b32c-0e4708e0d5e3.jpeg" />UP: Flux1 Dev Down: Flux1 Hybridprompt: eye catching, Bombshell beauty, Honey wild hair,Silky long legs high heels Swedish Lounge Spunky LeatherPortrait of beauty Elegant lady in sheer dress and vintage clothing,Bone corsetSeed: 726579420 Dev: 25 steps, Guidance 3.5 CFG 1, Sampler Euler, Scheduler Normal/Simple, Hybrid: 4 steps, CFG 1, Sampler Euler, Scheduler Normal/SimpleDev is excelent doing images of thin models women at the price of prompt adherence.

Flux1-Dev FP8&NF4&GGUF 6 steps, Hybrid 4 steps : SVDQ-int4-Flux.1-Dev : Flux1-Dev-NVFP4 + LORA models

This version is a 4 bit quantization with NF4 of the 8 bit FP8 NSFW2, for those with little amount of VRAM. All the usage mode indications of NSFW1 are applicable to this oneModes of use:<ul><li>Forge: in this interface either the UNet model or the Checkpoint, both are placed in the directory ../model/StableDiffusion</li><li>ComfyUI and SwarmUI: in both the Baked Checkpoint goes to .. /models/StableDiffusion and the Nobaked Unet model goes to .. /models/Unet</li></ul>Then with the Manager of Workflows ComfyUI you have to install nodes in Custom_nodes provided in, <a target="_blank" rel="ugc" href="https://github.com/DenkingOfficial/ComfyUI_UNet_bitsandbytes_NF4">https://github.com/DenkingOfficial/ComfyUI_UNet_bitsandbytes_NF4</a> (the model I made is type flux1-dev-bnb-nf4-v2-unet) and also install the nodes provided in <a target="_blank" rel="ugc" href="https://github.com/comfyanonymous/ComfyUI_bitsandbytes_NF4">https://github.com/comfyanonymous/ComfyUI_bitsandbytes_NF4</a>Use the URL option in manager and get the git file in the green "Code" button, they are <a target="_blank" rel="ugc" href="https://github.com/DenkingOfficial/ComfyUI_UNet_bitsandbytes_NF4.git">https://github.com/DenkingOfficial/ComfyUI_UNet_bitsandbytes_NF4.git</a> in Unet and <a target="_blank" rel="ugc" href="https://github.com/comfyanonymous/ComfyUI_bitsandbytes_NF4.git">https://github.com/comfyanonymous/ComfyUI_bitsandbytes_NF4.git</a> in ComfyUI_bitsandbytesIt´s a one time operation<ul><li>All the examples use CFG 1, steps 6, Sampler: Euler, Scheduler: Normal, Flux Guidance 3.5</li></ul>If you are very short of VRAM, in ComfyUI and Forge you can use the NoBaked version witht5-v1_1-xxl-encoder-Q3_K_M.gguf and ViT-L-14-TEXT-detail-improved-hiT-GmP-TE-only-HF.safetensors, for a total of 9.5 Gb of VRAM, 2.5 Gb less than the Baked version<a target="_blank" rel="ugc" href="https://huggingface.co/city96/t5-v1_1-xxl-encoder-gguf/blob/main/t5-v1_1-xxl-encoder-Q3_K_M.gguf">https://huggingface.co/city96/t5-v1_1-xxl-encoder-gguf/blob/main/t5-v1_1-xxl-encoder-Q3_K_M.gguf</a><a target="_blank" rel="ugc" href="https://huggingface.co/zer0int/CLIP-GmP-ViT-L-14/blob/main/ViT-L-14-TEXT-detail-improved-hiT-GmP-TE-only-HF.safetensors">https://huggingface.co/zer0int/CLIP-GmP-ViT-L-14/blob/main/ViT-L-14-TEXT-detail-improved-hiT-GmP-TE-only-HF.safetensors</a><ul><li>In ComfyUi you must add a custom node to use the node DualClipLoader(GGUF) with <a target="_blank" rel="ugc" href="https://github.com/city96/ComfyUI-GGUF.git">https://github.com/city96/ComfyUI-GGUF.git</a> in <a target="_blank" rel="ugc" href="https://github.com/city96/ComfyUI-GGUF">https://github.com/city96/ComfyUI-GGUF</a></li></ul><ul><li>In Forge just download the two files in the ../model/clip directory. Refresh the page and the files appear in the VAE-Clip dropdown list to select</li></ul>

Files with SHA256: 41175e579b6dcaf2ad5d53a51792817a997075b8cac79775f37b3fa23be34b00