Please check out the <a rel="ugc" href="https://education.civitai.com/quickstart-guide-to-flux-1">Quickstart Guide to Flux </a>for all the info you need to get started!<code>FLUX.1 [dev]</code> is a 12 billion parameter rectified flow transformer capable of generating images from text descriptions. For more information, please read our <a target="_blank" rel="ugc" href="https://blackforestlabs.ai/announcing-black-forest-labs/">blog post</a>.<h1 id="key-features-325mmh6sm">Key Features</h1><ol><li>Cutting-edge output quality, second only to our state-of-the-art model <code>FLUX.1 [pro]</code>.</li><li>Competitive prompt following, matching the performance of closed source alternatives .</li><li>Trained using guidance distillation, making <code>FLUX.1 [dev]</code> more efficient.</li><li>Open weights to drive new scientific research, and empower artists to develop innovative workflows.</li><li>Generated outputs can be used for personal, scientific, and commercial purposes as described in the <a target="_blank" rel="ugc" href="https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/licence.md">flux-1-dev-non-commercial-license</a>.</li></ol><h1 id="usage-y9h8q18hm">Usage</h1>We provide a reference implementation of <code>FLUX.1 [dev]</code>, as well as sampling code, in a dedicated <a target="_blank" rel="ugc" href="https://github.com/black-forest-labs/flux">github repository</a>. Developers and creatives looking to build on top of <code>FLUX.1 [dev]</code> are encouraged to use this as a starting point. Learn More Here: <a target="_blank" rel="ugc" href="https://huggingface.co/black-forest-labs/FLUX.1-dev">https://huggingface.co/black-forest-labs/FLUX.1-dev</a>

FLUX

flux_dev.safetensors

Anime art

Krea Dev

Pro 1.1 Ultra

Pro 1.1

Pro (Legacy)

Schnell

I compiled a little collection of flux.1 models. there are fp8 models with fp8 t5 and fp8 models with fp16 t5 for both dev and schnell. Single files for use with the regular checkpoint loader. there are also fp16 models available now. all models have clip, t5, and vae baked in. THESE ARE ALL STOCK FLUX.1Forr flux kontext, see here <a target="_blank" rel="ugc" href="https://civarchive.com/articles/16348/flux1-kontext-dev-quantized-models-available">https://civarchive.com/articles/16348/flux1-kontext-dev-quantized-models-available</a>`These all use bf16 upcasting, use the appropriate flags if you are tuning on gtx cards for some reason.`Unified single file versions of flux.1 for comfyui. All files have a baked in VAE and clip L included:flux.1_dev_8x8_e4m3fn-marduk191.safetensors is Flux.1 Dev quantized to 8 bit with an 8 bit T5 XXL encoder included.flux.1_dev_fp8_fp16t5-marduk191.safetensors is Flux.1 Dev quantized to 8 bit with an 16 bit T5 XXL encoder included.flux.1_schnell_8x8_e4m3fn-marduk191.safetensors is Flux.1 Schnell quantized to 8 bit with an 8 bit T5 XXL encoder included.flux.1_schnell_fp8_fp16t5-marduk191.safetensors is Flux.1 Schnell quantized to 8 bit with an 16 bit T5 XXL encoder included.flux.1_dev_16x16-marduk191.safetensors Flux.1 Dev quantized to 16 bit with an 16 bit T5 XXL encoder included.flux.1_schnell_16x16-marduk191.safetensors Flux.1 Schnell quantized to 16 bit with an 16 bit T5 XXL encoder included.flux.1_dev_8x8_scaled-marduk191.safetensors is Flux.1 Dev quantized to 8 bit scaled stochastic weights and normalized outlaying alphas. It uses an 8 bit scale dstochastic (tag limited to avoid loss) T5 XXL encoder included.Workflow examples are available here: SOONRepository is here: <a target="_blank" rel="ugc" href="https://huggingface.co/marduk191/Flux.1_collection/tree/main">https://huggingface.co/marduk191/Flux.1_collection/tree/main</a>Discord: <a target="_blank" rel="ugc" href="https://discord.gg/s3kj9VqpKc">https://discord.gg/s3kj9VqpKc</a>Tips welcome: <a target="_blank" rel="ugc" href="https://ko-fi.com/marduk191">https://ko-fi.com/marduk191</a>

Files with SHA256: 2eda627c8aee140edc77e28ed8dd3c662928ae60f0f960f36824f8862dcbb713