V4.0-Full Version:
V4.0 模型(纯净基础模型)，是在 V3.0 的基础上，融合了 SRPO 模型的写实与细腻，Krea 模型的艺术性与多风格，以及良好的质感与LoRA兼容性，模型的综合能力有较大提升。
非常的真实与细腻，即使 TTP 直接放大至 8M 像素，依然能保持极好的细节。
提示词还原能力较大提升，推荐使用 LLM 强化和详细描述的结构化提示词。
良好的艺术表现力和风格多样性，良好的 LoRA 兼容性，包括 NSFW / SFW 各种 LoRAs。
The V4.0 model(Pure base model), built on the foundation of V3.0, integrates the realism and delicacy of the SRPO model, the artistry and multi-style capabilities of the Krea model, as well as good texture and LoRA compatibility, resulting in a significant improvement in the model's overall capabilities.
Extremely realistic and delicate, maintaining excellent details even when TTP is directly enlarged to 8M pixels.
Greatly improved prompt restoration capability, it is recommended to use LLM-enhanced or structured prompts.
Good artistic expression and style diversity, good LoRA compatibility, include all kind NSFW / SFW LoRAs.
Also on: Huggingface.co, Modelscope
===========================================================================
V3.0-Krea Version:
Flux.1-Dev-Krea 模型改善了 Dev 模型的艺术风格与写实摄影的能力，但人像的清晰度和美学方面有所减弱，特别是与原 Dev 模型训练的 Lora 兼容性很差。本 V3.0-Krea 保留了 Krea 模型的主要长处，改善了图像清晰度及与原 Dev 模型 Lora 的兼容性，但 Lora 兼容性方面改善不多(主要指人像和风格LoRA，其它LoRA及CN还行)，不太理想，这是该版本比较遗憾的地方，请大家慎重下载。
Flux.1-Dev-Krea has improved the artistic style and realistic photography ability of the Dev version model, but the clarity and aesthetics of portraits have weakened, especially with poor compatibility with Lora trained on the original Dev model. The V3.0-Krea retains the main features of the Krea model, improves image clarity, and enhances compatibility with the Lora, but the Lora compatibility is improved minimal and not ideal(Mainly refers to portrait and style LoRA, other LoRA and CN are acceptable), which is a disappointing aspect of this version. Please download cautiously.
推荐使用 GNER-T5-XXL 代替 T5-XXL，获得更好的提示词理解能力，你可以从 https://civarchive.com/models/1888454 下载，或我的 HF Repo 下载。
Recommended to use GNER-T5-XXL instead of T5-XXL for better prompt understanding capabilities, you can download it from https://civarchive.com/models/1888454 or my HF Repo.
一些示例图片 (Some example image) :
模型使用：
基本组合：deis+simple / euler+beta，您可以尝试不同的组合。
Basic: deis+simple / euler+beta, You can try more different combinations.
Also on Huggingface.co
===========================================================================
V3.0-PAP Version:
v3.0-PAP：人像与艺术摄影出图优化基础模型。模型在构图、光影以及东方人脸型等方面进行了专门优化，进一步加强脸模的敏感性、适配性。
与 Dev 原版模型相比，该版本在人种和脸型方面更真实、更丰富，脸模的例图来自以下作者的 LoRA 模型，在此表示感谢！如有侵权，知会立删。
Portrait and Art Photography Optimization Base Model. The model has been specially optimized in composition, light and shadow, oriental face shape to further strengthen the sensitivity and adaptability of the face model.
Compared to the Flux.1 Dev original model, this version is more realistic and richer in terms of ethnicity and face shape, and the example drawings of the face model are from the LoRA model of the following authors, thanks in advance! If there is any infringement, it will be notified and deleted immediately.
https://civarchive.com/user/el_fluppe
https://civarchive.com/user/wolfcatz
https://civarchive.com/user/seanwang1221
https://civarchive.com/user/nawusijia
模型使用简单指南：
基本构图：deis+simple / euler+beta; 噪点更多：ddim/dpm_2/dpmpp_2+beta/beta57/sgm_uniform; 细节更丰富、更具想象力：heunpp2+ddim_uniform; 放大：UltimateSDUpscale/TTP; 胶片效果：添加 lut(35mm/AGAF/Kodak); 或者基于您自己环境的最佳测试组合。steps 20-30。工作流参见例图。
Basic: deis+simple / euler+beta; More noise: ddim/dpm_2/dpmpp_2+beta/beta57/sgm_uniform; More detail, more imaginative: heunpp2+ddim_uniform; Upscaler: UltimateSDUpscale/TTP; Film effects: add LUT (35mm/AGAF/Kodak); Or the best combination of tests based on your own environment. steps 20-30。 The workflow is shown in the example POST image.
Also on Huggingface.co
一个有趣的脸模控制测试示例 (An interesting face model LoRA control sample)：
===========================================================================
DedistilledMixTuned Dev V3.0:
中国农历蛇年钜献! (Great upgrade for Chinese Snake Year!)
V3.0 版模型全面升级，可能是目前 Flux Dev 微调模型中，模型能力最均衡，LoRA 兼容性、真实感、出图质量和艺术创作力最接近 Flux Pro 的模型。(为了方便评测对比，本模型的Seed与原Dev模型基本对齐)
Fully upgraded Version 3.0, it may be the best model in the current Flux Dev fine-tuning models. Have the very good balance in model capabilities, LoRA compatibility, realism, image quality and artistic creativity closest to the Flux Pro model. (For evaluation and comparison, the seeds of this model are basically aligned with the original Dev model)
V3.0 版模型使用指南：
模型通过分层融合技术，去除反蒸馏干扰，与原版 Flux.1 Dev 模型完全兼容，具有更高的 LoRA 权重敏感性。1024x1024 分斌率以下，建议 euler/deis + normal/beta/simple 等，1024 - 2048 大分斌率图像，建议 ddim/dpm_2/dpmpp_2m/heunpp2 + ddim_uniform/beta.
细节最强：dpmpp_2m+beta，艺术性最好：heunpp2+ddim_uniform
建议：KSampler, 20-30步。工作流请参见图：https://civarchive.com/images/53432419
The model is fully compatible with the original Flux.1 Dev. Had removed the de-distillation interference, and has a higher sensitivity to LoRA weights. For 1024x1024 and below, euler/deis + normal/beta/simple, etc., 1024 - 2048 for large binning images, ddim/dpm_2/dpmpp_2m/heunpp2 + ddim_uniform/beta.
More details: dpmpp_2m + beta, More artistry: heunpp2 + ddim_uniform
Recommended: KSampler, steps 20-30. Workflow of the model pls ref: https://civarchive.com/images/53432419
===========================================================================
DedistilledMixTuned Dev V2.0:
2025 新年献礼！经过一个多月打造，在 v1.0 基础上全新升级 V2.0 版本，以照片级的真实感，在细节体现、出图速度、LoRA兼容性、光影和谐度等方面达到一个新的平衡。
2025 New Year Gift! More than a month of training and fine-tuning, The V2.0 version has been upgraded based on v1.0, and has reached a better balance in detail reflection, drawing speed, LoRA compatibility, light and shadow harmony with photorealistic realism.
===========================================================================
DedistilledMixTuned Schnell V1.0:
可能是目前基于 Flux.1 Schnell 调制的各种模型中，快速出图(4-8步)，遵循原版 Flux Schnell 构图风格，提示词还原能力强，且在出图质量、出图细节、回归真实和风格多样化方面取得最佳平衡的开源可商用 Schnell 基础模型。
Only 4 step, The Model may achieve to the best balance in terms of image quality, details, reality, and style diversity compare with other tuned of Flux.1 Schnell. and have a good ability of prompt following, good of the original Flux model style following.
Based on FLUX.1-schnell, Merge of LibreFLUX, finetuned by ComfyUI, Block_Patcher_ComfyUI, ComfyUI_essentials and other tools. Recommended 4-8 steps, usually step 4 is OK. Greatly improved quality and reality compare to other Flux.1 Schnell model.
===========================================================================
DedistilledMixTuned Dev V1.0:
可能是目前快速出图(10步以内)的 Flux 微调模型中，遵循原版 Flux.1 Dev 风格，提示词还原能力强、出图质量最好、出图细节超越 Flux.1 Dev 模型，最接近 Flux.1 Pro 的基础模型。
May be the Best Quality Step 6-10 Model, In some details, it surpasses the Flux.1 Dev model and approaches the Flux.1 Pro model. and have good ability of prompt following, good of the original Flux.1 Dev style following.
Based on Flux-Fusion-V2, Merge of flux-dev-de-distill, finetuned by ComfyUI, Block_Patcher_ComfyUI, ComfyUI_essentials and other tools. Recommended 6-10 steps. Greatly improved quality compared to other Flux.1 model.
GGUF Q8_0 / Q5_1 /Q4_1 量化版本模型文件，经过测试，已同步提供，将不会再提供别的量化版本，如有需要，朋友们可根据下面提示信息，自己下载 fp8 后进行量化。
GGUF Q8_0 / Q5_1 /Q4_1 quantized model file, had tested, and uploaded the same time, over-quantization will lose the advantages of this high-speed and high-precision model, so no other quantization will be provided, you can download the FP8 model file and quantizate it according to the following tips.
===========================================================================
Recommend:
UNET versions (Model only) need Text Encoders and VAE, I recommend use below CLIP and Text Encoder model, will get better prompt guidance:
Text Encoders: https://huggingface.co/silveroxides/CLIP-Collection/blob/main/t5xxl_flan_latest-fp8_e4m3fn.safetensors
VAE: https://huggingface.co/black-forest-labs/FLUX.1-schnell/tree/main/vae
GGUF Version: you need install GGUF model support nodes, https://github.com/city96/ComfyUI-GGUF
Simple workflow: a very simple workflow as below, needn't any other comfy custom nodes(For GGUF version, please use UNET Loader(GGUF) node of city96's):
===========================================================================
洗去蒸馏油腻，回归模型本真，致力打造最纯正的 Flux 优质底模！
Wash away the distillation and return to the original basic.
如果您使用后觉得模型不错，请多多返图，谢谢！
If you feel the model is good for you, please post the image here, thanks a lot!
Thanks for:
https://huggingface.co/black-forest-labs/FLUX.1-dev, A very good open source T2I model. under the FLUX.1 [dev] Non-Commercial License.
https://huggingface.co/black-forest-labs/FLUX.1-schnell, A very good open source T2I model, under the apache-2.0 licence.
https://huggingface.co/Anibaaal, Flux-Fusion is a very good mix and tuned model.
https://huggingface.co/nyanko7, Flux-dev-de-distill is a great experimental project! thanks for the inference.py scripts.
https://huggingface.co/jimmycarter/LibreFLUX, A free, de-distilled FLUX model, is an Apache 2.0 version of FLUX.1-schnell.
https://huggingface.co/MonsterMMORPG, Furkan share a lot of Flux.1 model testing and tuning courses, some special test for the de-distill model.
https://github.com/cubiq/Block_Patcher_ComfyUI, cubiq's Flux blocks patcher sampler let me do a lot of test to know how the Flux.1 block parameter value change the image gerentrating. His ComfyUI_essentials have a FluxBlocksBuster node, let me can adjust the blocks value easy. that is a great work!
https://huggingface.co/twodgirl, Share the model quantization script and the test dataset.
https://huggingface.co/John6666, Share the model convert script and the model collections.
https://github.com/city96/ComfyUI-GGUF, Native support GGUF Quantization Model.
https://github.com/leejet/stable-diffusion.cpp, Provider pure C/C++ GGUF model convert scripts.
Attn: For easy convert to GGUF Q5/Q4, you can use https://github.com/ruSauron/to-gguf-bat script, download it and put to the same directory with sd.exe file, then just pull my fp8.safetensors model file to bat file in exploer, will pop a CMD windows, and follow the menu to conver the one you want.
LICENSE
The weights fall under the FLUX.1 [dev] Non-Commercial License.
Description
FAQ
Comments (25)
v1-fp8-schnell有什么不同吗？
v1-fp8-schnell 是基于 Schnell 进行反蒸馏调制的，可商用。而 v1.0 fp8 是基于 dev 的，不可商用。
Man, I gotta say, your fp8 model is BY FAAAAAR, the best one out there, the quality is best in the category, and the speed at 10 steps really good. The acuracy reading LORAS in particular is oustanding. You should be proud of yourself! Bravo and thank you lots! Hope you keep improving it over time man
Thanks a lot! any problem pls feedback me.
@wikeeyang The biggest problem I've been noticing so far is that the model is very good at portraying hands, but very bad at feet. In a full body scope it works fine with both hands and feet as long as the model is walking or standing, but in a more close image, a sitting or laying pose, feet are as bad or worse than in SDXL and SD models, wich seems weird for FLUX. I guess is a matter of the type of images in the database, not sure if you can focus some of the future updates on it. Anyway, still a top of the line checkpoint on everything else. =)
@JCriterio Thanks for the feedback! Flux has a high error rate in the hands(finger) and feet, so I'll try to optimize it as much as possible in the next step, and you can also try some LoRA for the hands or feet to see if it can improve the quality of image.
@wikeeyang No problem, thanks for answering. For my testing the problem seems to be that the database doesn't have almost any training with "prone" positions of the body, and not-standing backside images in general. It will give you the front of the body or the head when the model is lying face down or prone. And for the same reason, I think, it will try to represent the top of the feet and toes where the sole and bottom of the toes should be. It works well representing the backside of a person in general, feet included, when the person is standing or walking, but everything else seems to be severely lacking. I hope this is helpful.
@JCriterio Thanks!
您好,请问该模型是否能正常使用黑森林官方的depth和canny的LoRa以及redux模型?
我自己用起来似乎效果差,不知道是哪儿的问题,所以来问问
效果不会好，最好是使用黑森林合并打包的版本，那是原厂调优的底模合并的，LoRA 就算是用原厂的 Dev 模型，效果也差一些。
在大家关注FLUX DEV模型的同时，也希望更多的人一起来提升Schnell的可用性。Libre FLUX帮我们开了个好头，大杨老师的不懈坚持让一个可用版本的Schnell得以出现！While everyone is paying attention to the FLUX DEV model, we also hope that more people can work together to improve the usability of Schnell. Libre FLUX has given us a good start, and professor Wikee Yang's relentless persistence has enabled a usable version of Schnell to appear! Thank you.
谢谢！大家一起努力！Thanks! Let's go better together!
Does this model accept negative prompts like other de-distilled models?
Sure, if your sampler node have para can accept it, but I not sure the effective, you can try it in ComfyUI or Forge WebUI, also you can try LoRA and any other function like normal Flux model.
@wikeeyang After testing, no. This model allows input of negative prompts but it effectively ignores them.
@thebollo Thanks for the feedback, then seems the model more like normal Dev model.
Any chance we get an FP16 release? Would be greatly appreciated! Thanks for your hardwork!
I'm so sorry, I tried a few times, gave up, It was too hard for me, with huge files to be transferred and through the network blocking. And the FP8 image quality is good enough, and it can also be trained, so I really don't plan to upload FP16, so sorry again.
@wikeeyang Hello, it's understandable FP16 being big, however would you be able to up quantized versions of FP16 ? The benefit of quants is to start from a higher quality model, going from FP8 to Q8 yeilds very little benefits in both size and quality.
Great work！Could you please tell me the details of the de-distillation of the fp8-schnell model? Also, is this model integrated with dev after de-distillation, that it can achieve better performance?
Schnell's de-distilled model is "LibreFLUX", pls refer the https://huggingface.co/jimmycarter/LibreFLUX to find more details introduce. about merge with Dev model, I think you can find a lot of experiment in Huggingface. As for performance, I think Schnell is good enough, Dev is better in the details.