Type | |
Stats | 11,729 |
Reviews | (1,113) |
Published | Oct 25, 2024 |
Base Model | |
Training | Steps: 382,000 |
Hash | AutoV2 A34D7B4F23 |
PixelWave Flux.1-dev 03 fine tuned!
Safetensor Files: 💾BF16 💾FP8 💾NF4
GGUF Files: 💾Q8_0 🤗Q6_K 💾Q4_K_M
The 'diffusers' files are actually the Q8_0 and Q4_K_M GGUF versions. GGUF files also available on huggingface.
I fine tuned version 03 from base FLUX.1-dev for over 5 weeks on my 4090. It is able to do different art styles, photography, and anime. Trick I discovered to help with LoRAs.
I used dpmpp 2m sgm uniform 30 steps for the showcase images. If you want a neater/cleaner output, try increasing the guidance. Also mentioning a style can help, so the model doesn't have to guess.
I also recommend try adding the upscale latent by node, and scale the latent by 1.5, e.g. generating an image that is 1536x1536 instead of 1024x1024.
PixelWave Flux.1-schnell 03
GGUF Files: go to huggingface
I used dpmpp 2m sgm uniform 8 steps for the showcase images.
You can start with 4 steps, but there are less errors with anatomy if you run with more steps.
PixelWave Flux.1-dev 02
GGUF Files: 💾Q8_0 🤗Q6_K 💾Q4_K_M
Version 02 has greatly improved black and dark images, and more reliable outputs with fewer issues with hands.
I recommend using dpmpp_2s_ancestral, beta, 14 steps. Or euler, simple, 20 steps.
PixelWave 11 SDXL. A general purpose fine tuned model. Great for art and photo styles.
I use 20 steps, DPM++ SDE, CFG 4 to 6 or 40 steps, 2M SDE Karras
Accelerated Version - 5+ Steps, DPM++ SDE Karras, 2.5 CFG
PAG Recommended⚡Recommend 1.5 Scale, with CFG 3. Link to workflow
⭐Link to prompting guide.⭐ You don't need to use 'quality' terms such as 4K, 8K, masterpiece, high def, high quality, etc. Unless you want it, I recommend not using words such as 'vibrant, intense, bright, high contrast, neon, dramatic' for photographic styles if you a wanting a more natural look. This can cause images to look 'overcooked', but it's just the CLIP following your prompt. 🙂 If you do want vibrant, neon photos PixelWave will provide!
The focus for version 10 was to train the CLIP models, which improves the reliability, ensures you can produce a wide variety of styles, and better at following prompts.
Thanks to my friends who helped test: masslevel, blink, socalguitarist, klinter, wizard whitebeard.
Guide: Upscaling Prompts with LM Studio and Mikey Nodes
Guide: Add more details to your image using the skip step method
No need for the refiner model.
This model is not a mix of other models.
I also created Mikey Nodes which contains a lot of useful nodes. You can install it through comfy manager.
🌟 Support My Work 🌟
If you've enjoyed my work on PixelWave and want to show your support, I have a slightly different request. Instead of monetary contributions, I ask for kindness and positivity:
Be Kind to Each Other and Yourself: A little kindness goes a long way. Treat yourself and those around you with compassion and understanding.
Donate to Your Favorite Charity: If you're able, consider donating to a charity that resonates with you. Your generosity can make a real difference in someone's life.
Call Your Parents (or a Loved One): Take a moment to reach out to your parents, a family member, or a close friend. A simple call can brighten someone's day.
Tell Your Partner or a Friend You Love Them: Remind the special people in your life how much they mean to you.
Your actions, big or small, can create ripples of positivity. Let's make the world a better place, one kind gesture at a time. Thank you for your support! I hope you have a wonderful day! 💖