FLUX + Hyper Lora 8 Steps + LLM + Detailing + Inpainting + Upscaling + Low Vram
4.5
2 reviewsDescription
Made with Hyper Flux 8steps and Flux Dev Q4_0.GGUF. The main goal is to use FLUX with 8GB VRAM (my own configuration).
Multiple functions in the workflow are controlled by a switch in Group 0 (the black one).
1- Inpainting: it offers three options: (SAM Detector + Custom Mask or Only Custom Mask or Mask Uploaded)
2- Prompt Generation: A prompt can be generated either through text or an image via a LLM.
3- 1st Detailing: it is performed with FLUX.
4- Upscaling: it is done using the Tile Diffusion Node, SDXL Lightning, and CN SDXL Tile. It operates quickly and produces stunning results.
5- 2nd Detailing: a second pass is done with SDXL/FLUX for the background and the main subject.
6- Post-Processing: a final step of post-processing is done to adjust brightness, contrast, etc.
Make sure to download the exact models shown in the workflow. I selected them specifically to work with my 8GB VRAM card.
Models:
- flux1-dev-Q4_0.gguf
- Hyper-FLUX.1-dev-8steps-lora.safetensors
- t5xxl_fp8_e4m3fn.safetensors
- 4xLeexicaDat2_otf.pth
- 4x-UltraSharp.pth
- 4xFaceUpDAT.pth
- dreamshaperXL_lightningDPMSDE.safetensors
- ttplanetSDXLControlnet_v20Fp16.safetensors
Please, note the package required for Ollama is ComfyUI Ollama by stavsap.
ComfyUi-Ollama-YN is not required and create conflict with the Ollama nodes.
Discussion
(No comments yet)
Loading...
Reviews
No reviews yet
Versions (9)
- latest (25 days ago)
- v20240906-192820
- v20240906-143347
- v20240906-143311
- v20240906-133947
- v20240905-182824
- v20240905-182316
- v20240905-151019
- v20240903-003347
Node Details
Primitive Nodes (131)
Any Switch (rgthree)
BooleanBasic
DF_Get_image_size
Display Int (rgthree)
DownloadAndLoadFlorence2Model
DownloadAndLoadSAM2Model
EmptySD3LatentImage
Fast Groups Muter (rgthree)
Florence2Run
Florence2toCoordinates
FluxGuidance
FluxSampler
GetNode
Image Comparer (rgthree)
LayerColor: AutoAdjustV2
ModelSamplingFlux
Note
PrimitiveNode
Sam2Segmentation
Seed (rgthree)
SetNode
UnetLoaderGGUF
workflow/Checkpoint
workflow/Detailer_Settings
workflow/Settings
workflow/Simple_Background
workflow/Simple_Object
workflow/Tiles_Background
workflow/Tiles_Object
workflow/cn_background-strength
workflow/cn_subject_strength
Custom Nodes (115)
- CR Text
ComfyUI
- InpaintModelConditioning
- ImageUpscaleWithModel
- ConditioningZeroOut
- BasicGuider
- PreviewImage
- LoadImageMask
- SamplerCustomAdvanced
- BasicScheduler
- KSamplerSelect
- VAEDecode
- InvertMask
- LoraLoaderModelOnly
- UpscaleModelLoader
- DualCLIPLoader
- CLIPTextEncode
- VAELoader
- RandomNoise
- SaveImage
- GrowMask
- LoadImage
- ImageScaleBy
- DifferentialDiffusion
- CheckpointLoaderSimple
- VAEDecodeTiled
- VAEEncodeTiled
- ImageScale
- ControlNetApplyAdvanced
- ImageBlend
- MaskPreview+
- GetImageSize+
- AddMask
- PreviewBridge
- ImpactSwitch
- ImpactControlBridge
- ImpactGaussianBlurMask
- ImpactSchedulerAdapter
- SEGSPreview
- DetailerForEach
- KSampler //Inspire
- LayerColor: Levels
- LayerUtility: PurgeVRAM
- OllamaVision
- OllamaGenerateAdvance
- ControlNetLoaderAdvanced
- TTPlanet_TileSimple_Preprocessor
- ImageAndMaskPreview
- ColorMatch
- ShowText|pysssss
- MathExpression|pysssss
- Checkpoint Selector
- VAEDecodeTiled_TiledDiffusion
- VAEEncodeTiled_TiledDiffusion
- TiledDiffusion
- Image Blending Mode
Model Details
Checkpoints (5)
realvisxlV50_v50LightningBakedvae.safetensors
LoRAs (2)
HyperSD\FLUX.1\Hyper-FLUX.1-dev-8steps-lora.safetensors